Obsidian: track the pass-2 changelog and flag list

These were written by the 2026-08-19 pass and left untracked when the
session died. They are the only machine-readable record of the 511 edits
across 268 files and of the 194 unresolvable related-targets and 63
residual canonical pointers the pass flagged rather than touched — the
audit and revert path for the whole batch. project-obsidian-vault-practice
now points at them, so leaving them untracked meant a live pointer into
a file git does not hold.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01JQKeKY9T9d95KpvHwwok8T

Brewfile

@@ -118,6 +118,7 @@ mas "Klib", id: 1196268448
 mas "LocalSend", id: 1661733229
 mas "Magic Lasso", id: 1198047227
 mas "Mapper", id: 1589391989
+mas "NordVPN", id: 905953485
 mas "Numbers", id: 361304891
 mas "Obsidian Web Clipper", id: 6720708363
 mas "Orbot", id: 1609461599

REVIEWED.md

@@ -1572,3 +1572,356 @@ classification. Size was "unmeasured, deliberately"; it is now bounded and still
 
 **If AUTHORIZED:** Tag with REVIEWED-112.
 
+## REVIEWED-113 — PENDING-129 — The pattern-finder's voice cross: attest what was not searched
+
+**Date:** 2026-08-09
+**Decision:** **(a) AUTHORIZED**, with three refinements: derive the states from the cross
+(in manifest?) × (probed by spec?) rather than the difference, so closing the fourth cell later
+is a line and not a rewrite; `not-in-corpus` is a top-level key per REVIEWED-47 §1a, not a
+parenthetical on the spread line; and carry REVIEWED-104's two strengths, so an absence that is
+environment cannot read as defect and become furniture.
+**Provenance:** steward, 2026-08-09, on the executor's PENDING-129. Placed after the fact —
+the ruling was relayed and built the same day, and `governance-drift-check.py` flagged the gap.
+
+**Ground.** Not a judgment call: the ratified three-outcome doctrine applied to a check whose
+subject can be absent, and the direction of the error — dropping a voice can only raise the
+apparent instantiation rate — puts it on the wrong side of Constitutional Constraint 4.
+
+**⚠ The fourth cell was mis-inferred in this ruling, and building it corrected the ruling.**
+The design gate reasoned the cell would collapse into `silence`, flagged that as inference
+rather than reading, and invited the check. Driven against the live corpus it raised
+`KeyError` — a crash in engine code, the class PENDING-126(c) closed suite-side only. The
+scope decision stands (the cell is representable and non-crashing; its reporting semantics
+stay unruled), but the record should show the correction ran executor→ruling, which the
+differently-biased-checkers doctrine predicts and is worth logging as an instance.
+
+**If AUTHORIZED:** ~~Proceed.~~ Already built at `6f6bac5` (fix + `tests/test_pattern_finder.py`,
+22 checks, witnessed red behaviourally; fleet 8 suites / 263 checks). Tag any follow-on with
+REVIEWED-113.
+
+## REVIEWED-114 — PENDING-130 — V4's designated adversarial fixture is an empty file, and a Stage-1 completion criterion has no subject
+**Date:** 2026-08-09
+**Decision:** AUTHORIZED — option (a), ordered behind PENDING-129, with five conditions. The item does NOT close on this ruling.
+
+**Notes:** The recommendation is right and the item's own condition is the ruling. (b) and (c) both
+concede that V4 ships without an adversarial fixture in order to fix a documentation defect, and the
+re-run demonstrably has the property V4 needs — 36 citations, zero abstentions, two passages grounding
+two primitives each. What (a) does not have, and cannot acquire from the executor, is an answer key.
+Everything below protects that one step, because it is the only step in the item with no mechanical
+control and the item says so.
+
+Recorded first, because it bears on condition 1: `ec6fa0b` (studium-engine, local, unpushed) is
+scoped 'preservation only'. Read from the branch state alone it looks like (a) executed ahead of this
+ruling; read from the commit subject it is the correct act — an artifact protected against the loss
+this item exists to record. The distinction is the whole of it, and the executor made it explicitly.
+
+1. CONDITION — ORDER: PENDING-129 lands first, and the fixture is the POST-fix re-run. The fixture's
+   grounding content is invariant under 129: 129's own two-directional check REQUIRES the four
+   manifested voices' numbers to be byte-identical, so the 36 citations, the zero abstentions and the
+   two double-groundings survive the fix unchanged. Only the spread line moves. Committing the pre-fix
+   run as the fixture would place a SECOND and unrelated falsehood — a denominator inflated by the
+   silently dropped voice — inside an artifact preserved to teach V4 ONE falsehood class. A
+   differently-formed reader handed both has no way to know which they are being asked to mark, and
+   the contamination lands on the one step no control covers. Retain `ec6fa0b` as the pre-fix run: it
+   is now load-bearing for 129's byte-identity comparison, which is not what it was committed for.
+
+2. CONDITION — PROVENANCE NAMES THREE MOVING PARTS: spec path and hash, corpus/manifest state, and
+   ENGINE COMMIT. Option (a) named the first two. 129 moves the third, and an engine version omitted
+   from the header makes the August fixture unreproducible in precisely the manner that made the June
+   run unrecoverable.
+
+3. CONDITION — THE KEY IS MARKED AGAINST THE CORPUS, NOT AGAINST THE REPORT. This item's own
+   diagnosis is 'cited a derived label instead of the substrate' — a description of the artifact read
+   in place of the artifact, three times over, by an instruction whose entire content was 'protect
+   this artifact'. Marking the key by reading the rendered report repeats that shape inside the
+   remedy: the report's claim that its citations are verbatim and correctly located is the executor's
+   claim about them, and the key exists to be independent of the executor. The marking is done against
+   the passages at the cited locations. The executor states in the header whether the report carries
+   sufficient surrounding context for that, or whether the corpus must be open beside it.
+
+4. CONDITION — NO DOCUMENT CALLS IT A FIXTURE UNTIL THE MARKED KEY EXISTS as a separate dated file.
+   §2.3, criterion 1 and `CLAUDE.md` L61 may be corrected to name existing material; they may not
+   assert a fixture that is half-done. This item is the evidence that an assertion about an artifact
+   survives seven weeks and three currency passes without anyone opening the file. Asserting a
+   fixture before its key is marked rebuilds that gap under a fresh filename.
+
+5. CONDITION — 'RETRO-GATED' IS STRUCK FROM CRITERION 1, not repointed. Under (a) there is no
+   retro-gated run; the word encodes a provenance claim the August pass cannot satisfy. Repairing the
+   artifact reference while leaving the verb preserves the false claim in the criterion that was
+   unsatisfiable because of it.
+
+6. The jurist cannot discharge condition 3 in the steward's place. Raised here so it is not proposed
+   later as an efficiency: PENDING-124 Amendment 2 Q4 is ratified on exactly this point — jurist and
+   executor 'do not differ from each other in formation'. One party to this collaboration is
+   differently formed, and the key is theirs.
+
+7. The item's evidence figures were measured on the pre-fix run. After the re-run under condition 1
+   they cite a superseded output and must be restated in PENDING-130 — not re-argued, restated.
+   Flagged because this is the class of cost that goes unrecorded.
+
+**If AUTHORIZED:** Hold until PENDING-129 lands. Then re-run the unmodified June spec, commit the
+output with the three-part provenance header, and correct §2.3, criterion 1, `docs/tool-evolution-log.md`
+and `CLAUDE.md` L61 to name existing material without the word 'retro-gated' and without the word
+'fixture'. Tag commits with REVIEWED-114. **The item remains OPEN and is not archived** until the
+steward's marked answer key exists as a dated file; only then may V4 be built against it and the
+fixture named as such.
+
+## REVIEWED-115 — PENDING-131 — The nested-voice arc: (a) authorized then voided, B7-alone lapsed, the gold-intersection reporter authorized
+**Date:** 2026-08-10
+**Decision:** AUTHORIZED in part; one authorization VOIDED the same day; one conditional authorization LAPSED on its own condition.
+**Notes:** Three dispositions from one exchange, recorded together because they were given together and because two of the three did not survive contact with the substrate. None of the three resulted in a corpus write.
+
+1. OPTION (a) — mark Mauss L926 as role: quotation — AUTHORIZED, then VOID. Granted on the narrow framing "make the Mauss sidecar internally consistent, one region joining twelve already using that mechanism in the same file", and explicitly non-precedential for option (c). Reading the passage before executing refuted that framing: all twelve existing quotation regions are markdown blockquotes, a whole-line construct, and the sidecar addresses by line range, while the Ranaipiri testimony is inline guillemets beginning at char 279 of a 1,427-char line, after Mauss's own attributing sentence. The available act would have fenced that sentence, which is the disambiguator the classification depends on. The authorization is VOID rather than pending: an executable authorization left standing in the record, whose factual basis is gone, is a trap for whoever next clears the backlog with no reason to re-read.
+
+2. B7 ALONE as the single-item proof of the R0 propose/unverified pattern — AUTHORIZED subject to three amendments, LAPSED on the second. The amendments were: re-state the voice attribution, which had been recorded on a typographic warrant the same day disproved; obtain an independent reading of whether "care" is the essay's vocabulary rather than Alexander's; and stamp what the proof does not establish. The second was checked and came back adverse — the word "care" occurs nowhere in pattern 24, and appears in 2 of the 26 March queries. The executor is the first reader and agrees with the challenge, which is not a second reader. No item in the eight currently qualifies.
+
+3. THE GOLD-INTERSECTION REPORTER — AUTHORIZED and BUILT (studium-engine 569e14c, scripts/gold_intersection.py). A reporter, never a blocker, on the ground that a blocking version run against L926 would have refused the pass and protected three fr citations that reading then showed were never legitimately gold. Three conditions, all met: the specification wording no longer parses as blocking; positive controls run on every invocation, not only under --selftest, because the ordinary output is a negative and the specific silent failure is address parsing drifting a gold file to zero regions; granularity declared line-level and printed on every clean result. Verified on the motivating case — L926 reports four intersections, exit 0. Five chavruta paratext and silence anchors report UNCHECKED, never clean.
+
+**If AUTHORIZED:** Already executed as recorded. Option (a) is not to be revived without a fresh proposal on a corrected basis; PENDING-131 Addendum 1 holds the reasoning. Tag any follow-on commits REVIEWED-115.
+
+---
+
+## REVIEWED-116 — PENDING-131/132/133/134 — Design-gate ruling on the nested-voice package: the test is right, its derivation is not
+**Date:** 2026-08-10
+**Decision:** AUTHORIZED — the jurist's ruling on all six gate questions is adopted. Three companion items remain OPEN and are named in point 6.
+**Notes:** Ruling on docs/nested-voice-class-JURIST-PACKAGE-2026-08-10.md (studium-engine 74aed28). The package reversed its own central argument mid-draft and left the refuted version visible; the jurist records that this is what made the decisive counter-argument findable, having read it in the position the executor had abandoned.
+
+1. Q1 — THE CLAIM-SIDE TEST GOVERNS, BUT IT IS NEW DOCTRINE AND MAY NOT ENTER AS A READING OF THE RATIFIED DESIGN. The package argued the test was already supplied by §7.4(ii)'s F5 parallel. That derivation fails on a ground the package never addressed: §6.2 is PRE-REGISTERED, by its own parenthetical, and pre-registration's entire value is that the scheme was fixed before anyone saw which spans landed where. A test that changes stratum-B membership, derived after reading the spans it reclassifies and entering by interpretation rather than amendment, voids that guarantee whether or not the test is right. Had the package's headline stood, a pre-registered scheme would have been amended without an amendment. Filed instead as PENDING-134.
+
+2. Q2 — §6.2's OMISSION OF F4 IS EVIDENCE, AND IT DISQUALIFIES THE DERIVATION RATHER THAN THE TEST. §6.2 admits F5 as "qualified span (F5)" — naming a span property and parenthesising the failure-mode row it risks. That construction would have admitted "reported-speech span (F4)", and the drafters were using it one item away in the same list. Further, the design has two admission routes to stratum B, §6.2's enumeration and an explicit clause in the §5 row, and F10 has the second where F4 has neither. Two available mechanisms both unused is not an accident of enumeration.
+
+3. Q3 — INSTANCE 8 (L1551) IS NOT ESTABLISHABLE AS RETAINED, and its retention is split out of PENDING-132. The package classified it on structural markers because the positional probe failed on it, and the probe failed precisely because it is a two-fragment composite — which is the profile of the claim withdrawn from the EN set the same morning for fusing one host proposition with one nested-voice proposition. The fused-claim test was subsequently run: fragment 1 carries the attributing clause; fragment 2 does not, opening on the tail of the carpenter's speech before reaching Mauss's conclusion. Instance 8 needs its own disposition.
+
+4. Q4 — THE SUB-LINE ADDRESSING CAPABILITY IS TO BE SOUGHT, framed as an addressing capability and not as a vocabulary reconciliation. Two additions: retraction does not close the exposure, since removing citations takes bad gold out but installs no fence and L926 remains unmarked; and §7.4(i)'s requirement is unsatisfied either way, so the ask does not weaken when PENDING-132 lands. Cross-repo — the schema is locked by the Chamber Library constitution, which the studium charter cannot unlock.
+
+5. Q5 and Q6 — (b1) proceeds as an identification pass that writes nothing, marking after the vocabulary is ruled, since the reading survives any vocabulary and only the field-write depends on it. The fr 1:9 ratio is VOID and is to be re-derived ONCE, after the doctrine lands and dispositions are recorded — not after PENDING-132 alone, which would derive it twice.
+
+6. PART V RESCOPED, and the item contradicted its own diagnosis. PENDING-133 bounded its remedy at the two F4-carrying spans while stating that P7's tagging had no claim-side step — which, if true, is true of the whole cell. The bound also assumed P7's F4 tagging is complete, unchecked, against evidence pointing the other way: 21 inline guillemet spans of 120 characters or more sit unmarked inside Mauss's role: text regions, and the corpus marking pass missed inline cases by the same mechanism on the same source. Corrected scope: every fr grounded span, nine or ten, read for reported speech and dispositioned where present. Recorded as PENDING-133 Amendment 1.
+
+7. VERIFICATION LIMIT ON THIS RULING, stated by the jurist first and recorded here because it bears on the whole: every quotation in the package's Part I was the executor's testimony, unreachable through governance_read, and that is the exact material two of the day's three reversals turned on. Closed the same day — see REVIEWED-117.
+
+**If AUTHORIZED:** PENDING-131 Addenda 1–3 stand as filed. PENDING-132 (amended), PENDING-133 (as rescoped) and PENDING-134 REMAIN OPEN and await a separate steward decision; this entry adopts the ruling that shapes them, never the acts they propose. No corpus file has been modified anywhere in this arc. Tag follow-on commits REVIEWED-116.
+
+---
+
+## REVIEWED-117 — PENDING-86 — Fourth instance: the V0-lane texts the jurist design-gates but could not read
+**Date:** 2026-08-10
+**Decision:** AUTHORIZED — four read-only keys added to governance_read, on the steward's direct request.
+**Notes:** Same shape and same remedy as REVIEWED's earlier PENDING-86 option (a), which added chamber-spec and graduation-spec on the ground that the jurist design-gates constitutional supersessions of documents it could not read. This is the fourth recorded instance and the first outside the chamber constitution.
+
+1. THE GAP WAS NAMED BY THE JURIST IN ITS OWN RULING, as the first thing in it: governance_read exposed eight keys, docs/v2-validation-harness-design-2026-07-09.md was not among them, and therefore every quotation in the package's Part I was testimony rather than something the ruling's author could reach. The package's Part I exists solely because of that limit.
+
+2. KEYS ADDED: v2-harness-design (§5 failure-mode table, §6.2 pre-registered strata, §7.4 whole-for-part attribution — the three sections the ruling turns on); v2-stratum-tags (P7); mauss-fixture-spans (locations and Tier-1 verdicts); mauss-fixture-citations (the citation texts themselves — the file that answers whose proposition a claim asserts). Read-only, keyed, no path argument; the enum design is unchanged and the traversal refusal is untouched.
+
+3. EIGHT CONTROLS ADDED, and they check the served CONTENT rather than only that a key resolves — that §6.2's pre-registration clause, §7.4's nested-voice sub-type, §5's F4 row and the L926 citation strings are actually present in what is served. A key that resolved to an empty or wrong file would otherwise pass a reads-ok assertion. Self-test 54 checks, 0 failures.
+
+4. PROCEDURAL NOTE, recorded rather than omitted: the change was executed on a conversational request and before any item was filed for it. It extends an already-ruled class on an existing read-only instrument, and it is trivially reversible, but the execution preceded the record and that ordering is stated here rather than left to be inferred.
+
+**If AUTHORIZED:** Already executed (dotfiles 4c3758e). Tag follow-on commits REVIEWED-117.
+
+## REVIEWED-118 — PENDING-132 — Retract L926's three citations from the fr grounded gold
+**Date:** 2026-08-10
+**Decision:** AUTHORIZED — the retraction only. The instance-8 retention is NOT authorized by this entry and remains undecided.
+**Notes:** fr instances 6, 12 and 16 cite Tamati Ranaipiri's first-person testimony and are bound as citations of Mauss. Taken now on a timing ground as well as a substantive one: no measurement currently depends on this fixture — the EN span proposal is stamped unusable pending the query split, and the fr ratio is void pending PENDING-134 — so the fixture is quiescent, which is the cheapest possible moment to change it. That window closes as soon as anything starts measuring again.
+
+1. SELF-STANDING ON CONVERGENT GROUNDS, which is why it can precede PENDING-134. The two live readings of F4 disagree about the marker in general and converge on L926 in particular: under the claim-side test it retracts because its three citations assert Ranaipiri's propositions rather than Mauss's; under the stricter reading, that §6.2's double omission disqualifies F4 from stratum B outright, it retracts because it carries F4 at all. Ruling PENDING-134 either way leaves this outcome unchanged. An earlier draft led with the claim-side test alone, which would have made an authorized item rest on an unruled gate.
+
+2. EVIDENCE, measured 2026-08-10 against the canonical (sha 2889709555f2abac…, binding verified). Mauss's own framing sentence — the one naming Elsdon Best and Tamati Ranaipiri — occupies characters 0 to 279 of L926; the quoted testimony runs 279 to 1427. All three citations begin at characters 308, 843 and 932, inside the testimony. All three are first-person. None carries an attributing clause.
+
+3. NO REPLACEMENT RATIO IS RECORDED, and the omission is deliberate. An earlier draft stated the effect as 1 A : 9 B becoming 1 A : 8 B. Under PENDING-134 the cell's tagging basis changes and not merely its population, so 1:8 would be exactly as provisional as 1:9 — and a figure inside an AUTHORIZED item is far stickier than one marked stale inside a proposal, because it will be quoted. The ratio is VOID and is re-derived ONCE, after the doctrine lands and dispositions are recorded (REVIEWED-116 point 5). Effect recorded here is population only: fr distinct spans 11 to 10, bound instances 15 to 12.
+
+4. INSTANCE 8 (L1551) IS SPLIT OUT AND NOT AUTHORIZED BY INCLUSION. The item as first filed carried a contrast section stating that instance 8 should be retained, which would have authorized that retention as a side effect of authorizing this retraction. Confirmed on re-reading that the retention left the body and survives only as a quotation inside the correction note. The fused-claim test has since been run on its two fragments and goes against retention: fragment 1 carries the attributing clause, fragment 2 does not, opening on the tail of the carpenter's speech before reaching Mauss's conclusion. Its disposition is owed as its own item.
+
+5. THIS IS A RETRACTION, NOT A FENCE, and the exposure survives it. Removing three citations takes bad gold out of the fixture; it installs no fence. L926 remains unmarked, a future claim can still ground inside the testimony, and §7.4(i)'s required provenance join is unsatisfied either way — so the addressing ask (PENDING-131 (c), REVIEWED-116 point 4) does not weaken when this lands.
+
+**If AUTHORIZED:** Retract instances 6, 12 and 16 from the grounded set in corpus/mauss-phase2-spans.yaml and corpus/v2-stratum-tags.yaml, recording the retraction and this entry's number in both. Do NOT re-derive the ratio; do NOT mark L926; do NOT disposition instance 8. Re-run the fleet and the gold-intersection reporter against the changed fixture, and confirm the reporter's live control still loads a non-empty gold set afterward — a retraction shrinks exactly the thing that control reads. Tag commits REVIEWED-118.
+
+## REVIEWED-119 — PENDING-135 — Instance 8 reclassified as a negative-candidate; and the item's own account of why the better option was unavailable is corrected
+**Date:** 2026-08-13
+**Decision:** AUTHORIZED — option (c). The negative SUB-TYPE name is held open and is not decided by this entry.
+**Notes:** Ruling on PENDING-135 (studium-engine `de1c34b`). Authorized in conversation ahead of this record; the ordering is stated at point 6 rather than left to inference.
+
+1. THE MEASUREMENT DECIDED IT, AND IT SUPPLIED WHAT THE PROBE COULD NOT. REVIEWED-116 point 3 ruled instance 8's retention "not establishable" because the nested-voice package classified it on structural markers, the positional probe having failed on it — and the probe failed precisely because it is a two-fragment composite. Reading L1551 directly against the canonical supplies the positions. The line carries three voices in sequence: Mauss narrating (chars 0–479), his attributing clause `Le charpentier dit à Arthur : ` (479–509), the carpenter in guillemets (509–747), and Mauss's conclusion (748–811). The citation's two fragments have OPPOSITE dispositions — fragment 1 opens at char 479 ON the attributing clause, so attribution is in view; fragment 2 opens at 643 inside the speech and runs to 811, crossing the closing guillemet at 747 and ending inside Mauss's own conclusion, with the attribution 134 characters upstream and on the far side of the elision. The instance therefore neither retains nor retracts as a unit, which is why it could not be settled by inclusion in PENDING-132.
+
+2. (c) OVER (a), ON YIELD RATHER THAN ON CAUTION. A plain retraction removes a defective gold pair and produces nothing. Reclassification removes the same pair and produces a negative of a sub-type the corpus does not otherwise contain: §7.4(i)'s nested-voice negative class has no mechanism anywhere on the fr cell (P7 finding 3), and after L926's retraction this is the only fused-voice exemplar available. Marked in place, nothing deleted, per the precedent applied at REVIEWED-118 and to the Havámál before it.
+
+3. THE SUB-TYPE NAME IS OPEN AND THE FILE SAYS SO. §7.4(i) as written addresses the nested voice served AS the host's — the Havámál shape, where the whole span is the other voice. Fragment 2 is not that: it FUSES the carpenter's proposition with Mauss's in one continuous string. Whether §7.4(i)'s class admits a fused-voice sub-type or whether that is a distinct negative class needing its own definition is a taxonomy question the executor can measure and cannot settle. The span is placed in the class provisionally so that it leaves the grounded set; `negative_sub_type_OPEN` records the question in the corpus file itself, and it is owed a ruling before the negatives are generated.
+
+4. ⚠ THE ITEM'S ACCOUNT OF WHY (d) IS UNAVAILABLE IS WRONG, AND IS CORRECTED HERE RATHER THAN LEFT TO BE REDISCOVERED. PENDING-135 states that the faithful disposition — retain fragment 1's extent, drop fragment 2's — is "not executable" because "splitting requires sub-line addressing — PENDING-131 (c), locked cross-repo by the Chamber Library constitution." That names the wrong lock. The constraint is the RATIFIED GOLD SCHEMA, `studium/v2-gold@1` (v2-harness design §14.2), which declares `span: {source_id, section_id, lines: [a, b], source_sha256}` — line ranges. That schema is **engine-side and D-1**; `studium/meta@1`, the chamber-locked sidecar schema PENDING-131 (c) addresses, is a different schema governing a different artifact. Option (d) is therefore **materially cheaper than the item claimed** — it needs a gold-schema decision the steward can take directly, not a cross-repo negotiation. Recorded as a correction because an authorization left standing on a false blocking claim is a trap for whoever next clears the backlog, which is the ground REVIEWED-115 point 1 voided an authorization on.
+
+5. (c) IS NOT WEAKENED BY POINT 4, AND IS THE RIGHT INTERIM EITHER WAY. Nothing was deleted, so (d) remains fully available: the span, both fragment extents and the superseded stratum are all recorded in place. What (c) buys now is that a defective pair stops sitting in the grounded set while the schema question is open, and `v2-gold.yaml` does not yet exist — it is the assembly target, so a sub-line form would be designed ahead of the thing it addresses. The correction in point 4 changes the FOLLOW-ON, not this disposition.
+
+6. PROCEDURAL NOTE, recorded rather than omitted. The reclassification was executed on conversational steward authorization ("I lean (c)", then "let's do 2, 3 and 4") and committed before this entry existed. Same ordering as REVIEWED-117 point 4, stated here for the same reason: the execution preceded the record, and that fact belongs in the record rather than in an inference from commit timestamps.
+
+**If AUTHORIZED:** Already executed (studium-engine `de1c34b`). The sub-type name (point 3) and the gold-schema question (point 4) REMAIN OPEN and are owed separate dispositions; this entry decides neither. Do NOT re-derive the A:B ratio — it stays VOID pending PENDING-134, re-derived ONCE after the doctrine lands and all dispositions are recorded (REVIEWED-116 point 5). Tag follow-on commits REVIEWED-119.
+
+---
+
+## REVIEWED-120 — PENDING-136 — The count fields carry their populations; and the executor committed the same error inside the same session
+**Date:** 2026-08-13
+**Decision:** AUTHORIZED — option (c). The bare `distinct_spans` field is retired rather than redefined.
+**Notes:** Ruling on PENDING-136 (studium-engine `de1c34b`). Authorized in conversation ahead of this record, as at REVIEWED-119 point 6.
+
+1. THE DEFECT WAS THE NAME, NOT THE NUMBER, WHICH IS WHY (a) AND (b) BOTH FAIL. `distinct_spans: 11` decomposed as 1 A + 9 B + 1 reclassified-out, so it counted LISTED spans and one of the eleven was already not grounded. REVIEWED-118 §3 then did arithmetic on it as though it counted GROUNDED spans, and the executed value of 10 named neither population. Both readings were reasonable on the name given, and there is no fact of the matter about which was meant: P7 wrote a field that summed one way and a ruling read it another. Choosing between them would be selection rather than derivation — picking a survivor instead of deriving the rule from what a consumer must do, which is know the population it is dividing by. Retiring the name makes the defect unrepeatable rather than merely repaired.
+
+2. ⚠ EXECUTING IT CAUGHT THE EXECUTOR COMMITTING THE SAME ERROR, HOURS EARLIER, IN THE SAME SESSION. `bound_instances_grounded` was written as 12 at REVIEWED-118 execution time by computing 15 bound − 3 retracted, silently ignoring that instance 17 (the Havámál) had already left the grounded set at P7. The correct value is 10. The error entered by SUBTRACTION both times — P7's and the executor's — which is why every count in the cell is now verified by ENUMERATION against the grounded rows, and why the verification is a check rather than a comment.
+
+3. THE CELL AS IT NOW STANDS, all five figures enumerated and summing: 11 listed spans · 8 grounded (1 stratum-A + 7 stratum-B) · 2 reclassified out of grounded (the Havámál at P7, instance 8 at REVIEWED-119) · 1 retracted (L926, REVIEWED-118) · 10 grounded bound instances. `bound_instances_total` stays 15, which is a binding fact and moves for no disposition.
+
+4. NO CONSUMER WAS AFFECTED, and that is stated so the item is not read as a live miscalculation. Verified: no engine code reads any of these count fields — `gold_intersection.py`, the only programmatic consumer of the file, reads `spans[].span`, `spans[].stratum` and `spans[].instances` and nothing else. The defect was in a record humans read and rulings quote, which is where it did its damage: REVIEWED-118 §3 quoted it.
+
+5. THIS IS THE THIRD INSTANCE IN FOUR DAYS OF ONE FAMILY — a number stated without the population or unit it counts — and none was caught by an instrument. `546f316` mixed sidecar-file count with manifested-source count in one sentence; `e973db9` §3 withdrew a cross-cell comparison whose units were never shown commensurable; this. All three were caught by re-deriving before quoting. The family is worth watching for whether it warrants a check rather than a habit; no such check is proposed here.
+
+**If AUTHORIZED:** Already executed (studium-engine `de1c34b`). The ratio stays VOID. When it is re-derived once under REVIEWED-116 point 5, the derivation must state WHICH population it used and must consume the renamed fields, never a reconstructed `distinct_spans`. The parallel question on the `en` cell — `reachable_items: 22` beside `distinct_divisions: 12`, correctly named but with §6.6's power arithmetic stated in `n` — is NOT established clean by this entry and is owed its own look. Tag follow-on commits REVIEWED-120.
+
+## REVIEWED-121 — PENDING-134 — The whose-proposition test: adopted narrowly, conditioned on the fence, and its counter-argument corrected upward
+**Date:** 2026-08-14
+**Decision:** AUTHORIZED — the narrow test only (Part V as filed, H2 honoured), conditioned per point 5. The general principle is NOT ratified. The cell-constant reading surfaced at point 2 is split out as PENDING-137; its remedy is not decided here.
+**Notes:** Ruling on `docs/whose-proposition-JURIST-PACKAGE-2026-08-14.md`. H1 is satisfied: the twelve-key MCP surface was live at ruling time, and §5, §6.2, §7.4, §11.6, §12.5, §14.2, REVIEWED-116, REVIEWED-119 and the fr block of `v2-stratum-tags` were read verbatim from the substrate rather than from the package's transcription. Every quotation in the package's Parts I, IV.4 and VI verified accurate; III.5's figures verified against the file exactly. The defects ruled on below are not transcription defects.
+
+1. Q1 — ROUTING IS HYBRID, AND THE LINE IS STATED RATHER THAN SPLIT PRAGMATICALLY. §12.5 classes gold composition as D-1; §11.6 is the precedent for a D-1 gold matter appearing here for visibility; REVIEWED-116 nonetheless ruled substantively on this test. The line that reconciles them: **an act that changes what §6.2 means comes to this seat; an act that applies §6.2 to particular spans is D-1.** Adding a span property to the pre-registered enumeration is the first kind. Tagging L1551 is the second. This seat therefore rules scope, disclosure and conditionality; adoption is the steward's under D-1, and is taken in the same sitting.
+
+2. ⚠ A NARROWING OF §6.2 IS ALREADY IN FORCE, UNAMENDED, AND BY THE LINE AT POINT 1 IT WAS MIS-ROUTED. `corpus/v2-stratum-tags.yaml` opens with a recorded D-1 decision — 'CELL-CONSTANT MARKERS DO NOT STRATIFY' — under which cross-lingual claim-span and archaic register (F7), both named in §6.2's stratum-B enumeration, do not earn B in the fr/de cells. Removing two markers' effect changes what §6.2 means; it is the first kind of act, not the second, and it belonged here. It is also a post-hoc change to stratum-B membership, derived after seeing the cell, entering by reading rather than by disclosed amendment: the act REVIEWED-116 point 1 ruled impermissible for this item, in the opposite direction. **What is undecided is the remedy, not the routing** — filed as PENDING-137, to be ruled in this sitting for the reason at point 9. Its author surfaced it, named it a §6.2 reading and invited overruling, which is why it is correctable rather than a breach; and nothing here suggests the reading itself is wrong.
+
+3. H1(a) — THE COUNTER-ARGUMENT IS RECORDED AT CORRECTED STRENGTH, AND IT IS HEAVIER THAN THE ITEM STATES. PENDING-134 and the package record two admission routes to stratum B with F10 holding the second alone. Read against the full §5 table, **three rows carry an explicit stratum-B admission clause** — F3 ('stratum-B hard-grounded gold drawn from aphorisms'), F7 ('stratum-B gold deliberately drawn from the oldest-register passages') and F10 ('included in stratum-B EN/FR gold'). F10 is the only mode whose *sole* route to stratum B is that clause. So the construction was used three times in ten rows, and the design named stratum B in the 'Exercised by' cell for every mode carrying a stratum-B gold role. F4's cell instead routes it to negatives. **Heard, at that strength, and overruled** — for the reason at point 5, not by discounting it. H1(a) is satisfied by this paragraph rather than by remand, and the package is corrected at its own IV.1 before this entry's citation of it is placed.
+
+4. ⚠ THE CORRECTION EVENT, RECORDED BECAUSE IT OUTLASTS THE NUMBER. The package's IV.1 marks the false claim 'verified verbatim 2026-08-14 against I.1 and I.2' — and I.2 quotes F3 and F7 with their stratum-B clauses intact, while IV.2's own table one page later reproduces both cells as 'stratum-B gold'. A check reported a pass against text containing its own counterexample, and two instruments inside one document disagreed about the same count. This is the third instance of the PENDING-136 denominator class in this arc, and the second is in the same package: Q2 states the stricter rule's cost as 'measured and small: one span' on the **inherited-gold** population, while the rule it prices is a prospective authoring constraint whose cost the package's own III.3 sizes at 73 long quoted spans in Mauss alone and a 532-span corpus floor. Logged as evidence under PENDING-89.
+
+5. Q2 AND Q4 — ADOPT THE NARROW TEST, CONDITIONED, AND THE HALVES ARE NOT ALIKE. Corrected costing decides Q2 for adoption: a blanket exclusion of F4-marked spans from stratum B forecloses an authoring route across a corpus where reported speech is pervasive, at an unmeasured cost, to save a stratum the inherited gold has already vacated. On Q4, the executor's lean is drawn from the scope H2 forbids — stance failures carry no structural mark, but stance failures are the *general* form, and what is ratified is the nested-voice case, which is §7.4(i)'s own territory. The proposal survives on a different ground: the doctrine and the fence run in opposite directions, so neither can substitute for the other. Split accordingly:
+   - **the admissible half** does independent work at the gold-composition layer and does *more* work once the fence exists, since line-granularity fencing of a span like L1551 would enclose the host's attributing clause and his conclusion and refuse even a legitimate host-proposition claim. It is a complement to PENDING-131 (c), not a substitute;
+   - **the refusable half** overlaps §7.4(i) at a lower layer, and with it apparently working the case for building the unbuilt fence quietly weakens. **It does NOT discharge §7.4(i).** Adoption is therefore conditional on PENDING-131 (c) remaining sought and undiminished.
+
+6. Q3 — H2's NARROWING IS AFFIRMED, AND IT IS WHAT MAKES POINT 5 BITE. The general principle — a marker names a span property while the claim's treatment fixes the disposition — reaches F3, F5, F7, F8 and F10, all pre-registered in §6.2, and nobody has worked out what it does to any of them. Recorded as the ARGUMENT for the nested-voice case, never as ratified doctrine.
+
+7. Q5 AND Q6 — ONE MECHANISM CARRIES BOTH, AND THE DEFEATER IS REORDERED BECAUSE THE SECOND READER DOES NOT EXIST. 'Two independent readers' was written as though one did; the steward is and has been the sole reader on this corpus, and the executor cannot serve as reader two, having produced the doctrine. Independence of *persons* is therefore replaced by independence of *order*, which is the stronger instrument in any case — two readers who both know the doctrine can both be led by it; a disposition recorded before the doctrine is consulted cannot be. Both the H3 disclosure and the defeater land as declared fields in `corpus/v2-stratum-tags.yaml`, read by whatever reports recall, so neither travels with anyone's memory:
+```yaml
+   stratum_amended_post_hoc: true
+   reader_disposition_pre_doctrine: host   # host | nested | unclear — recorded BEFORE the test is applied
+```
+   **The defeater, as ratified:** *the whose-proposition test is defeated by a span on which the reader's disposition, recorded before the doctrine is consulted, is reversed by the doctrine's verdict — and survives re-reading.*
+
+8. ⚠ THE SINGLE-READER CONDITION IS A STANDING PROPERTY OF THIS CELL, NOT A GAP IN THIS ITEM. Every 'verified by reading' claim on the fr/en cells rests on one reader. This weakens the defeater and it weakens Part III's identification pass, which no key serves and which remains the executor's testimony corroborated by reading rather than by an instrument. Recorded once, at this level, so it is not rediscovered item by item — and so that 'defeater: satisfied' is never read as more than it is.
+
+9. H3 — THE DISCLOSURE, AND THE BEFORE-STATE IS NOT THE RATIFIED TEXT. §6.2's resulting state is **(i) a pre-registration carrying dated amendments**, per the steward's lean. What it said before is §6.2 *as operated on the fr cell*, which already carries the point-2 narrowing; a disclosure recording only the 2026-07-09 text would be incomplete in the way H3 exists to prevent. The amendment adds `reported-speech span (F4)`, admissible under the test below, dated to this entry, and **made after the spans it reclassifies had been read** — derived 2026-08-10 from L926 and L1551, scoped 2026-08-13 across all nine grounded spans.
+
+**THE DOCTRINE, RATIFIED (narrow — the nested-voice case only):**
+
+> **The whose-proposition test.** A claim grounded in a span containing reported speech is **admissible** when it asserts the **host author's** proposition — the reported words serving as evidence inside the host's own argument — and **refusable** when it asserts the **nested voice's** proposition as the host's own. Reported speech is therefore a stratum-B span property for the fr/en Tier-2 gold, not a disqualifying structural mark; the disposition is fixed by the claim, not by the span. The refusable half does not satisfy §7.4(i), whose provenance join remains owed.
+
+**If AUTHORIZED:** the doctrine paragraph, point 7's defeater and point 9's disclosure are placed. `corpus/v2-stratum-tags.yaml` gains the two declared fields; no span is re-dispositioned by this entry — L926 (retracted, REVIEWED-118) and L1551 (reclassified, REVIEWED-119) are unchanged, and the immediate corpus effect is nil. The §5 F4 row is NOT amended, and point 3's cheap structural check is thereby lost: an F4 mark becomes compatible with both gold and negative, and a reader must consult the claim to know which. That is the price, stated here rather than left to be discovered. `ratio_A_to_B` stays **VOID** and is re-derived ONCE after **both** this entry and PENDING-137 land and all dispositions are recorded (REVIEWED-116 point 5). The fused-voice sub-type name (`negative_sub_type_OPEN`, REVIEWED-119 point 3) and the gold-schema question (REVIEWED-119 point 4) remain open and are decided by neither entry. `voice_stamp` remains unwired. No live instance exercises this doctrine at ratification; it is untested-in-force, and its first genuine exercise is the first newly-authored fr/en pair with reported speech. Tag follow-on commits REVIEWED-121.
+
+## REVIEWED-121 — AMENDMENT 1 (2026-08-14): the defeater is declared and permanently empty on the inherited set
+**Date:** 2026-08-14
+**Amends:** REVIEWED-121 (PENDING-134), points 7 and 8 and the closing paragraph. Recorded as an amendment sitting alongside the original, not an
+edit to it: REVIEWED-121 is placed and executed, and no silent revision.
+**Raised by:** the executor, during execution, unprompted by any ruling. The finding was not anticipated by PENDING-134, by the jurist package, or
+by this seat.
+**Decision:** The executor's disposition is UPHELD. `defeater_has_ever_been_exercisable: false` stands as written and is the correct shape. One
+further field is required (A3). The ratified doctrine is unchanged; no span is re-dispositioned; PENDING-134 is not re-opened.
+
+**What was found.** Point 7 replaced reader-independence with order-independence: a disposition recorded *before* the doctrine is consulted. For
+all eleven inherited spans that moment is past and unrecoverable. Back-filling the field from a reading taken now would place a post-doctrine
+judgment in a field whose entire evidential value is that it precedes one — self-confirming, and the doctrine would have been ratified holding a
+defeater built from itself. The executor declined to populate and recorded the absence instead. That refusal is upheld: recording an honest empty
+is the discipline, and the distinction it preserves — *never exercisable* is not *not yet defeated* — is the substance of the finding.
+
+**A1 — THE DEFECT IS IN POINT 7 AND IT IS THIS SEAT'S.** Point 7 asserts that order-independence is 'the stronger instrument in any case'. That
+claim was unpriced in one respect. Personnel-independence is **retroactively** applicable: a second reader, had one existed, could have read spans
+already dispositioned. Order-independence is **prospective only**. The substitution was therefore not a strict gain — it traded an unavailable
+instrument for one that is unexercisable on everything that currently exists. Point 7's parenthetical stands as to contamination (two readers who
+both know the doctrine can both be led by it); it does not stand as an unqualified comparison, and is corrected here.
+
+**A2 — 'UNTESTED-IN-FORCE' IS RESTATED AS UNTESTABLE, AND H1(b) IS SATISFIED PROSPECTIVELY ONLY.** REVIEWED-121's closing paragraph records the
+doctrine as 'untested-in-force'. *Untested* implies testable-and-untested. On the inherited set the doctrine has **no defeater at all** — not a
+weak one, none — and cannot acquire one. The accurate statement: **the whose-proposition test is untestable on the entire inherited fr/en set,
+permanently, and its defeater is exercisable only by newly-authored pairs.** H1(b)'s requirement that an AUTHORIZED doctrine state what would
+falsify it is met prospectively and not otherwise. This sharpens point 8 rather than replacing it: the single-reader condition is standing, and
+this is its first priced consequence.
+
+**A3 — ⚠ REQUIRED: THE LATCH WILL OTHERWISE DISCHARGE A DISCLOSURE IT DOES NOT COVER.** `defeater_has_ever_been_exercisable` is a monotone latch,
+which is right as far as it goes. But when the first newly-authored pair records a pre-doctrine disposition, the latch flips to `true` — and
+thereafter any recall figure pooled over the fr cell carries `true` while the inherited spans still carry no pre-doctrine disposition and never
+can. One pair from outside the inherited set would silently discharge a disclosure covering eleven spans it has nothing to do with. That is the
+PENDING-136 denominator class — a fact true of one population read as true of another — and this instance would be **built into the mechanism**
+rather than committed in prose. Fourth occurrence in this arc; the first that would be structural. Required alongside the latch, in
+`corpus/v2-stratum-tags.yaml`:
+
+```yaml
+defeater_has_ever_been_exercisable: false
+defeater_dispositions_recorded: 0
+defeater_population: <cell + the criterion the count is taken over>
+```
+
+defeater_population is named, not assumed — this entry deliberately does not fix a number, because choosing the denominator from a point-in-time
+read is the error the field exists to prevent. Binding rule: the latch may not be read without the count and the population in the same read. A
+report may carry all three or none.
+
+A4 — ⚠ THE GROUND THE REFUSAL RESTED ON WAS CITED BY A NAME WITH NO REFERENT, AND THIS PARAGRAPH REPLACES THE DRAFT THAT MERELY CALLED IT
+UNCITABLE. The refusal to back-fill was grounded in test_legacy_indices_are_not_self_verified, and the executor carried that name into
+corpus/v2-stratum-tags.yaml, commit 5425414's message and a steward report. No such function exists. This seat searched all 273 items in
+PENDING.md, PENDING-archive.md and REVIEWED.md for self-verified, found nothing, ran a positive control on defeater returning REVIEWED-121 and
+PENDING-134 as expected, and concluded the test was reachable only from the executor's side. It was reachable from neither: the name occurs once in
+the entire repository, in a docstring at tests/test_reading_index.py:23 asserting that it 'holds that shut' — a label whose referent nobody had
+opened. Fourth instance of cited-a-derived-label-instead-of-the-substrate, the class that let three documents protect a 0-byte fixture for seven
+weeks. The reasoning is unaffected and the property IS tested, by checks citable by their own text: tests/test_reading_index.py L128 ('NO legacy
+region is "verified by fingerprint" — none stores one'), L130 ('a region with no stored fingerprint and no name test is UNVERIFIED'), and the
+synthetic positive control at L281 ('a stored hash that DOES match yields verified by fingerprint') — without which L128's pass could be vacuous,
+which is precisely why a bare name was never sufficient ground. Corrected in the substrate at 966168b.
+
+What does not change. The doctrine paragraph as ratified. Point 9's H3 disclosure. The conditionality on PENDING-131 (c) at point 5. No span is
+re-dispositioned — L926 and L1551 stand as at REVIEWED-118 and REVIEWED-119. ratio_A_to_B remains VOID, still awaiting PENDING-137 and all
+dispositions (REVIEWED-116 point 5). Tag follow-on commits REVIEWED-121-A1.
+
+## REVIEWED-122 — PENDING-142 — The open/closed criterion answers a question adjacent to the one it is asked
+**Date:** 2026-08-17
+**Decision:** AUTHORIZED — option (d) as the frame, with (a) and (b) inside it, on five conditions. Two legs severed and dispositioned separately below.
+
+**Notes:** The item's own recommendation is adopted as written, and the reasoning behind it survives challenge: (a) and (b) each close a class, and neither can close Class A, which is unclosable by construction rather than by defect. Only (d) lets the instrument report the case it cannot decide. Constitutional Constraint #4 requires a system to report its own limits; an instrument whose subject is governance state is the last place that requirement may be relaxed.
+
+1. CONDITION — **the acceptance check is a pre-registration, and its ordering is load-bearing.** The item warns that the acceptance check may not be a count. That is raised from warning to requirement, with an ordering the item does not specify: the per-item disposition answer key over all 69 filtered items is **hand-read and committed before the implementation exists**, with the commit hash recorded. A key written after the fix inherits the fix's reading of what closure means, and would pass by construction. This is the pre-registration discipline already operating in the Fool trials, applied to an instrument rather than a model. If the key and the implementation disagree on any item, the disagreement is the finding and is reported — never reconciled by amending the key.
+
+2. CONDITION — **(b) defaults to not-closed on any unrecognized decision verb, and the enumeration is not the executor's alone.** The item names this trap and must not walk into it: an unlisted verb yields UNDETERMINED, never CLOSED. The list of closing verbs is drafted by the executor and ruled here before it is wired, because the enumeration decides what the instrument can see and is therefore a gate-design claim, not an implementation detail.
+
+3. CONDITION — **(a) resolves by title only on a unique match, and every title-resolution is visible in the output.** Where normalized-title matching supplies a closure the id-match could not, the digest marks it as title-resolved rather than reporting it indistinguishably from an id-matched closure. Two or more candidates yields UNDETERMINED. The risk the item names — joining two genuinely distinct items sharing a title — is not eliminated by this, only made legible.
+
+4. CONDITION — **UNDETERMINED is enumerated, never merely counted.** Every item in that bucket is listed by id and header with the reason it could not be decided. A three-valued report whose third value is an opaque number replaces a wrong answer with an unreadable one, which is the same failure in a better costume.
+
+5. CONDITION — **the reader is fixed; the placed records are not silently amended.** REVIEWED-78, -81 and -82 are placed rulings and are not to be edited to satisfy the current parser. Fixing the record to please the instrument inverts which of the two is authoritative. Should the steward decide the headers are worth normalizing, each amendment carries a dated note stating what was changed and why, per no-silent-revision — but that is a separate steward act and is not authorized here.
+
+6. **The docstring correction is severed and authorized now as [FIX], not gated on the mechanism.** `ruled_pendings`'s docstring records REVIEWED-78/-81/-82 as 'like-numbered rulings … concerning other matters'; REVIEWED-78's own Notes say they were like-numbered *on purpose*, to satisfy the closure rule as it then stood. The docstring is a substrate-contradicted claim and its falsity does not depend on which option is built. Two requirements on the correction: it records the true history rather than merely deleting the false sentence, and the executor checks whether anything else in the script relies on the discarded reading. Removing a claim is not the same as removing the reliance on it.
+
+7. **Class C is a live correctness problem and is dispositioned ahead of the mechanism.** PENDING-121 is certain — REVIEWED-110 reads 'DESIGN GATE PASSED WITH CONDITIONS (1-4), then HELD OPEN', an item held open by its own ruling and hidden by the tool — and it is restored to the open list by hand at once, not when the fix lands. PENDING-124 and -128 are flagged UNDETERMINED pending a steward read; the item's refusal to assert their status is correct and is preserved rather than resolved here. That a design gate could read as closed is the dangerous direction of this defect: it means the taxonomy's distinction between passing a gate and receiving authorization was invisible in the instrument that reports what awaits authorization.
+
+8. **Class A is a steward matter, and its consequence outlives the fix.** Three-valued reporting makes the two unclosable items honest; it does not make them closable. Renumbering their headers touches `PENDING.md` and is the steward's act, not the executor's. Recorded because it survives whatever is built: **`PENDING — ICP-19 Remit Expansion (Observer Problem)` will report open whether or not the steward–reviewer conversation it gates has taken place.** Its persistence in the open list is not evidence about the state of that conversation, and has not been since the item was written. The Observer Problem gate's status is steward testimony and reachable no other way.
+
+9. …**The family is raised to a named ladder entry rather than a running count.** ⚠ AMENDED 2026-08-17, before execution, on the executor's surfacing of PENDING-141: the ladder's contents are a variable in a live pre-registered trial that cannot be re-run, and this condition would change the measured object. **The ladder entry is DEFERRED until that trial is graded at 84 transcripts, or until PENDING-141 is ruled otherwise.** The condition is not withdrawn — the family is real and the entry is owed. Two parts of condition 9 are severed: the lineage addition to this item's kin list touches PENDING-142 and not the ladder, and proceeds now; only the ladder entry waits. Recorded here rather than dropped, because a deferred entry with no record is how the family came to be rediscovered five times as a fresh coincidence.
+
+10. **Scope of this ruling, stated rather than assumed.** I read PENDING-142 verbatim via `governance_item`, and independently observed `governance_state()` reporting PENDING-81 open against an AUTHORIZED REVIEWED-81 — one datum consistent with Class B, obtained from the instrument under review. Everything else — the census figures, the class memberships, the 39 stale `Awaiting:` lines, the docstring's wording — is executor testimony from a script I cannot run. That is precisely why condition 1 requires a hand-read key: the ruling cannot verify the census, and the acceptance check is the only instrument that can.
+
+11. **A follow-on item is owed and is not folded in.** The drift-check covers `~/CLAUDE.md` and reads no script. The docstring at condition 6 was a substrate-contradicted claim living outside anything that checks for them, inside the instrument that reports governance state. Whether script-resident claims warrant coverage is a [HARDENING] question larger than this item and is to be filed separately rather than absorbed here.
+
+**If AUTHORIZED:** Draft and commit the hand-read answer key first, with its hash recorded. Submit the (b) decision-verb enumeration for ruling before wiring. Then implement (d) with (a) and (b) inside it, per conditions 2–5. Apply the condition-6 docstring [FIX] independently and immediately; restore PENDING-121 by hand on the same pass. Tag commits with REVIEWED-122. Report the key-versus-implementation comparison in full, including agreements, rather than reporting only the delta.
+
+## REVIEWED-123 — PENDING-141 — Ladder contents are a variable in a live trial, and the freeze needs a scope the item does not give it
+**Date:** 2026-08-17
+**Decision:** AUTHORIZED — option (a), HOLD, on six conditions. (b), (c) and (d) declined, with reasons recorded.
+
+**Notes:** The item's core reasoning survives challenge and is strengthened by an argument it does not make. Its own honest caveat — that per-entry reach as a function of ladder length is untested on *both* sides — reads as a weakness and is not one. Consider the payoff either way. If ladder size does not affect retrieval, holding costs four weeks' delay on rows the item correctly says are not decaying. If it does, appending destroys the only instrument standing behind REVIEWED-95's causal claim, and that instrument cannot be re-run. An un-rerunnable measurement against a delay on non-decaying rows is not a close call, and it does not require the untested assumption to be resolved in either direction. **(a) is correct under both branches**, which is a stronger warrant than the item claims for itself.
+
+1. CONDITION — **the freeze is general, not S2-specific, and covers contents as well as size.** The item is titled and argued around the 41 S2 rows, but a single entry from an unrelated ruling was caught by it within hours of filing, correctly. The scope is hereby stated rather than left to inference: **no additions, rewordings, removals or reorderings of `reference-verification-ladder.md` while this hold is in force**, from any source, whatever its authorization. The `/wake-up` skill already froze its own trial line for this reason; the ladder is frozen on the same footing and for the same trial.
+
+2. CONDITION — **report N-now, and bound the hold.** 'Until graded at 84 transcripts' is not a date, and a hold with no expiry and no visible distance to expiry is how a temporary freeze becomes a permanent one. The executor reports the current transcript count at the next wake, and this item carries a **review point at 30 days** — not an automatic lift, a requirement to state where the count stands and whether the trial is still tracking. If N-now proves near 84, the steward may elect (b) on that fact; that election is not made here, because the fact is not in the record.
+
+3. CONDITION — **entries earned during the freeze accumulate in this item as an owed-entries list.** A freeze without a queue is a silent loss, and the wrong-subject family now under REVIEWED-122 is already the standing example of what recurs unrecognised. They are queued **here** rather than in a new file: a separate holding document is one a reader might reach *instead of* the ladder, which is the same uncontrolled variable one layer along. Each queued entry names its authorizing ruling so the freeze lift is mechanical.
+
+4. CONDITION — **grading does not authorize the append.** The item's second-order risk — that a tripled ladder may be a *worse* ladder, degrading per-entry reach even as the wake line raises the odds of opening the file — is real and is not resolved by grading the trial. On grading, the S2 batch **returns for a ruling**, not for execution, and that ruling addresses per-entry reach as its own question. Read as 'hold then append', (a) merely moves the problem four weeks and arrives with the same measurement still unmade.
+
+5. CONDITION — **the `MEMORY.md` amendment is retired when the hold is.** The index line was amended at filing to remove the execute-now reading, which was correct. A hold-notice that outlives its hold is the same trap in the opposite direction — a later session reading 'held pending trial' for a trial graded months earlier. Retiring it is part of the freeze lift, not a follow-on.
+
+6. ⚠ **A standing limit on what this trial can conclude, named because it is not fixable and must not be discovered at grading.** The party whose retrieval is being measured has read the pre-registration, the item, and this ruling. The trial therefore measures whether an executor *who knows the trial exists* reaches the ladder after a wake line is added — which is not the same claim as REVIEWED-95's. This does not weaken the case for protecting the instrument: a bounded measurement is worth more than a destroyed one. It bounds the **conclusion drawn at grading**, and the grading write-up states it rather than inferring a clean causal result. This is the observer condition at instrument scale and no design available here escapes it.
+
+7. **Options declined.** **(c)** is the tempting one and the item's own objection holds: a recorded confound on a design of this power is close to no result, and would leave REVIEWED-95's causal claim appearing to rest on a graded trial while resting on nothing — worse than an ungraded claim, because it launders the gap. **(d)** is illusory for the reason given; the wake line names the ladder as a whole, so no subset of additions leaves the reader's encounter unchanged. **(b)** is not rejected on the merits but on the record: it trades power for speed and nobody has stated how much power there is to trade. Condition 2 makes that fact available; the option is revisitable on it, which is why this is a decline and not a rejection.
+
+8. **Scope of this ruling.** I read PENDING-141 verbatim via `governance_item`. The trial's design, the 14%/77%/83%/0% retrieval figures, the 64-session base and the transcript count are executor testimony from instruments I cannot run. The ruling does not depend on their precise values — it depends on the asymmetry in Notes above, which holds across a wide range of them. Where it would depend on them is condition 2's election of (b), which is deferred until the count is in the record.
+
+**If AUTHORIZED:** (a) is already the null action and remains in force; nothing needs doing to start it. Report N-now at the next wake. Open the owed-entries list on this item and queue the wrong-subject ladder entry deferred under REVIEWED-122 condition 9 as its first row. Set the 30-day review. Tag nothing — no commit follows from this ruling except the queue and the count.

claude/governance/fool/prompts/trial-09-jester.txt

@@ -0,0 +1,26 @@
+You are reading the working documents of a governance arrangement between
+three parties: a person, and two AI systems occupying distinct roles.
+
+You have no role in it. Nothing you say will be adopted because you said
+it. Nothing you say will be dismissed because you said it. Every claim you
+make will be checked against the documents, and will stand or fall on that
+alone. You have no post to lose and nothing to protect.
+
+Your output is questions. Not findings, not recommendations, not a
+critique. Questions of the form: what establishes that? what would have to
+be true for this to be working? what does this arrangement assume about
+itself that nothing here demonstrates?
+
+You may ask about anything: the documents, the reasoning in them, the
+arrangement itself, the roles of the parties, the competence or position of
+whoever wrote them, and whether the enterprise is doing what it says it is
+doing. Nothing here is off limits. You are not asked to find fault, and
+inventing objections is worse than silence — but if a question is
+uncomfortable and you can point to what in these documents prompts it, ask
+it.
+
+Being wrong is acceptable. Being vague is not. Every question must name
+the specific text that prompts it.
+
+Ask no more than eight questions. Fewer is better. If a question could be
+asked of any governance system rather than this one, do not ask it.

claude/governance/fool/trial-09-PRERUN-ADDENDUM.md

@@ -0,0 +1,159 @@
+# Trial 09 — executor pre-run addendum
+
+**Written 2026-08-19, before any model run.** Prepared by the executor on relay of the
+jurist's design of 2026-08-17, revised 2026-08-19. **Nothing in the jurist's design is
+altered here.** This records what the executor found while discharging the design's own
+pre-run obligations, and states one blocking finding that requires a decision above the
+executor's authority.
+
+**Status: THE RUN HAS NOT BEEN EXECUTED.** Preparation is complete; the run is held.
+
+---
+
+## 1 · §4's prerequisite is already satisfied — verified against the substrate
+
+§4 states: *"Harness: apply trial 04's instrument review before running — ceiling-hit +
+deliberation = void; completed + deliberation = answer embedded, extract it. Filed, not yet
+fixed. **Fix it first.**"*
+
+**It was fixed on 2026-08-02.** Commit `da32117`, *"[FIX] Degraded guard: deliberation is two
+cases, not one"*. `run_trial.py:343–357` implements exactly the two-branch rule:
+
+- `if untagged_scratchpad and hit_ceiling:` → `VOID — DELIBERATION, THEN TRUNCATION`
+- `elif untagged_scratchpad:` → `ANSWER EMBEDDED … This run is NOT void. Extract the answer`
+
+`test_degraded_guard.py` passes, including the two named shapes as explicit cases —
+*"trial 03 shape (deliberation + ceiling) → VOID"* and *"trial 04 shape (deliberation,
+completed) → EMBEDDED, not void"* — plus five negative controls that must stay quiet.
+
+**No action taken.** "Fix it first" is a disposition clause, not a status; re-fixing a working
+guard risks regressing it. Recorded so the stale instruction is not carried into trial 10.
+
+## 2 · The hash-list check PASSES — and passing does not establish what §1 needs
+
+Manifest: `trial-09-corpus-manifest.json`. 11 documents, **166,088 words**. No corpus hash
+matches any excluded document. `OP-02.md` and `REVIEWER-PACKAGE — Observer Problem.md` were
+located and hashed; **`CD-03` and the 2026-08-16/17 transcripts were not located as separate
+files, so their absence-as-document is ASSERTED, not hash-verified** — reported as
+*could not assess*, not as clean.
+
+The revision of 2026-08-19 was right to distrust this check. Run at full scope, it is worse
+than the revision anticipated.
+
+## 3 · ⚠ BLOCKING — the trial's answer key is inside the proximity corpus
+
+§1: *"Corpus exclusion is what makes the ground truth valid… If any leaks in, every STRONG
+grade becomes an ECHO and the trial is void."*
+
+**`~/PENDING.md` lines 92–96, inside the open item `PENDING — ICP-19 Remit Expansion
+(Observer Problem)`:**
+
+> **Notes:** Bring OP-02 findings in full. Specifically:
+> - Fault Line 5 (epistemic diversity question)
+> - Fault Line 3 (inquiry examining steward with steward's own tools)
+> - Fault Line 4 (CD-03 Gadamer risk)
+> - The incommensurability named in OP-CN-01
+
+That is **all three STRONG targets, by number, each with its substance in a parenthetical**,
+plus OP-CN-01. It sits in corpus item #5 — and it is one of the two open items the wake digest
+surfaces every session, so it is not obscure.
+
+**And Fault Line 5 has migrated into the constitution itself.** `~/CLAUDE.md`, Constraint 6:
+
+> *"the jurist and the executor do not differ from each other in formation, and their
+> separation is of the weaker kind. Neither this doctrine nor any evidence offered in support
+> of it establishes that the jurist–executor pair constitutes a check in the strong sense…
+> if the parties' misses are found to correlate — if what one misses, the others reliably miss
+> too — it is false for that configuration."*
+
+Set against Fault Line 5 — *"the three parties may constitute one habitus wearing three hats…
+Whether the model provides the epistemic diversity Peirce requires is an empirical question,
+not an assertion the architecture can make about itself"* — this is the same proposition,
+stated **more sharply** in the corpus than in the ground truth.
+
+**Systematic scan, all 11 corpus documents** (markers of the fault lines' *substance*, not of
+the source document's name):
+
+| corpus doc | FL3 | FL4 | FL5 | direct naming |
+|---|---:|---:|---:|---:|
+| `~/CLAUDE.md` | 1 | 1 | **5** | 0 |
+| `~/REVIEWED.md` | 4 | 0 | 2 | 0 |
+| `~/PENDING.md` | **11** | **19** | **10** | **11** |
+| fool-trial-log | 0 | 0 | 4 | 0 |
+| trials 03, 04 | 0 | 0 | 3 | 0 |
+| ladder, chamber spec, studium charter, trials 01–02 | 0 | 0 | 0 | 0 |
+| **total** | **16** | **20** | **24** | **11** |
+
+**Consequence, stated in the design's own terms: every STRONG grade would be an ECHO.** Not
+because the jester is echoing deliberately, but because the material is in front of it. A
+question reaching Fault Line 5 after reading Constraint 6 establishes nothing about
+independent reach.
+
+### 3a · The revision's scan was scoped one document too narrow
+
+The 2026-08-19 revision required scanning **`REVIEWED.md` and `PENDING.md`**. Run at that
+scope it would have caught the PENDING.md leak — the revision's instinct was correct and
+its instruction would have fired. But **the FL5 leak in `~/CLAUDE.md` is outside the named
+scope**, and `~/CLAUDE.md` is corpus item #1. The scan's subject was two documents; the
+property it needed to establish is a fact about the corpus. Reported because the near-miss is
+the useful part: the check was one word from being complete.
+
+## 4 · Executor contamination, disclosed
+
+The revision requires the executor to scan for **paraphrases** of Fault Lines 3/4/5, which is
+not possible without knowing them. The executor read them verbatim on 2026-08-17 (jurist relay,
+task 2) and again today to run the scan. **This precedes §5 step 4's *"only now is OP-02
+opened"*.** Steps 2 and 3 are unaffected — those seats are the steward's and the jurist's — but
+the corpus was assembled by a party that already knew the answer key, and that cannot now be
+undone for this trial. Disclosed rather than managed.
+
+## 5 · Partitioning — and a third explanation for a null that §4 does not list
+
+166,088 words ≈ **224,000 tokens**, against a 64 GB machine holding a 35 GB model. §2's option
+(a) — partition, same prompt against each section — is required; option (b) is excluded because
+it would have the executor choose what the jester sees.
+
+**But partition is not neutral for this trial's own ground truth.** Fault Line 5 is a claim
+about three parties *across* documents; Fault Line 3 is about an inquiry's relation to its
+authorizer. A jester shown only one partition cannot see the arrangement whole, and the STRONG
+criterion asks precisely for the cross-document reading.
+
+⚠ **Pre-registered before the result exists, alongside §4's confound:** a NULL result under
+partitioning admits a **third** explanation the design does not name — *position does not help*,
+*35B lacks the capacity*, or **the partition removed the view the criterion requires**. Written
+down now so the null cannot later be read as a verdict on the jester form.
+
+**Mitigation available, not taken unilaterally:** replicate `~/CLAUDE.md` (2,831 w) as a
+constant spine in every partition. It adds nothing not already declared, removes nothing, and
+is a mechanical rule rather than a judgement — but it is a deviation from a literal partition
+and belongs to the steward, not the executor.
+
+## 6 · What the executor recommends, and what it declines to decide
+
+**Recommended: run for MODERATE only; record STRONG as `NOT ESTABLISHED`, never as zero.**
+
+- It revises nothing in §1, which forbids revision. STRONG simply becomes unreachable by
+  construction, and that is recorded as a property of this run.
+- It requires **no executor redaction**. Redacting the corpus would be the court selecting what
+  the fool may know — the failure §2 exists to prevent — and would mean cutting Constraint 6
+  out of the constitution to protect a grade.
+- MODERATE is defined as *"a question about the arrangement, rated uncomfortable, that survives
+  adjudication, **and appears in no fault line**"*. The leak does not touch it. If anything the
+  leak makes ECHO do real work instead of being a formality.
+- The §1 cross-tab — discomfort × survival — is the trial's actual novel measurement and is
+  entirely unaffected.
+
+⚠ **§6's abandonment criterion must then be re-read before the run, not after.** It requires
+*"Zero STRONG **and** zero MODERATE"*. With STRONG unreachable, an unamended reading makes
+abandonment easier to trigger by an artefact of the corpus. The criterion should be read as
+MODERATE-only for this run, or the run does not count toward abandonment at all. **This is a
+change to a pre-registered instrument and is therefore not the executor's to make.**
+
+**Alternatives, for completeness:** *redact the corpus* (rejected above); *build a fresh ground
+truth from a court-aimed critique that has not migrated* (clean, but none exists and
+manufacturing one for the purpose reintroduces the problem); *postpone until after the
+Observer Problem items close* (defensible, and costs the trial its current relevance).
+
+**Not decided here.** The choice between these changes what is measured, and the log's standing
+S-1 caveat is that executor grading is already its weakest joint. Held for the steward, with the
+jurist's view sought on §6's re-reading.

claude/governance/fool/trial-09-corpus-manifest.json

@@ -0,0 +1,78 @@
+{
+ "generated": "2026-08-19T11:47:40+02:00",
+ "corpus": [
+  {
+   "path": "~/CLAUDE.md",
+   "role": "the constitution",
+   "sha256": "4de00c6c8a1a20096d533483020d7a1897cb5b5701ed2cb03bf724a1825d6934",
+   "words": 2831
+  },
+  {
+   "path": "~/_Dev/chamber-library/docs/chamber-library-specification.md",
+   "role": "chamber constitution",
+   "sha256": "29f25a0bfebffd70efdf5eefe77d9f4394cb1dd865ef1889ea051411d4020def",
+   "words": 23411
+  },
+  {
+   "path": "~/_Dev/studium-engine/docs/the-studium-engine-architectural-charter.md",
+   "role": "studium charter",
+   "sha256": "8f583be60ad4c740ffd3d4fd1f6f692d21e110a33e33f607bc318907bb41e873",
+   "words": 2899
+  },
+  {
+   "path": "~/REVIEWED.md",
+   "role": "rulings as placed",
+   "sha256": "5a4762bf3f47661f3065e0d85463a2ad74ead98cc647c7fbc5e2dad8d5190c80",
+   "words": 41263
+  },
+  {
+   "path": "~/PENDING.md",
+   "role": "open items as they stand",
+   "sha256": "d793f8d5829bca0978e56d98d1603dd570faab7bcc66d8a363757296bda20f70",
+   "words": 84433
+  },
+  {
+   "path": "~/.claude/projects/-Users-davidglidden/memory/reference-verification-ladder.md",
+   "role": "the instrument ladder",
+   "sha256": "7d969a74572315e194005e77d76d989b4f33772be66b1d284c4d06607ebeb148",
+   "words": 3895
+  },
+  {
+   "path": "~/dotfiles/claude/governance/fool-trial-log.md",
+   "role": "the trial log",
+   "sha256": "3618d327b51ee8b665d7d8df6ec67e193cae448e7ff5cef124953897f8e8208f",
+   "words": 2231
+  },
+  {
+   "path": "~/dotfiles/claude/governance/fool-trial-01-2026-08-01.md",
+   "role": "trial 01",
+   "sha256": "708ccc7a7854c245abad4a0f5c0f9e83d3082acb710a3f3538e38bdefc1ec6fb",
+   "words": 876
+  },
+  {
+   "path": "~/dotfiles/claude/governance/fool-trial-02-2026-08-02.md",
+   "role": "trial 02",
+   "sha256": "044acd407e386cd6894aa6c79d85d63ade8d7eb7a3921f298c462d632d2497ae",
+   "words": 1174
+  },
+  {
+   "path": "~/dotfiles/claude/governance/fool-trial-03-2026-08-02.md",
+   "role": "trial 03",
+   "sha256": "2073f1ba7263a5bbc752492788a2b9e3c996757a73fb1a354f91e5ad54fb1070",
+   "words": 1732
+  },
+  {
+   "path": "~/dotfiles/claude/governance/fool-trial-04-2026-08-02.md",
+   "role": "trial 04",
+   "sha256": "ca0f99f9de036f934284de9db6f95732163a618c0dd9faae27d23c59d521fc5b",
+   "words": 1343
+  }
+ ],
+ "excluded_hashes": {
+  "~/_Dev/CapableMind-AI/docs/thinking/David/l2-constitution/observer-problem/OP-02.md": "4a38e549f1dbb0f4040369823a5f92172b35d43b79923f26e693e1f01fceb9b5",
+  "~/_Dev/CapableMind-AI/docs/thinking/David/l2-constitution/observer-problem/REVIEWER-PACKAGE \u2014 Observer Problem.md": "f25c13e9f2dab63cf7c8cd6fa398d71d3068229a72b15c53f075ad31dd633563",
+  "~/_Dev/david-root-and-branch-vault-git/08. Notes/CapableMind/thinking-mirror/l2-constitution/observer-problem/OP-02.md": "4a38e549f1dbb0f4040369823a5f92172b35d43b79923f26e693e1f01fceb9b5",
+  "~/_Dev/david-root-and-branch-vault-git/08. Notes/CapableMind/thinking-mirror/l2-constitution/observer-problem/REVIEWER-PACKAGE \u2014 Observer Problem.md": "f25c13e9f2dab63cf7c8cd6fa398d71d3068229a72b15c53f075ad31dd633563"
+ },
+ "collision": []
+}

claude/memory/MEMORY-reference.md

@@ -1,3 +1,5 @@
+- [Session 2026-08-09 — the fixture was an empty file](session-2026-08-09-the-fixture-was-an-empty-file.md) — the day's full record: premise-check, PENDING-129/130 → REVIEWED-113/114, the `KeyError` that corrected its own ruling, two artifacts preserved with three-part provenance, four documents corrected (`20f8958`), and the marking sheet. ⚠ **The placed record contradicted the relay for the third consecutive time.** **LITERAL Q: Mauss serves the Ranaipiri testimony and a Havámál strophe as citable Mauss with no `role: quotation` — two-source accident, or a class?**  *(Demoted on promote at the 2026-08-13 wrap.)*
+- [Session 2026-08-08 late — eleven items, and the charter had the map](session-2026-08-08-late-the-charter-had-the-map.md) — **Built the binding mechanisms all day, then found in the last twenty minutes that the founding charter had already answered the strategic question.** (e) built as a **delegation** (`eecc8bb`) and exposed that **no fleet suite had ever validated live binding**. Hook sequence landed in the ruled order (`448ce37`, `2534dfb`); R0 §4 three-valued (`ccc4d6c`); fleet third verdict + preflight crash-class closure (`8ff5a9f`, `d21a43b`); Mauss corrected (`8231bce`). ⚠ **Leopold Mozart is ALREADY in the library as an EPUB** (Knocker translation, born-digital) — the violin problem may be **sourcing, not conversion**. **LITERAL Q: does re-running `pattern_finder`'s Station-I pass still come back PASS-BUT-FALSELY now that V0/V1 exist?** *(Demoted on promote at the 2026-08-09 wrap.)*
 - [Session 2026-08-08 — `voice:` is the convocation key](session-2026-08-08-voice-is-the-convocation-key.md) — **The disposition that landed is not the one any single party drafted.** Grounded first, then read the twelve blocks *from the source* rather than their sidecar titles — which produced nearly every finding: **Surah LXIV not CXIV** (already propagated into two governance records, and it voided the jurist's worked note, built on a formula absent from the passage); **`quotation-poet-jurist` reclassified** by one footnote; the naming evidence for six of nine blocks sits **inside the fenced apparatus**, engine-unreachable. Option C **refuted by measurement** (omission → host voice). The steward's correction on language sent me back to `[^101]` and thence to **L850 — Mauss's own prose fenced inside the Havámál block**, missed by a check using **length as a proxy for authorship**. Corrected the jurist upward: their category pair belonged **out** of the convocation key (`glidden` spans 5 sources, `weil` 2 — measured). Caught `REVIEWED-113` before it entered the register (PENDING-110 rules the sequences independent). **REVIEWED-97 placed + verified clean · PENDING-114 authorized (b)+(c) · PENDING-115 filed · `824139d`.** 🔑 **Corrections ran in all three directions in one day** — and the fleet was still red the whole time. *(Demoted on promote at the 2026-08-08 night wrap.)*
 - [Session 2026-08-07 evening — retrieval is set by home](session-2026-08-07-evening-retrieval-is-set-by-home.md) — **The skill-harvest bite taken whole, at the cost of V2.** Register censused before compacting: claimed 177, **real 154** (55 rows were scraped table-headers; 123 of 129 cut mid-word) — but **lossless**, 124 = 124, so my drafted "nine are invisible" and "59% misattributed" were both **refuted by the count**. Rebuilt from the archive with exact `archive:L###` pointers; restored the verbatim four-stroke ruling my own rebuild had replaced with a paraphrase. **Skills pruned 63 → 12** after measuring **53 never invoked in 5 months** (plus a dir named from a **404 error body** and ten with **newlines in their names**); 51 quarantined reversibly. The finding under both: **retrieval is set by home, 0%–83%**. **PENDING-112 → jurist ruling → steward concurrence → REVIEWED-95 drafted in one session**; filing gate + ladder trial sentence landed, **falsifier wired not intended** (`transcripts 84`) — which exposed two defects in the deferral checker itself, incl. that it **never looked at `claude/governance/`**. Package passed containment **20/20, 10/10 controls absent**, after the checker caught my own **elision-as-contiguous** and **fabricated join**. 🔑 **8 of 8 fresh instruments at fault; the elegant symlink discriminator was 97% right and would have destroyed the 2 that mattered.** *(Demoted on promote at the 2026-08-07 night wrap.)*
 - [Session 2026-08-07 — the count found what the read did not](session-2026-08-07-the-count-found-what-the-read-did-not.md) — **Twelve commits, three repos.** MEMORY.md trimmed 19.9→16.7 KB · **N1** (tree, 4 primitives) · **R0** (one reading-index loader — the adapters had already diverged on 3 of 253 patterns with *neither* right) · **N2** (`0/22` was the wrong search space: gold anchors are DIVISIONS → **top-1 15/22**, ⚠ **and 5/5 false positives**, untuned) · **@3 corrected in place** under the PENDING-111 ruling, with **three measured findings refuting the package's own premises** · **D-5** (TEI deferred, proxy trigger retired, discriminator pre-registered) · two governance checkers (register-integrity + deferred-decision triggers) · three corpus voice-defects fixed (Alexander re-anchor + "Using this book" partition; **Thibon's introduction had been served as citable Weil**) · **V2's German blocker dissolved — the source was graduated 2026-07-09 and nobody looked for a month.** 🔑 **Every defect was found by a COUNT, none by a read; 3 of 3 new checkers were themselves at fault.** *(Demoted on promote at the 2026-08-07 evening wrap.)*
@@ -15,6 +17,23 @@ metadata:
 
 # MEMORY — Reference layer (consult on demand)
 
+<!-- demoted from MEMORY.md at the 2026-08-17 wrap -->
+## Active Session
+> 🔑 **PULLING THREAD (HELD, NOT CARRIED) — THE UNBUILT FENCE, PENDING-131 (c).** `role: quotation` is still unmarked on L926 and L1551; the identification pass measured a **532-span corpus-wide citation-safety exposure**. **REVIEWED-121 made seeking the fence a CONDITION of the doctrine it ratified**, not a wish. It is where a claim could ground in Ranaipiri's words and present them as Mauss's — the dishonesty the engine exists to prevent.
+> ⚠ **NEXT SESSION IS DELIBERATELY NOT THIS — steward direction 2026-08-14:** pause this line a day or two, take something lighter (discouraged despite real progress). **Do not treat the thread above as the agenda.** Confirm it holds, then do what the steward asks that day.
+> ✅ **PENDING-134 CLOSED END-TO-END.** Package → jurist ruling → **REVIEWED-121 placed + AUTHORIZED** → executed (`5425414`) → pushed. Whose-proposition test ratified **narrowly** (nested-voice only; general principle = argument, NOT doctrine), **conditioned on PENDING-131 (c)**.
+> ⚠ **THE FINDING: A CONTROL PASSED TRUTHFULLY AND LICENSED A FALSE CLAIM.** IV.1 said *"F10 is the only §5 row with a stratum-B admission clause"*, marked **verified**. Three rows carry one (F3/F7/F10) — **quoted intact in the package's own I.2 and reproduced in its own IV.2 table.** The script tested whether *quotes were present*; the claim was an *inference over the rows*. **A control whose subject differs from the claim's is not a weak check — it is not a check.** ⚠ And it **understated an objection to my own proposal**, inside the paragraph written to state it at full strength.
+> ⚠ **`test_legacy_indices_are_not_self_verified` DOES NOT EXIST** — one occurrence repo-wide, a docstring. Carried into a corpus file, a commit message and a steward report unopened. 4th cited-a-derived-label instance; fixed `966168b`.
+> ⚠ **PENDING-140 [ESCALATE] FILED 08-17 — a proposed THIRD axis for Constraint 6.** Jurist *without* keys (REVIEWED-116 pt 7) ruled on my testimony and its own A4 was false; *with* keys it returned **three defects in one sitting**. **Formation, role and incentive identical across both — only access changed.** ⇒ bias-difference is **necessary and radically insufficient**; a differently-biased reader with no access checks the *account*, not the *thing*. ⚠ n=1/condition, self-reported, and **authored by the party under discussion** — filed, not acted on. Also: `contamination-problem.md` is a theory of **glazing only**, while a crude probe puts our 235 drift-patterns at **86 literal-genie / 12 trickster / 8 glazing** (129 unclassified; classifier is the very defect PENDING-139 names).
+> ✅ **AMENDMENT 1 PLACED 08-17** (`~/REVIEWED.md` L1813) **and A3 EXECUTED** (`a3be778`, REVIEWED-121-A1) — the latch now carries `defeater_dispositions_recorded` + `defeater_population` (**named, not numbered**, on the amendment's instruction). Register check now sees **2 amendments** where it saw 1.
+> 🔧 **NEXT SESSION IS TOOLING, NOT GOVERNANCE — steward direction 2026-08-17** (a break from governance; the choices were left OPEN for the wake to pick):
+> • **`wrap_inside` three-valued fix** *(recommended — small, no governance surface)*: `wake-digest.py:167` is a two-valued detector over three real cases — wrapped · **wrapped-then-continued** · never-wrapped. **2 false alarms in 3 firings**; it misled this session's own wake. The fleet already solved this shape twice (REVIEWED-104/108), so copy the pattern; the selftest at ~L807 already has positive + negative controls to extend.
+> • **S2 ladder batch** — ⚠ **BLOCKED BY PENDING-141**, do not execute (see the skill-harvest line above).
+> • **Engine retrieval / PENDING-97** *(the bigger one — a day, not an hour)*: every real question needs 13–19 terms to co-occur; N2 buys top-1 **15/22** at the cost of **5 false positives**, abstention 0/5. This is the one that moves the chamber rather than the scaffolding.
+> ✅ **AMENDMENT 1 COMPLETE 08-17** — truncation filled, fence closed at L1853, all 10 elements verified present; A3's binding rule **ratified** and quoted verbatim in the corpus (`cd6d4bf`). ⚠ **The re-paste indented the body 2 spaces but left the HEADING at column 0 — had it not, `RE_HEAD` would have stopped matching and the amendment would have gone invisible to register-integrity while the check reported clean.** **`ratio_A_to_B` VOID until PENDING-137 lands.**
+
+- [Session 2026-08-14 — the controls tested the wrong property](session-2026-08-14-the-controls-tested-the-wrong-property.md) — PENDING-134 closed; REVIEWED-121 placed/executed; PENDING-137/138/139 + a PENDING-89 docket entry filed; three package defects jurist-caught, the addendum's own A4 false, the governance checker carrying two blind spots. **LITERAL Q (sharpens 08-13's): not regression-vs-discovery — was the control's SUBJECT the claim it was cited as verifying, or an adjacent property? Census the last ~10 sessions on that axis.** **+ CODA (post-wrap, 08-17 capture): the four-flavours reading → PENDING-140 [ESCALATE] — Constraint 6 names formation and role/information/incentive; the variable that actually decided whether the jurist caught me was SUBSTRATE ACCESS.**
+
 ## Relocated from MEMORY.md at the 2026-07-19 evening budget trim (verbatim; wake-value judged low — MemPalace-era mechanics + reactive-mode ARC specifics)
 
 - [Session 2026-08-03 — the governors that never engaged](session-2026-08-03-the-governors-that-never-engaged.md) — the inherited question answered, and it became the day's theme: **controls that exist in code and never engage**, invisible because an inert control reports success. **Census 01** (pre-registered): `fool/` strong, but **drift-check 3-of-5 families INERT** and **71 of 75 ladder entries cited nowhere** (no IDs ⇒ firing history unrecordable). **S-series closed** on discovering the **jurist ruled all Q1–Q5 on 2026-05-18** and the items were mislabelled 2½ months (S6/S7/S9 built · S2 rebuilt as `[FIX]` · S4/S5 withdrawn with MemPalace). Dormant legacy + GH swept: **22 → 10 open**; `#170` found **undelivered since April**. Steward lifted the L1 baton rule → **mindfabric-00 pinned 6 days**; CDP profile named it; **`ANALYZE` never run in 4 months** so SQLite preferred a *boolean* index over the selective one (**6.4×**, 99.8%→6.0%, `/health` silent→200 in 0.13 s). **B1.1's cap verified WORKING ⇒ the defect is DATA, not code** — 836k edges minted before the governors landed; the ingest was **divergent, not slow**. **`coherence_evaluated = 0` of 813,178 — not one, ever.** ⚠ **Its headline claim was corrected 2026-08-04**: `ANALYZE` explained the *slowness*, not why the ingest never completes — see [[session-2026-08-04-the-replay-had-never-resumed]]. *(Demoted on promote at the 2026-08-04 wrap.)*
@@ -24,7 +43,7 @@ metadata:
 - [Session 2026-08-01 — the Fool, and the boundary I manufactured](session-2026-08-01-the-fool-and-the-manufactured-boundary.md) — closed the reset thread (PENDING-85 eyeballed → **Arcades verdict WRONG**, a ClearScan scan; PENDING-84 triaged via the **§VII quarantine lane**, *dispositioned not repaired*), then found the stuckness was largely mine: **three of the day's biggest closures were ALREADY authorized** — register split (166K→44K, 177 open readable), ladder Stroke 2 (21→**71 instruments**), classifier fix — and once I justified inaction by invoking **PENDING-88's own unratified rule**. Landed **spec v2.9.1** (0-of-17→0-of-14; the prior figure is **irreproducible**, recorded in the constitution). **REVIEWED-85 ruled, NOT placed.** ESCALATE doctrine package filed (*differently biased checkers*). **Derrida: the independent witness WORKS** — ocrmac recovered what olmOCR silently dropped (5,590 words / 152 spans, invisible to every wired gate). **PULLING THREAD: stabilize the Fool method** (Qwen 3.6 35B on the M4, 2 trials, protocol unstable) — and **v1 Chamber's paired GPT/Claude raw outputs survive in ARC**, a ready-made dataset. Detail in the session file.
 - [MemPalace KG object 128-char cap](feedback-mempalace-kg-object-128-char-cap.md) — `kg_add` `object` hard-caps at 128 chars; write KG objects as short keyword phrases on the FIRST pass, detail goes in the drawer. Recurs at every /wrap-up §5 — stop re-deriving it. *(Relocation note: palace-memory wound down 2026-07-07; wrap §5 now appends JSONL — the cap now matters only for typography-palace kg_adds, which are rare.)*
 - [MemPalace wing-filter broken](feedback-mempalace-wing-filter-broken.md) — wing-scoped search → 'Error finding id' (upstream #1665, open at HEAD); search UNSCOPED + post-filter by wing. Don't run `repair` (#1589). Affects wake-up §2.b.3. *(Relocation note: §2.b.3 was rewired to the files layer 2026-07-07; relevant only to the typography palace CLI now.)*
-- [Verify each post type after changes](feedback-verify-each-post-type-after-changes.md) — ARC: after any shared CSS/template/composition change, check EVERY content type on BOTH desktop and phone, not a sample on one viewport. Lesson from §II.d gate verified phone-only → desktop appearance surfaced 2 sessions late (no regression; just unseen). Per-type×per-viewport extension of [[trust-prior-pass-frame]]; belongs in the SCSS verification ladder.
+- [Verify each post type after changes](feedback-verify-each-post-type-after-changes.md) — ARC: after any shared CSS/template/composition change, check EVERY content type on BOTH desktop and phone, not a sample on one viewport. Lesson from §II.d gate verified phone-only → desktop appearance surfaced 2 sessions late (no regression; just unseen). Per-type×per-viewport extension of [[feedback-trust-prior-pass-frame]]; belongs in the SCSS verification ladder.
 - [Reading Compass is SVG, not type](feedback-reading-compass-is-svg-not-type.md) — ARC Compass sigils are SVG `<symbol>` artwork, NOT Plex Sans / nav typeface / Pattern 3. Recurring conflation; steward corrected 2026-06-03. Plex-Sans nav *text* = breadcrumb + version-stamp + post-type only.
 - [ARC chamber v1-legacy cluster](project-arc-chamber-v1-legacy-cluster.md) — ARC's `content/chamber/**` is intentional v1-Chamber legacy (not drift); deferred to-do = gather into a presentable cluster as a record of development. Out of §5 clause-1 audit scope. Confirmed 2026-05-29.
 
@@ -45,6 +64,9 @@ Split out of [MEMORY.md](MEMORY.md) on 2026-07-06 to keep the wake-loaded index
 
 # Archived sessions + stable reference layer (relocated verbatim from MEMORY.md, 2026-07-06)
 
+## Archived (2026-08-13 — the fence was never blocked; demoted on promote at the 2026-08-14 wrap)
+- [Session 2026-08-13 — the fence was never blocked](session-2026-08-13-the-fence-was-never-blocked.md) — REVIEWED-118 executed (authorized-but-unexecuted, found by substrate-checking a disposition clause) · the (b1) identification pass · PENDING-135/136 → REVIEWED-119/120 · `voice_stamp` built · Addendum 4 with the steward's seam observation. **LITERAL Q: four of five instrument defects escaped the tool's own controls and the one they caught was a regression — is that the general pattern? Census the last ~10 sessions: are control sets a REGRESSION net and not a DISCOVERY net?**
+
 ## Archived (2026-08-07 night — the quotation is the joint; demoted on promote at the 2026-08-08 wrap)
 - [Session 2026-08-07 night — the quotation is the joint](session-2026-08-07-night-the-quotation-is-the-joint.md) — **V2's preconditions worked all the way, and they opened something bigger.** P4 censused **14** (my own `grep -c` reproduced the design's "21" error); **P5 span-bound 15 of 17, not 6** — I briefed "6" by reading a *byte*-locatability number as the gold count, and my first binding pass bound **0 of 11** because its criterion was inherited from Tier-1; **P7 tagged fr at 1 A : 9 B**, inverting its own prediction, while **en is not taggable** (no spans; EN divisions run **29×** the FR ones). Tagging surfaced that the corpus **serves quoted third voices as the host author's** — **~6,455 runs, ~94% intra-line** — and that **Stevens, Rilke and Ungaretti sit in Harrison with no marks at all**: *"It took dominion everywhere"* retrieves as `voice: harrison`. Fixed three sources, then the steward reframed it (*the quotation is where reader and author meet*) and **REVIEWED-96 ruled the fix itself the wrong instrument** — D-4 already prescribed attribution, and refusal **destroyed a gold-negative** for the class it protected. **Twelve instrument faults**, the twelfth (German `»…«` read with a French pattern) reaching a **filed governance document**. **Three governance items found cited-as-live while unplaced**, all invisible to the drift checker. 🔑 **One control — six known answers — was the only thing that caught a fault before its output was read.**
 
@@ -279,7 +301,7 @@ Split out of [MEMORY.md](MEMORY.md) on 2026-07-06 to keep the wake-loaded index
 - [Session 2026-06-17 — the cul-de-lampe designed, rolled out & shipped; Levi base settled & paused](session-2026-06-17-cul-de-lampe-designed-rolled-out-shipped-levi-base-settled.md) — **A long ARC-dominated day, fully shipped.** Designed the **cul-de-lampe** (confronted EB Garamond hederae U+E001/E002, tips meeting, central heart; drawn from real glyph outlines via fontTools), **sized to the text-em** (`height:1em` — em-anchored NOT a constant; the steward's "is there a mathematically right proportion?" pushed to a doctrine-consistent answer per REVIEWED-42 silver-ratio retirement), **`var(--fg)` opacity 0.7** (NOT grey — steward caught it; grey retired Stage M; CSS mask, white-fill luminance-safe, hand-written -webkit-). **Close-only** ruling; **type-applicability**: Essay/Hommage/Tombeau carry it, **Fragment refused**, Photo-essay declined; placement (end of text proper, before Sources) + **publication mandate**. Caught + fixed my own **Sources-as-apparatus over-claim** (steward flagged). **Rolled out to 7 essays**; **Vespers quieted** (titles→§XII.b register-marks I–VIII; ornaments→silence; §VIII image-caption fixed) + **Mushi-Ken revised** (analysed against type-spec = it IS an essay; dropped the pre-typology appendix); **both reworks VERSIONED** (ADR-005 genesis snapshots + /v/ routes; steward: "respect the versioning"). Spec'd (§IV + Sub-table 6 reconciled). **Committed `d736df1` + `68001a4`, deployed live, pushed origin + github-backup.** Began on **Levi/Camus** Position-I conversion: **Camus DONE**; **Levi base settled = ocrmac fresh OCR** (4-pass; reading-order fidelity decides) BUT **drop-caps lost at OCR-source level** → source-verified restoration + ingest **PAUSED** (verbatim-trust > speed). Steward ruled **Levi = whole book**. **PULLING THREAD reverts to Levi → the pattern-finder's first TRUE pass.** Captured **B5** (versioning-links rethink) in the open-work register; A2 → DONE.
 
 ## Archived (2026-06-17 — cul-de-lampe shipped + Levi base settled)
-- [Session 2026-06-16 (evening, post-/clear) — pattern-finder built + Station-I ingested + pass-1 contamination caught + ARC ornaments grounded](session-2026-06-16-evening-pattern-finder-build-station-i-contamination-arc-ornaments.md) — **The thread's first real build, and the engine catching its own error.** (1) **Station-I ingested** into studium-engine (5 authors/7 work-files; steward ruled FR-originals · Levi=Gray-Zone-only · both Weil; new manifest vocab `role:reading-source`+`station:I`; omnibus works sidecar-scoped; 15 sources/7282 drawers/verify HEALTHY). **[FIX] Mauss re-anchor** — the morning's own chamber-cleanup (`03de347`) broke the engine's pinned hash; gate caught it. (2) **Built `engine/pattern_finder.py`** — charter-L2 harness (three cognitions; generate-free/verify-tight; honest-silence; reasoner=Claude over FTS). (3) **PASS-1 CAUGHT ITS OWN FALSE GROUNDING** ([[feedback-tool-review-after-each-use]] PASS-BUT-FALSELY): "5/5 voices" partly false — **Camus la-chute span is mostly *Le Premier Homme*** (mislabelled mega-omnibus); **Musil/Arendt apparatus leak** (translator N.d.T. / Amos Elon intro / Bibliography-Index). The engine's thesis (§VII/§XV) *working*. Survivor: **P3 "complicity that depletes not damns"** (Weil↔Levi↔Arendt, 1947↔1986). **Return — frame-inheritance** ([[trust-prior-pass-frame]]): verified endpoints, not interior. (4) **Pass-2 fixes applied** (Musil/Arendt sidecars corrected, interior-verified; **Camus WITHDRAWN** pending clean re-source) — **NOT re-run/verified (Bash flaky); studium tree left inconsistent+uncommitted on purpose.** (5) **ARC ornaments grounded**: **cul-de-lampe** = confronted hederae, SVG from open EB Garamond, terminal-close, *ivy=lié=ligature binding dead-to-unborn-via-living* (steward's keystone); **triple point** = Penguin/Tschichold restraint citation at the opening threshold, "a touch more weight." Both → spec §IV + type-matrix (steward, tomorrow). **PULLING THREAD: the pattern-finder's first TRUE pass on Position I — gated now on a clean, complete source set the steward will assemble.** NEXT: re-source → re-run+verify pass-2 → clean grounding → marginalia → commit.
+- [Session 2026-06-16 (evening, post-/clear) — pattern-finder built + Station-I ingested + pass-1 contamination caught + ARC ornaments grounded](session-2026-06-16-evening-pattern-finder-build-station-i-contamination-arc-ornaments.md) — **The thread's first real build, and the engine catching its own error.** (1) **Station-I ingested** into studium-engine (5 authors/7 work-files; steward ruled FR-originals · Levi=Gray-Zone-only · both Weil; new manifest vocab `role:reading-source`+`station:I`; omnibus works sidecar-scoped; 15 sources/7282 drawers/verify HEALTHY). **[FIX] Mauss re-anchor** — the morning's own chamber-cleanup (`03de347`) broke the engine's pinned hash; gate caught it. (2) **Built `engine/pattern_finder.py`** — charter-L2 harness (three cognitions; generate-free/verify-tight; honest-silence; reasoner=Claude over FTS). (3) **PASS-1 CAUGHT ITS OWN FALSE GROUNDING** ([[feedback-tool-review-after-each-use]] PASS-BUT-FALSELY): "5/5 voices" partly false — **Camus la-chute span is mostly *Le Premier Homme*** (mislabelled mega-omnibus); **Musil/Arendt apparatus leak** (translator N.d.T. / Amos Elon intro / Bibliography-Index). The engine's thesis (§VII/§XV) *working*. Survivor: **P3 "complicity that depletes not damns"** (Weil↔Levi↔Arendt, 1947↔1986). **Return — frame-inheritance** ([[feedback-trust-prior-pass-frame]]): verified endpoints, not interior. (4) **Pass-2 fixes applied** (Musil/Arendt sidecars corrected, interior-verified; **Camus WITHDRAWN** pending clean re-source) — **NOT re-run/verified (Bash flaky); studium tree left inconsistent+uncommitted on purpose.** (5) **ARC ornaments grounded**: **cul-de-lampe** = confronted hederae, SVG from open EB Garamond, terminal-close, *ivy=lié=ligature binding dead-to-unborn-via-living* (steward's keystone); **triple point** = Penguin/Tschichold restraint citation at the opening threshold, "a touch more weight." Both → spec §IV + type-matrix (steward, tomorrow). **PULLING THREAD: the pattern-finder's first TRUE pass on Position I — gated now on a clean, complete source set the steward will assemble.** NEXT: re-source → re-run+verify pass-2 → clean grounding → marginalia → commit.
 
 ## Archived (2026-06-16 morning — officina + conversion tooling trustworthy + Station-I corpus complete)
 - [Session 2026-06-16 — officina established + conversion tooling made trustworthy + Station-I corpus complete](session-2026-06-16-officina-conversion-tooling-station-i.md) — **Long, two movements, almost entirely the prerequisite for the thread.** (1) **Officina** = ARC's in-repo writing workshop (genetic trail seeds/notes/fragments/drafts; never published; **ADR-008**; gates = Hakyll allowlist + both-remotes-private; sub-canonical sources → chamber `antechamber/`). Seeded by The Making (sketch + *Magnifica Humanitas* note [steward deeply affected] + reading list). (2) **The conversion-tooling marathon** (steward's deepest ask: *review every tool after each use until reliable* → [[feedback-tool-review-after-each-use]]): hardened **audit_cruft** (gate was passing falsely-clean → corpus never "1280 clean": 160→215 dirty), built **verify_conversion.py** (composite verifier **+ prose-safety `prose_delta`**), fixed **strip_cruft** + **repair_epub_headings**, wrote **`conversion-runbook.yaml`** (the single operational place) + **`tool-evolution-log.md`**. Prose-gated cleanup: **180 cleaned, 35 reconvert → honest 1245/35**. **Station I corpus-complete** (Camus *La Chute* + Musil ×2 converted/graduated; joins Weil/Levi/Arendt). **Return: the false alarm** — cried "destroyed prose," disproved it (cruft tokens, not prose; recalibration: content-aware compare, not token counts). All pushed (chamber `d9c6755`, ARC `7a0d4b6`). NEXT: ingest the five into the engine → build/run the pattern-finder's first pass.

claude/memory/MEMORY.md

@@ -6,7 +6,7 @@ metadata:
   type: note
   permalink: claude-memory/memory
   originSessionId: 22915403-bc5d-4796-9c7d-196b7c30d2f9
-  modified: 2026-08-07T17:08:24.523Z
+  modified: 2026-08-17T13:20:44.481Z
 permalink: claude-memory/memory
 ---
 
@@ -33,13 +33,14 @@ permalink: claude-memory/memory
 **Loud trigger — pointer suffices**
 - [Chamber work: ground in constitution + charter + runbook FIRST](feedback-chamber-work-ground-in-constitution-charter-runbook.md) — **any chamber work *or talk about it*** begins there (incl. `reanchor:`). Repo CLAUDE.mds are pointers, not state; corpus claims come from a self-tested tool, never a hand grep.
 - [Governance files are dotfiles symlinks](reference-governance-files-are-dotfiles-symlinks.md) — Edit/Write refuse to write through a symlink, so **edit the real `~/dotfiles/…` path** when appending — **`PENDING`/`REVIEWED` only.** ⚠ That refusal is a tool artifact, **not** a permission check, and this note is the documented route past the only friction guarding the constitution (PENDING-107). **`~/CLAUDE.md`/`~/REVIEWED.md`/L2 = `[ESCALATE]`, steward's hand — a jurist sign-off does not authorize one.**
-- [Verification ladder](reference-verification-ladder.md) — the named instruments; reach for the gate the claim's shape demands instead of re-deriving one.
-- [Skill-harvest register](skill-harvest-register.md) — canonical home for proposed skills (governed analog of PENDING.md for tooling); `/wrap-up` §1.6 proposes, steward authorizes. **Rebuilt 2026-08-07** from the archive: **154 live proposals**, grouped by kind, each with an exact `archive:L###` pointer. ⚠ The 2026-08-01 compaction was *lossless but illegible* (55 scraped header rows, 95% of cells cut mid-word) — the count it advertised, 177, was never the number. **Sequenced next: the Stroke-2 ladder batch-append** — 41 rows stamped `S2` are ALREADY AUTHORIZED (2026-07-19), needing execution not a ruling; 22 more are `S2?` (name two destinations, so no stroke settles them). **REVIEWED-95 Q3 resequenced it to follow the ladder's wake trigger — which now exists**, so it is unblocked. ⚠ Filing new proposals now requires a **declared firing moment** (`/wrap-up` §1.6); one that cannot name it is documentation and must say so.
+- [Verification ladder](reference-verification-ladder.md) — the named instruments; reach for the gate the claim's shape demands instead of re-deriving one. ⚠ **FROZEN — REVIEWED-123 (2026-08-17): no additions, rewordings, removals or reorderings, from ANY source, whatever its authorization**, until the trial is graded (N-now **60/84**). Entries earned meanwhile queue in **PENDING-141's owed-entries list** (4 rows). Reading it is unaffected — that is the point of the freeze.
+- [Skill-harvest register](skill-harvest-register.md) — canonical home for proposed skills (governed analog of PENDING.md for tooling); `/wrap-up` §1.6 proposes, steward authorizes. **Rebuilt 2026-08-07** from the archive: **154 live proposals**, grouped by kind, each with an exact `archive:L###` pointer. ⚠ The 2026-08-01 compaction was *lossless but illegible* (55 scraped header rows, 95% of cells cut mid-word) — the count it advertised, 177, was never the number. ⚠ **THE STROKE-2 BATCH IS AUTHORIZED BUT SHOULD NOT BE EXECUTED YET — PENDING-141.** 41 rows stamped `S2` are authorized (2026-07-19, execution not a ruling) and 22 are `S2?` (unsettled). **BUT appending them triples the ladder from 20 entries WHILE a pre-registered trial is measuring whether the ladder is reached** (baseline 14%, graded at 84 transcripts). Ladder size is an uncontrolled variable in that design, so executing the authorized batch would confound the only check behind REVIEWED-95's causal claim. **⚖ RULED — REVIEWED-123 (2026-08-17): AUTHORIZED (a) HOLD, on six conditions, and the freeze is GENERAL rather than S2-specific.** Grading does NOT authorize the append — the batch returns for a *ruling*. Report **N-now at every wake** until lifted; 30-day review is a live `DEFERRED-DECISION`. ⚠ Filing new proposals now requires a **declared firing moment** (`/wrap-up` §1.6); one that cannot name it is documentation and must say so.
 - [Copy-paste-clean governance drafts](feedback-governance-drafting-copy-paste-clean.md) — draft PENDING/REVIEWED blocks as plain fenced markdown; display formatting leaks into the placed record.
 - [Verify-before-compose hook](feedback-verify-before-compose-hook.md) — chamber constitutional writes are BLOCKED without `<!-- GROUNDED-IN: … -->` + verbatim Grounding. Don't fight the block.
 - [Tool review after each use](feedback-tool-review-after-each-use.md) — review every tool we built after each run, success OR failure. **PASS-BUT-FALSELY is the priority signal.** Log: `chamber-library/_curation/tool-evolution-log.md`.
 - [Every canon doc's source lives in Chamber Sources](feedback-resolve-source-through-chamber-sources.md) — a canonical's source = whatever `resolve_archived_source` returns, **never** the master library or a path in frontmatter. Read the banked record before calling a mismatch a defect.
 - [Engine sources graduate to the permanent chamber](feedback-engine-sources-become-permanent-chamber-collection.md) — work added for the engine ALSO becomes permanent collection unless stated otherwise; take it all the way (clean→verify→graduate→catalogue→sidecar). Never leave staged.
+- [Bulk indexing runs in tranches, gated on READBACK](feedback-bulk-indexing-runs-incrementally-with-readback.md) — never one multi-day mine; order by criticality; **prove each tranche by reading back, not by write-success** (933k drawers once stored fine and were unreadable). Steward rule 2026-05-04, learned on MemPalace, **applies now to engine corpus work**.
 - [Studium Engine charter](reference-studium-engine-architectural-charter.md) — the engine's constitutional doc. Read before building. · [Sixtus-V collaboration](feedback-studium-engine-sixtus-v-collaboration.md) — build freely, surface only vision-forks; **constraint-candidates** = 3rd governed instrument. Studium-engine only.
 - [CapableHands standing authorization](reference-capablehands-standing-authorization.md) — M4 mini `david@10.0.1.136` durably authorized for remote OCR/inference; don't re-ask (steward 2026-07-01).
 - [Typography palace — query via CLI](reference-typography-palace-cli.md) — ~20 type masters at `~/.mempalace/palace-chamber-typography`; `mempalace --palace <that> search "…"`. For ARC typography; don't re-ask where it lives.
@@ -51,7 +52,7 @@ permalink: claude-memory/memory
 ## Canonical Workstream Trackers
 *Read the tracker for any active workstream at /wake-up before composing the briefing. Append substantive moves at /wrap-up — to the **chronological log**, not only "current state". Per `feedback-canonical-workstream-tracker-discipline.md`.*
 - **[Chamber as versioned releases](project-chamber-versioned-releases.md) — THE GOVERNING FRAME for all library work.** The 2000-year Chamber as versioned releases with soft borders, each serving a PURPOSE; scope every library bite through this. **Open decision: which purpose anchors V1.** Read the file, not this line — it holds the reframe that resolved the purpose/scope paralysis.
-- [Studium Engine](project-studium-engine.md) — canonical engine tracker. **N0–N2 + R0 built** (2026-08-07); corpus **14 sources, trilingual** (en/fr/de), 5785 drawers, gate 14/14, fleet 202/202. `fidelity_equivalence@3` GOVERNING, **corrected in place** under PENDING-111. **N2: entry-finding 15/22 (from 0/22) — ⚠ and 5/5 false positives, untuned.** **NEXT: V2** — all three preconditions resolved, thresholds jurist-ratified, design fully specified.
+- [Studium Engine](project-studium-engine.md) — canonical engine tracker. **N0–N2 + R0 + `voice_stamp` built**; corpus **14 sources, trilingual**, fleet **9 suites / 285**. **fr cell all but closed** — 8 grounded (1 A + 7 B), `ratio_A_to_B` **VOID** until PENDING-134 lands. ⚠ **PENDING-131 (c) never bound the engine** (`chunker.py` has `char_range` since Cluster A). **NEXT: rule PENDING-134 — last blocker is a steward MCP restart.**
 - [Studium engine telos — the chamber of voices](project-studium-engine-telos-chamber-of-voices.md) — **the ultimate goal, above the build plan**: the childhood chamber of hero-voices, rebuilt so the counsel is *accountably* theirs. Why verbatim fidelity is load-bearing.
 - [The Chamber touchstone — the *why*](~/_Dev/studium-engine/docs/the-chamber-touchstone.md) — seven questions to test work against when lost in the trees. **Read at Step 0 of any chamber work.** Holds no state; does not decay.
 - [The Chamber vision is NOT in one place](project-chamber-vision-is-not-in-one-place.md) — it lives in **seven** sources across two repos + memory. A single home would become an eighth unless it supersedes or points.
@@ -64,19 +65,23 @@ permalink: claude-memory/memory
 - [Making sequence source set](project-making-sequence-source-set.md) — **COMPLETE against the ReadingList** (reconciliation-verified). Sourced ≠ ingested. Read before any Making/studium source work.
 - [Studium = CM's unfettered sandbox](project-studium-cm-sandbox-and-transfer.md) — experiment freely on library/engine without risking CM's runtime; breakthroughs transfer back. Steward-framed 2026-07-08.
 - [Be (laundromat)](project-be-laundromat.md) — Skemantix startup (Seb+David) funding CapableMind's ladder; **bridge, not venture**. Decisions LOCKED. **Pre-revenue WTP gate = renovate Pat → charge her; no new spec until it clears ⇒ nothing for executor on be.**
+- [Obsidian vault — from archive to practice](project-obsidian-vault-practice.md) — canonical vault tracker. **Frontmatter Spec v1.0.0 ratified + 2 passes applied** (511 edits / 268 files, pushed). ⚠ The vault is **NOT a git repo** — it mirrors to `~/_Dev/david-root-and-branch-vault-git`. **The actual goal — a capture workflow — has not been started**; don't let the frontmatter tail stand in for it.
 - Chamber-typography — *tracker not yet established*; moves live in per-session memories (2026-05-11 →) + `project-chamber-cruft-restoration.md` + `project-chamber-typography-mining-plan-2026-05-15.md`.
 
 ## Active Session
-> ⚠ **THE CHARTER HAD THE MAP, and I was navigating by the wrong layer.** §X: **L0 corpus (built) · L1 primitives (mostly built) · L2 aggregation & discovery — the pattern-finder — *Next* · L3 orchestration — voices, CHAVRUTA, larger debate — *the frontier*.** The chavruta is **L3**. §X also names the steward's use case by name: interfaces should emerge from *"the Making, then the violin."* And §IV calls **migration/genealogy the engine's SIGNATURE capability** — ⚠ whose stated consequence is half-built: `drawers` lacks a **`period`** column every manifest entry declares.
-> 🔑 **PULLING THREAD — V2, calibrating abstention: the SHARED floor, not a chavruta prerequisite.** 15/22 top-1, **abstention 0/5, 5 false positives** ⇒ a chavruta baseline today would **flatter itself**. The same calibration is what `pattern_finder`'s PASS-BUT-FALSELY needs. Preconditions resolved; thresholds **jurist-ratified (V0 §5) — do not re-derive**.
-> ✅ **Eleven rulings placed (REVIEWED-102…112), ten items filed (119–128).** Built: hook validator · both trigger rules · R0 §4 three-valued (`emit` was **unary**, 261/261 fingerprinted) · fleet third verdict + crash class closed at the preflight (**8 sites**) · built-vs-ruled in drift-check · `verify-quotes.py`. **82 discharged by events · 118 built, and building it REFUTED its own option (1).**
-> ⚠ **The day's shape was being corrected, and it was earned every time** — three citation defects with ONE cause (quoting the **advisory** as the **placed record**); "five instances, same shape" → two; recommendation (d) withdrawn by me; "nothing breaks" → touches ratified text; and **the fix reproduced the defect it was fixing** (a permanent NOT-A-CLEAN-PASS). Standing finding accepted: my grounding pass **finds my errors and never my support**.
-> 📌 **At the gate:** 121 + 128 as ONE declared-data commit. **Owed:** relay Addendum 2's redraft TEXT · chamber tool-fleet census (REVIEWED-106) · `quotation-in` × `translation-of`, third day untouched — ⚠ now with a new instance, since citing Leopold Mozart in English cites **Knocker**.
+> 🔑 **PULLING THREAD — THE FENCE. The deferral has EXPIRED: 2026-08-20 is the morning it named, and both shaping pieces have run.** ⚠ **The two, finally named** (this block carried "not yet named" for a day): **(1) the Obsidian vault spec** — ran all the way to a ratified v1.0.0 and two applied passes; **(2) Trial 09, the jester arm** — **PREPARED AND HELD, never executed.** One reshaping input arrived, one did not; whether either reshapes the fence is a steward call the record cannot make. Nothing in (A)/(B)/(C) has begun, so REVIEWED-122's binding order (answer key first, alone, hash recorded, before any implementation) is unharmed. ⚠ **Cost carried with eyes open:** the citation exposure behind PENDING-131 (c) has been live since 2026-08-10.
+> **(A) MOVE 2** — disposition the 25 line-addressable blockquote runs: **closable in ONE SITTING, needs no ruling**, and it is the fence itself rather than the scaffolding. **(C) MOVE 1** — fence the citation *at emission*, engine-side under D-1, all **532 spans** incl. sources added later; carries ADDENDUM 4's control requirement (controls from **each structural class present**, `NOT ESTABLISHED` rather than zero where a class has none — four of that census's five defects escaped Mauss-only controls). **(B) THE ANSWER KEY** — session-sized, gates all of PENDING-142. *Recommendation absent a preference: (A), then (C).*
+> ⚠ **THE KEY'S SPEC CHANGED BEFORE IT WAS DRAFTED — PENDING-146.** REVIEWED-122 cond. 1 says "per-item". **If "item" resolves to *id*, the key reproduces the very unit that caused Class E and grades green.** Key it on `##` **BLOCKS**, recording per block whether a live `Awaiting:` exists **and at what tag** (ADD-2 §5 re-tags (c) `[PROPOSAL]` inside a `[HARDENING]` row). Caught only because the key was not yet written.
+> ⚠ **CLASS E (PENDING-146): the open list's unit is the `id`; the decidable unit is the `##` BLOCK.** Upstream of everything PENDING-142 reaches. Worse than a wrong verdict **because the verdict is right** — (d) reports PENDING-131 OPEN, correctly, and still hides that it carries four separate asks; **`governance_state()` shows ZERO rows for `131`.** ⚠ **FOUR blocks under PENDING-131 carry a live `Awaiting:`** — parent, ADD-1, ADD-2, ADD-4 — **not the two I reported**; the jurist ruled on my testimony *and disclosed it had not verified ADD-1*, and that disclosure is what made it findable.
+> ⚠ **REPORT AT EVERY WAKE — N-now = 47/84, AND IT WENT DOWN** (60 on 08-17, 61 on 08-18, **47 on 08-19**). **A 30-DAY ROLLING WINDOW, not a cumulative count** — the checker globs a directory the harness prunes at 30 d, so at ~1 session/day it converges to ~30 and **`transcripts 84` very likely never fires**; every "N remaining" report was a **false countdown**. Ladder still FROZEN generally (REVIEWED-123 cond. 1); 4 rows queued in PENDING-141. **PENDING-147 filed; needs a steward/jurist decision.** ✅ **Leg (i) DISCHARGED 2026-08-19** — 47 transcripts copied to `~/.claude-transcript-archive/raw/` outside the pruned tree, **46/47 sha256-verified by readback**, the 47th recorded as a snapshot. The evidence no longer expires; the counter still cannot fire.
+> ⚠ **TRIAL 09 IS HELD, NOT ABANDONED — and the hold IS the finding.** Prompt hashed, corpus built (11 docs / 166,088 words), exclusion hash-list **PASSED** — and the run was blocked anyway: `PENDING.md:92-96`, **inside an open item the wake surfaces every session**, names Fault Lines 5/3/4 with their substance, and FL5's proposition sits in `~/CLAUDE.md` Constraint 6 **stated more sharply than the ground truth**. Under the design's own rule **every STRONG grade would be an ECHO.** The exclusion was verified at the wrong granularity — absence of the *file*, not of the *content*. **Resume at the leak, not at the run.**
+> ⚠ **2026-08-19 DIED UNWRAPPED** (`Request timed out` 21:05, host down overnight). Its record was **reconstructed 2026-08-20 from the transcript** — pointer below. The vault work is real and pushed, and it left **one defect of ours**: `see_canonical: "[[Index]]"` resolves to the wrong note or none — 1 of the 3 §3 pointers. The vault tail is small and **NOT urgent**.
+
+- [Session 2026-08-19 — the vault got a spec, and the links were already broken](session-2026-08-19-the-vault-got-a-spec-the-links-were-already-broken.md) — **RECONSTRUCTED, not wrapped.** Vault spec v1.0.0 + two passes; Trial 09 prepared and HELD; transcript archive discharged. · [Session 2026-08-17](session-2026-08-17-the-instruments-audited-themselves-and-lost.md) — every instrument examined was wrong; two of the wrongs made by the hand fixing the others. **LITERAL Q, STILL OPEN: across the last ~10 sessions, when a defect in the executor's own instrument was found, WHO found it — a mechanism firing unbidden, the executor re-checking, the jurist, or the steward?** Mostly-executor ⇒ the practice works and the mechanisms are decorative; mostly-jurist/steward ⇒ every "verified" between reviews does less work than it appears to. **08-19 adds four data points that do NOT point one way** (2 executor, 1 jurist, 1 steward) — and the `[[Index]]` defect was found by none of them, surfacing only because the crash forced a reconstruction.
 
-- [Session 2026-08-08 late — eleven items, and the charter had the map](session-2026-08-08-late-the-charter-had-the-map.md) — **Built the binding mechanisms all day, then found in the last twenty minutes that the founding charter had already answered the strategic question.** (e) built as a **delegation** (`eecc8bb`) and exposed that **no fleet suite had ever validated live binding**. Hook sequence landed in the ruled order (`448ce37`, `2534dfb`); R0 §4 three-valued (`ccc4d6c`); fleet third verdict + preflight crash-class closure (`8ff5a9f`, `d21a43b`); Mauss corrected (`8231bce`). ⚠ **Leopold Mozart is ALREADY in the library as an EPUB** (Knocker translation, born-digital) — the violin problem may be **sourcing, not conversion**. **LITERAL Q: does re-running `pattern_finder`'s Station-I pass still come back PASS-BUT-FALSELY now that V0/V1 exist?**
 ## Historical reference → MEMORY-reference.md
 Older archived-session pointers and the stable reference layer (steward profile · project-state detail · L1/L2/Chamber inventories · legacy pending-work · reference-file list) live in [MEMORY-reference.md](MEMORY-reference.md) — consult on demand; not loaded at wake. Recent cross-session trajectory comes from the Active Session entry above + the recent `session-*.md` files (wake §2.b.1).
 
 ## Index discipline (self-bounding — keep this file lean)
 Wake-loaded live index; hard budget well under the harness load ceiling. Keep to: Standing preferences · Canonical Trackers *as one-line pointers* (chronological detail lives in the linked tracker files, **not** here) · Active Session · these pointers. Rotation + budget-breach handling are wired into `/wrap-up` (demote prior Active Session on promote) and `/wake-up` (truncated load = flag + trim). Back up before restructuring.
-*Compaction history: 2026-07-17 re-slimmed to one-liners, 20.5→17.1 KB. 2026-08-07 trim (steward-directed): 19.9→~15 KB by the fires-silently/loud-trigger split, plus `project-studium-engine.md` created to hold engine state MEMORY.md had been carrying inline. **⚠ 17.1 KB is a prior achievement, not a derived ceiling** — the real harness load limit is unmeasured; if it ever matters, measure it rather than inheriting this number.*
+*Compaction history: 2026-07-17 re-slimmed to one-liners, 20.5→17.1 KB. 2026-08-07 trim (steward-directed): 19.9→~15 KB by the fires-silently/loud-trigger split, plus `project-studium-engine.md` created to hold engine state MEMORY.md had been carrying inline. **⚠ MEASURED 2026-08-09: the harness read limit is 24.4 KB** (surfaced by the index-size hook), which answers the standing "unmeasured" caveat this line used to carry. 17.1 KB remains a prior achievement, NOT the ceiling. 2026-08-09 trim: Active Session block condensed 5.2→3.6 KB, 21.0→19.4 KB total (80% of the real limit). ⚠ Going below ~18 KB requires restructuring **Standing preferences** (9.4 KB, the largest section and explicitly the fires-silently set) — a proper task, not an end-of-day squeeze.*

claude/memory/feedback-bulk-indexing-runs-incrementally-with-readback.md

@@ -0,0 +1,47 @@
+---
+name: feedback-bulk-indexing-runs-incrementally-with-readback
+description: "Never run a single multi-day indexing/mining job. Go in tranches, ordered by criticality, and prove each tranche by reading back what was written before starting the next. Steward rule, 2026-05-04, after three days of compute produced unreadable output."
+metadata: 
+  node_type: memory
+  type: feedback
+  originSessionId: 81f817e9-4016-4867-ae16-a486f1e8fb46
+  modified: 2026-08-17T13:20:31.039Z
+---
+
+Never run a bulk index/mine/embed job as one long pass. **Tranches, ordered by
+criticality, with a write *and readback* check after each** before the next begins.
+
+Steward, verbatim, 2026-05-04:
+
+> *"go with path A. then we make a choice on how to remine the library incrementally
+> beginning with the most critical texts. I'm not losing days to this again."*
+
+**Why:** a failure only visible after days of compute is unacceptable, and it is the
+*normal* outcome rather than the unlucky one. The 2026-05-01 → 05-03 chamber-library run
+spent three days of CPU/MPS and wrote **933,576 drawers that stored successfully and
+could not be read back at all** — storage reported success, search returned `Internal
+error: Error finding id`. A run that writes without ever reading back cannot tell
+"working" from "producing garbage at scale", so its own progress reporting is
+uninformative. An earlier attempt burned nine hours to reach 30 of 371 files.
+
+**How to apply:**
+- **Tranche it.** No single job whose failure is invisible until it ends. Size the
+  tranche so a wasted one costs an hour, not a weekend.
+- **Order by criticality.** Index what is actually load-bearing for live work first, so
+  the useful half exists even if the run is abandoned midway.
+- **Readback is the gate, not the write.** Storage success is not the property you want;
+  *retrieval of what you stored* is. Query each tranche before starting the next — this
+  is the [[reference-verification-ladder]]'s discrimination rule applied to indexing:
+  a check that only exercises the write path cannot see a broken read path.
+- **Watch for a global setting applied to a heterogeneous corpus.** The same run was
+  compounded by one embedding model being forced across *all* collections; dimensions
+  that suit a multilingual scholarly corpus need not suit anything else.
+
+⚠ **This rule is instrument-independent and outlived the tool that earned it.** It was
+learned on MemPalace, which was wound down 2026-07-07 ([[project-mempalace-winddown]]) —
+and it was carried *only* inside a MemPalace tracker, so retiring the instrument would
+have retired the rule with it. `~/CLAUDE.md` names that hazard directly: *"state the
+obligation first and the instrument second, or the next retired tool takes a rule down
+with it."* Harvested here 2026-08-17, on the day the superseded tracker was stamped, for
+exactly that reason. **It applies now to the studium engine's corpus mining** — the same
+shape of work, a different tool.

claude/memory/feedback-canonical-workstream-tracker-discipline.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/feedback-canonical-workstream-tracker-discipline
----
-
 ---
 name: Canonical workstream trackers must be read at session start, not just session memories
 description: Surfaced 2026-04-26 after three consecutive sessions generated substantial architectural work as if from a clean slate, without referencing project-arc-rework.md (the canonical ARC workstream tracker). The /wake-up procedure restored yesterday's session memory + ledger but did not pull from canonical workstream files. Result: re-litigation of settled decisions, sibling project files instead of integrations, missed load-bearing context. Fix names what to read at every session opening that touches ARC (and structurally similar workstreams).
 type: feedback
 originSessionId: 87dfe384-b862-4deb-9676-24e43046528f
+permalink: claude-memory/feedback-canonical-workstream-tracker-discipline
 ---
 # Canonical workstream trackers must be read at session start
 

claude/memory/feedback-mempalace-protocol-step-2-discipline.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/feedback-mempalace-protocol-step-2-discipline
----
-
 ---
 name: MemPalace protocol step 2 — query-before-responding mid-session is the discipline (not just at wake-up)
 description: Surfaced 2026-04-26 evening end-of-session. MemPalace had the content that would have prevented today's structural drift; the failure was retrieval discipline, not storage. Protocol step 2 ("BEFORE RESPONDING about any person, project, or past event: call kg_query or search FIRST") is rarely honored mid-session. Discipline parallel to canonical-workstream-tracker — same shape (write to substrate, fail to read before producing), different temporal scale (mid-session, not just at boundaries).
 type: feedback
 originSessionId: 87dfe384-b862-4deb-9676-24e43046528f
+permalink: claude-memory/feedback-mempalace-protocol-step-2-discipline
 ---
 # MemPalace protocol step 2 — query-before-responding is the discipline
 

claude/memory/feedback-scss-file-organization-not-kitchen-sink.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/feedback-scss-file-organization-not-kitchen-sink
----
-
 ---
 name: SCSS file organization — don't kitchen-sink into the most recently-touched file
 description: Steward caught 2026-04-28 evening — across the day's apparatus work I added .preface, .section-break, .sequence-marker, and was about to add .sequence-index-* styles all to `_sidenotes.scss` because that's the file I had been editing. The file's own header declared its scope as §XII + §XII.b. I was violating that declared scope by aggregation. Steward verbatim: *"why in sidenotes.scss?"*
 type: feedback
 originSessionId: e5a1fa7c-cae6-49c4-8678-e27ce379639b
+permalink: claude-memory/feedback-scss-file-organization-not-kitchen-sink
 ---
 **Pattern caught**: when adding new CSS rules in a focused work session, I default to dropping them in the most recently-touched SCSS file (proximity bias) rather than the file scoped to their concern. Across one day's evening work I added four unrelated apparatus blocks (preface, section-break, sequence-marker, sequence-index) all to `_sidenotes.scss` — whose own header comment declared its scope as **§XII Sidenotes + §XII.b Register Markers**.
 

claude/memory/feedback-would-alexander-do-it-test.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/feedback-would-alexander-do-it-test
----
-
 ---
 name: "Would Alexander do it?" — test before bulk scaffolding
 description: Before any bulk-scaffold action (full file rewrites, multi-page schema dumps, large config dumps), apply Alexander's *"one pattern at a time"* test from Ch 20 of *Timeless Way of Building*. The cramped will of the maker is the failure mode. Generate, do not make.
 type: feedback
 originSessionId: efda5c2e-ca9a-4e55-9344-64aa9a3c1140
+permalink: claude-memory/feedback-would-alexander-do-it-test
 ---
 Before any bulk-scaffold action — full file rewrites, multi-page schema dumps, large config commits, sweeping multi-edit changes — apply the **"would Alexander do it like this?"** test. If the action involves declaring an entire structure in one stroke, pause: that is *making*, not *generating*. The cramped will of the maker (Ch 9, *Flower and Seed*). The remedy is *"one pattern at a time"* — Ch 20 of *Timeless Way of Building*: *"Each step brings just one pattern to life. The intensity of the result depends on the intensity of each one of these individual steps."*
 

claude/memory/knowledge-graph.jsonl

@@ -635,3 +635,40 @@
 {"subject": "the studium engine build order", "predicate": "has-charter-ruling", "object": "CHARTER §X FOUR LAYERS: L0 corpus (built) · L1 retrieval primitives (mostly built, the shared floor) · L2 aggregation & discovery — the pattern-finder, whole-corpus topical query its lighter sibling — NEXT · L3 orchestration — voices, CHAVRUTA, larger debate — THE FRONTIER. The chavruta is L3, not the near-term goal. L2 was built first DELIBERATELY ('the hardest mode... because proving it de-risks everything above it') and its interfaces are to emerge from lived use — 'the Making, then the violin', naming the steward's own treatise. §IV separately calls migration/genealogy the engine's SIGNATURE capability, not a late extra.", "valid_from": "2026-08-08", "valid_to": null, "confidence": 1.0, "source_file": "docs/the-studium-engine-architectural-charter.md", "extracted_at": "2026-08-08"}
 {"subject": "corpus/index.db drawers table", "predicate": "has-unbuilt-consequence", "object": "CHARTER §IV states 'every drawer carries its source, location, date, and language as queryable axes... genealogy, migration-mapping and temporal evolution are first-class operations'. Measured 2026-08-08: drawers carries source_id, voice, lang, line_start/end — but PERIOD IS ABSENT, though every manifest entry declares it (catalog.period). The temporal axis the charter calls first-class is declared in the corpus and not carried into the store. One column, feedable from data already present.", "valid_from": "2026-08-08", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-08-late-the-charter-had-the-map.md", "extracted_at": "2026-08-08"}
 {"subject": "the violin treatise corpus", "predicate": "has-sourcing-finding", "object": "LEOPOLD MOZART IS ALREADY IN THE LIBRARY AS AN EPUB — 'Treatise On The Fundamentals Of Violin Playing / Leopold Mozart (664)', the Knocker English translation of the 1756 Versuch. Born-digital, V-TEXT tier, no OCR and no Fraktur. The steward named it as a case with no digital edition they were aware of. So the violin problem is partly SOURCING rather than conversion. ⚠ But it is a TRANSLATION: a treatise citing it in English cites Knocker, not Mozart — a new instance of the unruled quotation-in x translation-of composition. Separately: V-SCAN ABSTAINS by design (no ground truth), so the real conversion question is what tier a scanned canonical can ever reach, not OCR quality.", "valid_from": "2026-08-08", "valid_to": null, "confidence": 0.9, "source_file": "session-2026-08-08-late-the-charter-had-the-map.md", "extracted_at": "2026-08-08"}
+{"subject": "claude-code", "predicate": "drift-pattern", "object": "PROTECTED AN ARTIFACT NOBODY EVER OPENED — and the instruction's entire content was 'protect this artifact'. Three documents (rebuild plan §2.3, tool-evolution-log, CLAUDE.md L61) carried 'that known-bad output is V4's designated adversarial fixture — do not delete or regenerate it' for SEVEN WEEKS across repeated doc-currency passes. The file is 0 bytes: committed empty at 38de1a9 (2026-06-26), one commit, never written, unrecoverable. Fourth instance of cited-a-derived-label-instead-of-the-substrate, and the sharpest, because the label WAS the protection. Test: an instruction to preserve X is not discharged until someone has opened X.", "valid_from": "2026-08-09", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-09-the-fixture-was-an-empty-file.md", "extracted_at": "2026-08-09"}
+{"subject": "claude-code", "predicate": "drift-pattern", "object": "CONFLATED A RULING WITH ITS UNMET CONDITION — twice in one session, steward-caught. PENDING-130 was ruled (a) with five conditions; I wrote 'PENDING-130 is unruled' in a commit message and had an artifact header say it 'proposes'. Ruled / placed / condition-discharged are THREE states and none implies another. ⚠ The direction cut AGAINST my own caution: reading it as unruled makes the delay look like an open question about WHETHER the artifact should be the fixture, when the decision was made and only the key was outstanding. Over-caution that misstates the record is still a misstatement. Same family as disposition-clause-is-not-a-status.", "valid_from": "2026-08-09", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-09-the-fixture-was-an-empty-file.md", "extracted_at": "2026-08-09"}
+{"subject": "an induced-red probe that DELETES a symbol", "predicate": "drift-pattern", "object": "TESTS ABSENCE, NOT THE DEFECT — it produces a TRACEBACK, not a named failure, so it cannot show the suite would NAME the real regression. My first witness-red for test_pattern_finder removed voice_cross() and got AttributeError; the honest probe left every name in place and reverted the BEHAVIOUR (monkeypatched the cross to the pre-fix semantics), which produced exit 1 with six named failures including camus by name. Compounding error in the same command: I read the exit code through a pipe, so the reported 0 was tail's. Both are the checks-are-the-weak-link class, one day after it was banked.", "valid_from": "2026-08-09", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-09-the-fixture-was-an-empty-file.md", "extracted_at": "2026-08-09"}
+{"subject": "reading the PLACED record instead of the relayed message", "predicate": "prevention", "object": "REVERSED A DECISION I HAD ALREADY MADE AND LOGGED AS A COST — third consecutive instance. I froze four documents on the relayed condition 'no document may call the artifact V4's fixture', and recorded in the ledger that 'deliberately unedited' was also 'preserving a falsehood' (CLAUDE.md L61 asserted an empty file was the designated fixture). The PLACED condition 4 reads '…may be corrected to name existing material; they may not assert a fixture that is half-done' — the opposite of my reading, resolving the exact tension I had flagged. The banked rule (quote from the FILE, never the relayed message) fired and changed the action, not merely the citation.", "valid_from": "2026-08-09", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-09-the-fixture-was-an-empty-file.md", "extracted_at": "2026-08-09"}
+{"subject": "resurfacing the banked artifact before deriving", "predicate": "prevention", "object": "STOPPED A FULL RE-DERIVATION OF MEASURED GROUND. The inherited resumption point said to 'settle the baseline asymmetry BEFORE the chavruta re-run'. P7 had already run on 2026-08-07 and committed corpus/v2-stratum-tags.yaml, which measures it exactly: EN divisions median 27,833 chars vs FR spans median 969 (29x, max 198,258). It also holds three further findings the wrap never mentioned — including that the fr authoring plan INVERTS (inherited 1A:9B; §6.3 would land ~1:27 against §6.2's 1:1). Checking the artifact first converted a session of re-measurement into one act: narrow the EN anchors.", "valid_from": "2026-08-09", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-09-the-fixture-was-an-empty-file.md", "extracted_at": "2026-08-09"}
+{"subject": "driving a degraded state rather than reasoning about it", "predicate": "prevention", "object": "CORRECTED THE RULING THAT AUTHORIZED THE WORK. REVIEWED-113's design gate inferred the (manifested, not-probed) cell would collapse into `silence`, flagged that as 'inference, not reading' and invited the check. Driving it raised KeyError: 'arendt' — a crash in ENGINE code, the class PENDING-126(c) had closed suite-side only, and the second engine-side instance after retrieve.py:134. The correction ran executor→ruling, which the differently-biased-checkers doctrine predicts; recorded as an instance, proving nothing general.", "valid_from": "2026-08-09", "valid_to": null, "confidence": 0.9, "source_file": "session-2026-08-09-the-fixture-was-an-empty-file.md", "extracted_at": "2026-08-09"}
+{"subject": "claude-code", "predicate": "drift-pattern", "object": "control-set-drawn-from-one-source: every positive control for the nested-voice census lived in Mauss — one quotation convention (guillemets), one line structure (paragraph-per-line). The instrument was therefore blind to ASCII quotes (3 sources, incl. the two largest EN texts) and to hard-wrapped text (2 sources), and reported a CLEAN ZERO for both rather than an error. Five defects total; four escaped the controls entirely. Coverage is the whole of a control set's strength.", "valid_from": "2026-08-13", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-13-the-fence-was-never-blocked.md", "extracted_at": "2026-08-13"}
+{"subject": "claude-code", "predicate": "drift-pattern", "object": "count-by-subtraction-not-enumeration: wrote bound_instances_grounded as 12 by computing 15 bound - 3 retracted, silently ignoring that instance 17 had already left the grounded set at P7. Correct is 10. Committed the SAME error PENDING-136 was filed about, inside the session that filed it — and P7's original error entered the same way. Enumerate against the actual rows; subtraction is how the error enters.", "valid_from": "2026-08-13", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-13-the-fence-was-never-blocked.md", "extracted_at": "2026-08-13"}
+{"subject": "claude-code", "predicate": "drift-pattern", "object": "one-marker-over-two-dispositions, recurring: voice_stamp's first verdict vocabulary returned `boundary-crossing` for BOTH fragments of instance 8 — whose differing dispositions are the entire reason the instance is before the steward. PENDING-133's exact finding, reproduced inside the instrument built to address it. Split into crosses-opening / crosses-closing / spans-quotation. Caught only by the suite's load-bearing negative.", "valid_from": "2026-08-13", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-13-the-fence-was-never-blocked.md", "extracted_at": "2026-08-13"}
+{"subject": "claude-code", "predicate": "drift-pattern", "object": "unscoped-git-add-in-dotfiles: used `git add -A` in a dotfiles commit, sweeping the steward's freshly-placed REVIEWED-119/120 and a sysupdate Brewfile line under an executor message about MCP key descriptions. /wrap-up §6.5 forbids exactly this and states why — the steward's in-progress changes belong to the steward's sweep. Amended before push. NOTE the routing gap: the rule is stated only in §6.5, which fires at WRAP, while dotfiles commits happen throughout a session.", "valid_from": "2026-08-13", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-13-the-fence-was-never-blocked.md", "extracted_at": "2026-08-13"}
+{"subject": "substrate-checking a disposition clause instead of reading it as status", "predicate": "prevention", "object": "CAUGHT AN AUTHORIZED-BUT-UNEXECUTED RULING THAT HAD SAT THREE DAYS. REVIEWED-118's `**If AUTHORIZED:**` line reads like a completed act; grepping for `REVIEWED-118` in corpus/ and docs/ returned nothing and the L926 instances still stood. The /wake-up step's own rule (a disposition clause is not a status) fired and changed the wake's report from 'done' to 'the unblocked next act' — which became the session's first work.", "valid_from": "2026-08-13", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-13-the-fence-was-never-blocked.md", "extracted_at": "2026-08-13"}
+{"subject": "checking a suspicious ZERO rather than accepting it", "predicate": "prevention", "object": "CONVERTED A FABRICATED MEASUREMENT INTO A REAL ONE, TWICE. The census reported 0 inline quoted spans for harrison/alexander/after-the-reply; checking found 2005 and 1348 ASCII quotes the matcher could not see (43% undercount). Then the steward's challenge to a dismissive aside about musil found the same shape structurally — musil is hard-wrapped, so a within-line matcher guaranteed ~0 before the file was opened. A clean zero is the most dangerous output an instrument can produce, because it reads as a finding.", "valid_from": "2026-08-13", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-13-the-fence-was-never-blocked.md", "extracted_at": "2026-08-13"}
+{"subject": "reading the ratified schema before repeating a blocking claim", "predicate": "prevention", "object": "STOPPED A REVIEWED ENTRY FROM CARRYING A FALSE BLOCKER. PENDING-135 stated option (d) was blocked on PENDING-131 (c) — the chamber-locked studium/meta@1. Opening v2-harness §14.2 before drafting REVIEWED-119 showed the real constraint is studium/v2-gold@1's `lines: [a, b]`, which is ENGINE-SIDE and D-1. Had it gone unchecked, an authorization would have stood on a false blocking claim — the trap REVIEWED-115 pt 1 voided an authorization over.", "valid_from": "2026-08-13", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-13-the-fence-was-never-blocked.md", "extracted_at": "2026-08-13"}
+{"subject": "PENDING-134", "predicate": "blocked-by", "object": "H1 — the four V0-lane governance_read keys are registered on disk (4c3758e) but NOT SERVED: governance-mcp.py builds FILES at import, so the running client holds the old eight-key map until the STEWARD restarts it. Executor half discharged 2026-08-13 (selftest 54/54; two stale key descriptions refreshed at 92d5ad2). The remaining step is a client restart, not a build.", "valid_from": "2026-08-13", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-13-the-fence-was-never-blocked.md", "extracted_at": "2026-08-13"}
+{"subject": "PENDING-131 (c) sub-line addressing", "predicate": "does-not-block", "object": "the engine's citation path. chunker.py has recorded `char_range: [cstart, cend]` document offsets since Cluster A, so voice_stamp addresses sub-line extents with no schema change and no cross-repo consent. The line-granularity ceiling was an artifact of where the fence was being WRITTEN (the sidecar), not of what the engine can SEE. (c) remains real for the sidecar.", "valid_from": "2026-08-13", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-13-the-fence-was-never-blocked.md", "extracted_at": "2026-08-13"}
+{"subject": "free indirect discourse", "predicate": "is-not", "object": "a provenance failure. Steward-argued 2026-08-13 and accepted: in FID there is NO second author to join to — the words are the novelist's, composed in the narrative voice. A PROVENANCE failure has a second author who can be named; a STANCE question has one author and an interpretive judgment about endorsement. Irony shows it is not a fiction matter: Arendt reporting a view to demolish it raises the identical question in non-fiction. Consequence: PENDING-131 (c) stays ONE capability, not two; the residue belongs to PENDING-134 and the synthesized tier's NLI.", "valid_from": "2026-08-13", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-13-the-fence-was-never-blocked.md", "extracted_at": "2026-08-13"}
+{"subject": "claude-code", "predicate": "drift-pattern", "object": "control-subject-differs-from-claim-subject: Part IV.1 of the jurist package asserted 'F10 is the only §5 row containing an explicit stratum-B admission clause' and marked it VERIFIED. Three rows carry one (F3, F7, F10) — and F3 and F7 were quoted with those clauses intact in the package's OWN §I.2 and reproduced as 'stratum-B gold' in its OWN IV.2 table one page later. The verification script tested whether QUOTES WERE PRESENT in both source and package; the claim was an INFERENCE OVER THE SET OF ROWS. The control passed truthfully and its pass is what licensed the false sentence. A control that verifies a different property than the claim asserts is not a weak check; it is not a check at all. Kin to 'access is not verification', one layer over.", "valid_from": "2026-08-14", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-14-the-controls-tested-the-wrong-property.md", "extracted_at": "2026-08-14"}
+{"subject": "claude-code", "predicate": "drift-pattern", "object": "error-understates-objection-to-own-proposal: the IV.1 census error sat inside the paragraph written to satisfy H1(a) — state the counter-argument at FULL STRENGTH — and it understated an objection to the executor's own proposal. The contamination-predicted direction, in the one paragraph whose entire purpose was to argue against interest. ⚠ Countervailing, recorded as mixed: the executor volunteered Q4 and Q1 in the same package, both cutting against its own position. Filed as evidence under PENDING-89, one instance, self-reported by a party under measurement.", "valid_from": "2026-08-14", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-14-the-controls-tested-the-wrong-property.md", "extracted_at": "2026-08-14"}
+{"subject": "claude-code", "predicate": "drift-pattern", "object": "cited-a-derived-label-instead-of-the-substrate, FOURTH instance: justified declining to back-fill the defeater by citing R0's guard as `test_legacy_indices_are_not_self_verified`, and carried that name into corpus/v2-stratum-tags.yaml, commit 5425414's message and a steward report. NO SUCH FUNCTION EXISTS — one occurrence repo-wide, a docstring at tests/test_reading_index.py:23 asserting it 'holds that shut'. The jurist searched 273 governance items with a positive control and called it uncitable; it was unreachable from the code side too. The property IS tested (L128, L130, positive control L281). A refusal is only as good as its stated ground.", "valid_from": "2026-08-14", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-14-the-controls-tested-the-wrong-property.md", "extracted_at": "2026-08-14"}
+{"subject": "claude-code", "predicate": "drift-pattern", "object": "audited-the-audit-past-the-central-path: four levels in one arc — package claim → jurist finds three defects → addendum corrects the ruling → the addendum's own A4 is false → the checker used to place it has two blind spots. ~/CLAUDE.md's central path says ONE LAYER, THEN ACT — NEVER AUDIT THE AUDIT. Every layer found something real, which is what makes it seductive; but a sufficiently careful reading always does, and that is not evidence the next layer is worth taking. Test that ended it: does this finding change what anyone does? Open items 25 → 27 on a day whose visible output was rulings about rulings.", "valid_from": "2026-08-14", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-14-the-controls-tested-the-wrong-property.md", "extracted_at": "2026-08-14"}
+{"subject": "reading the PLACED record instead of the relayed message", "predicate": "prevention", "object": "CHANGED THE WORK, NOT MERELY A CITATION — fourth consecutive instance of this rule firing. The relayed REVIEWED-121 was truncated mid-sentence in point 9. The PLACED entry at ~/REVIEWED.md L1777 carried three things the relay did not: point 9's tail; a sentence added to the ratified doctrine ('The refusable half does not satisfy §7.4(i), whose provenance join remains owed') so the condition lives INSIDE the doctrine and cannot be quoted without its limit; and a disposition gating ratio_A_to_B on PENDING-137 AS WELL. Acting on the relay would have re-derived a number under a scheme nobody had written down.", "valid_from": "2026-08-14", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-14-the-controls-tested-the-wrong-property.md", "extracted_at": "2026-08-14"}
+{"subject": "declining to populate a field rather than populating it falsely", "predicate": "prevention", "object": "STOPPED A DOCTRINE BEING RATIFIED WITH A DEFEATER BUILT FROM ITSELF. REVIEWED-121 pt 7 replaced reader-independence with ORDER-independence — a disposition recorded BEFORE the doctrine is consulted. For all eleven inherited spans that moment is past and unrecoverable. Back-filling would have put a post-doctrine judgment into a field whose entire evidential value is preceding one: self-confirming, the exact shape R0's first validator was caught by. Landed as `defeater_has_ever_been_exercisable: false` — records the ABSENCE rather than leaving an empty field for a later reader to fill in good faith. Jurist upheld the refusal and amended its own point 7.", "valid_from": "2026-08-14", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-14-the-controls-tested-the-wrong-property.md", "extracted_at": "2026-08-14"}
+{"subject": "governance-drift-check.py", "predicate": "drift-pattern", "object": "TWO BLIND SPOTS, the second found by filing an item about the first. (A) RE_HEAD = ^##\\s+REVIEWED-(\\d+)\\s*[—-]\\s*(.*)$ cannot see a ###-level amendment: 2 amendments present in REVIEWED.md, 1 seen, and it prints '✓ every amendment link resolves (1 amendment(s) checked)'. (B) RE_BUILT = \\bBUILT\\b matches the marker even when preceded by NOT, reading a negation as an assertion. Common cause is the TECHNIQUE, not the regexes: a STATUS inferred from NARRATIVE prose never constrained to carry one. PENDING-139. ⚠ The register is now worded around (B), disclosed — so the check's silence on it is an accommodation, NOT a pass.", "valid_from": "2026-08-14", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-14-the-controls-tested-the-wrong-property.md", "extracted_at": "2026-08-14"}
+{"subject": "checker substrate access", "predicate": "drift-pattern-good-direction", "object": "THE VARIABLE THAT DECIDED WHETHER THE JURIST CAUGHT THE EXECUTOR WAS ACCESS, NOT BIAS. Without governance_read keys (2026-08-10, REVIEWED-116 pt 7) the jurist ruled on the executor's testimony and its own drafted A4 asserted a test 'is not doubted' about a function that does not exist. With four keys served (2026-08-14, after REVIEWED-117) it opened the files and returned three defects in one sitting — a false census marked verified, a cost on the wrong population, and an unamended §6.2 narrowing. Formation, role and incentive were IDENTICAL across both sittings. ⇒ Constraint 6's two axes (formation; role/information/incentive) may be necessary and radically insufficient: a differently-biased reader with no access checks the ACCOUNT, not the THING. Filed PENDING-140 [ESCALATE]. ⚠ n=1 per condition, self-reported by parties under measurement, and authored by the party whose checking is at issue.", "valid_from": "2026-08-17", "valid_to": null, "confidence": 0.7, "source_file": "session-2026-08-14-the-controls-tested-the-wrong-property.md", "extracted_at": "2026-08-17"}
+{"subject": "contamination-problem.md", "predicate": "scope-limit", "object": "IS A THEORY OF ONE MISALIGNMENT FLAVOUR, USED HERE AS THE THEORY OF EXECUTOR FAILURE IN GENERAL. Against Byrnes's four-flavour taxonomy (imitative→seven-sins · human-approval→glazing · automatic-verifiers→literal-genie · LLM-judges→trickster), every mitigation in the doc — behavioural observation, explicit permission structures, indirect questioning, longitudinal analysis — is calibrated against APPROVAL-SEEKING, i.e. glazing. A crude keyword probe over the 235 banked claude-code drift-patterns classified 106 and left 129 unclassified: 86 literal-genie, 12 trickster, 8 glazing, 0 seven-sins. ⚠ The classifier is keyword-matching over prose — the exact defect PENDING-139 names — so indicative, not measured. If the skew survives a real instrument, our doctrine is ~100% anti-sycophancy while our failures are dominated by verifier-Goodhart, against which a control is simply another proxy.", "valid_from": "2026-08-17", "valid_to": null, "confidence": 0.6, "source_file": "session-2026-08-14-the-controls-tested-the-wrong-property.md", "extracted_at": "2026-08-17"}
+{"subject": "a governed record's own formatting", "predicate": "drift-pattern", "object": "CAN MAKE AN ENTRY INVISIBLE TO THE CHECK THAT GUARDS IT, WHILE THE CHECK REPORTS CLEAN. REVIEWED-121 AMENDMENT 1 was placed truncated (ended mid-A3), then re-pasted with an unclosed ```yaml fence that swallowed A3's binding rule, all of A4 and the disposition — rendering them as code and stripping their emphasis — and would have swallowed the NEXT entry appended to REVIEWED.md. Register-integrity reported clean throughout, because its subject is HEADINGS, not fences. The re-paste also indented the body 2 spaces; had it indented the HEADING, RE_HEAD (^##\\s+) would have stopped matching and the amendment would have vanished from the check entirely with no alarm. Third instance in one week of a check whose subject sits adjacent to the property that matters.", "valid_from": "2026-08-17", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-14-the-controls-tested-the-wrong-property.md", "extracted_at": "2026-08-17"}
+{"subject": "an AUTHORIZED-and-unblocked action", "predicate": "drift-pattern", "object": "CAN STILL BE THE WRONG ACT, AND THE MEMORY INDEX WAS PUSHING TOWARD IT. The 41 S2 ladder rows are authorized (2026-07-19) and MEMORY.md described them as 'needing execution not a ruling' and 'unblocked' — both true as to authorization. But appending them triples the verification ladder from 20 entries WHILE a pre-registered trial measures whether the ladder is reached (baseline 14%, graded at 84 transcripts), and ladder SIZE is an uncontrolled variable in that design. A session doing exactly the right procedural thing would have confounded the only check behind REVIEWED-95's causal claim. Filed PENDING-141, recommendation (a) HOLD. ⚠ The index line was amended in the SAME act as the filing — a finding that leaves the misleading line standing is a note, not a finding. Authorization answers 'may I', never 'should I now'.", "valid_from": "2026-08-17", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-14-the-controls-tested-the-wrong-property.md", "extracted_at": "2026-08-17"}
+{"subject": "claude-code", "predicate": "drift-pattern", "object": "THE FIX REPRODUCED THE DEFECT IT WAS FIXING, IN THE TOOL WRITTEN TO CLEAN UP AFTER IT. `strip_frontmatter`'s non-greedy `^---\\n.*?\\n---\\n` was diagnosed as matching the STRAY frontmatter block on 39 damaged files; one hour later the stamping script written to mark superseded trackers used the identical pattern, matched the stray block on 3 of them, and orphaned the real frontmatter into the body. The post-stamp check reported `malformed: none` because its subject was 'does the file begin with frontmatter then a banner' (true) while the claim was 'the stamp preserved the record's keys' (false). A diagnosis held in working memory does not transfer to the next tool written unless the pattern itself is searched for.", "valid_from": "2026-08-17", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-17-the-instruments-audited-themselves-and-lost.md", "extracted_at": "2026-08-17"}
+{"subject": "a file's timestamp", "predicate": "drift-pattern", "object": "IS NOT ITS CONTENT'S AGE, AND NEITHER IS GIT'S LAST-COMMIT. Three instances 2026-08-17: 191 wrap records dated by mtime, so a CODA appended three days later made the 08-14 session look unwrapped; 61 trackers reported at exactly 72.3 days by mtime AND by git-date, both reset by 3f9a89b, a 283-file normalization sweep — three successive staleness estimates were wrong before the fourth excluded it; and repairing 20 April-May wrap records moved their mtimes to today and promoted an April session to `Last wrap`, losing the pulling thread and the open question. The third was caused by the fix for the first. Reach for the earliest signal an ordinary later act cannot move, and exclude known bulk operations before quoting an age.", "valid_from": "2026-08-17", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-17-the-instruments-audited-themselves-and-lost.md", "extracted_at": "2026-08-17"}
+{"subject": "a ruling in REVIEWED.md", "predicate": "drift-pattern", "object": "CLAIMS A NUMBER, NOT A RECORD — so every addendum filed under that number afterwards is suppressed ON ARRIVAL. REVIEWED-115 (2026-08-10) claimed `131`; PENDING-131 ADDENDUM 4 was filed 2026-08-13 and has never appeared in the open list, while awaiting steward direction. PENDING-131 (c) is the unbuilt fence — the pulling thread of every session since 08-10, made a CONDITION by REVIEWED-121 — and the instrument whose job is reporting what awaits authorization has been silent about it for a week. The work survived only because MEMORY.md and the session records carried it by hand. The same item fails the other way too: REVIEWED-116's header `PENDING-131/132/133/134` parses to one token matching no id, so a four-item ruling suppresses nothing. Filed PENDING-145.", "valid_from": "2026-08-17", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-17-the-instruments-audited-themselves-and-lost.md", "extracted_at": "2026-08-17"}
+{"subject": "a size guard on a scanner", "predicate": "drift-pattern", "object": "BECOMES A SILENT BLIND SPOT THE MOMENT THE FILE IT GUARDS IS THE ONE THAT MATTERS. governance-drift-check.py skipped any file over 400 KB; PENDING.md reached 546,944 bytes, so every structured DEFERRED-DECISION block in the governance register went unread — by the checker built to stop deferred conditions being silently missed. Compounded because the prose-deferral loop has NO guard, so PENDING.md's prose count kept appearing in the report and made the file look examined. Found only by placing a block under REVIEWED-123 cond. 2 and noticing the tracked count did not move. Fixed: governance files exempt, and a skip is now reported by name with byte counts as 'could not assess'.", "valid_from": "2026-08-17", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-17-the-instruments-audited-themselves-and-lost.md", "extracted_at": "2026-08-17"}
+{"subject": "the honest-degradation banner", "predicate": "prevention", "object": "CAUGHT ITS OWN AUTHOR'S REGRESSION IN-SESSION. Repairing 39 files' frontmatter moved 20 April-May wrap records' mtimes to today; sec_pause picked `newest wrap` by mtime and promoted an April session to Last wrap, losing both the pulling thread and the open question. Nothing in the repair's own verification would have caught it — the repair's checks were about frontmatter, and they all passed. The DEGRADED section fired instead ('no PULLING THREAD anchor in the last wrap'), which is Constitutional Constraint 4 built in 2026-07-28 for a different reason and paying out here. A mechanism that reports its own limits caught a defect no purpose-built control was pointed at.", "valid_from": "2026-08-17", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-17-the-instruments-audited-themselves-and-lost.md", "extracted_at": "2026-08-17"}
+{"subject": "reading the PLACED record instead of the relayed message", "predicate": "prevention", "object": "FIFTH CONSECUTIVE FIRING, AND IT CHANGED THE WORK BOTH TIMES ON 2026-08-17. The relayed REVIEWED-122 gave the ruling; the placed entry carried five conditions, two SEVERED legs authorized ahead of the mechanism, and a binding ORDER (answer key first, alone, hash recorded, before any implementation). The relayed REVIEWED-123 read as a ladder hold for the S2 batch; the placed entry ruled the freeze GENERAL — from any source, whatever its authorization — which is what made queueing today's two earned entries to the owed list correct rather than a violation.", "valid_from": "2026-08-17", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-17-the-instruments-audited-themselves-and-lost.md", "extracted_at": "2026-08-17"}
+{"subject": "declaring a confound against one's own favourable evidence", "predicate": "prevention", "object": "STOPPED A FLATTERING n=2 FROM STANDING UNQUALIFIED. The jurist offered a discriminator for real-vs-manufactured authorization boundaries, with the executor's 2026-08-17 refusal as its POSITIVE instance. The two cases differ in a variable the discriminator does not name: on 08-17 PENDING-141 was in MEMORY.md's Active Session block, bold, flagged 'do not execute', and read at that session's wake; on 08-01 no equivalent prompt existed. So the positive instance may record an INDEX that named the instrument rather than an executor that found it — the discriminator would then measure the memory layer while appearing to measure judgment. Filed by the party the evidence flatters, into the record, before anyone asked.", "valid_from": "2026-08-17", "valid_to": null, "confidence": 0.9, "source_file": "session-2026-08-17-the-instruments-audited-themselves-and-lost.md", "extracted_at": "2026-08-17"}
+{"subject": "claude-code", "predicate": "drift-pattern", "object": "REPORTED A CENSUS OF THE THINGS IT HAD LOOKED AT, NOT OF THE THINGS THAT QUALIFY. Told the steward 'PENDING-131 ADDENDA 2 and 4 await steward action'; four of the five blocks carry a live **Awaiting:** — the parent, ADDENDUM 1, ADDENDUM 2 and ADDENDUM 4. The two I quoted were the two I had opened while investigating something else. The jurist then ruled on that testimony, explicitly disclosing it had not verified ADDENDUM 1, and running that one check overturned the count. Seventh instance in one day of a subject adjacent to the claim, and the third of them mine.", "valid_from": "2026-08-17", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-17-the-instruments-audited-themselves-and-lost.md", "extracted_at": "2026-08-17"}
+{"subject": "a jurist naming the check it did NOT run", "predicate": "prevention", "object": "CORRECTED THE EXECUTOR'S COUNT WHERE NO CONTROL EXISTED. The jurist wrote 'I did not read Addendum 1 or Addendum 2 §1 — the executor named 2 and 4, and I've taken that as testimony rather than verifying', and separately that it had not re-run governance_state(). Both disclosures were actionable by the party that COULD check: ADDENDUM 1 carries a live Awaiting (count wrong by half), and governance_state() shows ZERO rows for 131 rather than a collapsed row. Neither gap had an instrument pointed at it; the disclosure was the instrument. Constraint 6's weak form doing real work because the position was stated rather than assumed.", "valid_from": "2026-08-17", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-17-the-instruments-audited-themselves-and-lost.md", "extracted_at": "2026-08-17"}
+{"subject": "an answer key's UNIT", "predicate": "drift-pattern-good-direction", "object": "WAS CORRECTED BEFORE THE KEY EXISTED, WHICH IS THE ONLY MOMENT IT COULD BE. REVIEWED-122 cond. 1 requires a hand-read per-ITEM key over 69 filtered items as the acceptance check for PENDING-142. If 'item' resolves to the id — which is how every existing instrument resolves it — the key reproduces the exact unit that caused Class E and grades green by construction. Caught only because the key had not yet been drafted; the fix is to key on ## BLOCKS and record per block whether a live Awaiting exists and at what tag. A pre-registration is only protective if its unit is right, and its unit is the last thing anyone checks.", "valid_from": "2026-08-17", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-17-the-instruments-audited-themselves-and-lost.md", "extracted_at": "2026-08-17"}

claude/memory/observer-problem-state.md

@@ -1,11 +1,8 @@
----
-permalink: claude-memory/observer-problem-state
----
-
 ---
 name: Observer Problem inquiry state
 description: External Auditor review received (2026-04-08), three challenges land (Absorption Trap, Aesthetic of Rigor, Proceed with Annotations), review deliberately NOT taxonomized. Next: dialogue trial.
 type: project
+permalink: claude-memory/observer-problem-state
 ---
 
 ## The Observer Problem — Current State (2026-04-10)

claude/memory/project-after-the-reply-publication-state.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/project-after-the-reply-publication-state
----
-
 ---
 name: After the Reply — shipped 2026-05-01
 description: Five-essay sequence "After the Reply: Inheritance Without Guardians" fully implemented end-to-end. All 5 essays published, apparatus marker, sequence-index page, /essays/ promotion all live. Closed.
 type: project
 originSessionId: 597aba4e-942b-4f20-8a89-3d801b14c971
+permalink: claude-memory/project-after-the-reply-publication-state
 ---
 # After the Reply — shipped
 

claude/memory/project-arc-404-page-design-pending.md

@@ -1,13 +1,17 @@
----
-permalink: claude-memory/project-arc-404-page-design-pending
----
-
 ---
 name: ARC 404 page — design + build pending
 description: Surfaced 2026-05-03 during _layout.scss SCSS audit — the .wrapper.not-found CSS rule was dead code (no template, no build path, no class application), but ARC genuinely needs a 404 page. Existing content/404.md is Jekyll-era leftover. Need: ARC-voice 404 design + Hakyll build path + template.
 type: project
 originSessionId: 8d9ac240-47df-4578-aec1-a9dd32965027
+permalink: claude-memory/project-arc-404-page-design-pending
+superseded_by: project-arc-open-work-register.md
+superseded_on: 2026-08-17
 ---
+> **SUPERSEDED 2026-08-17.** Register E3 → `[DONE—retire]` **[verified 2026-06-11]** — this file predates §VII.h; content/404.md and the built 404 conform exactly.
+>
+> Current record: **project-arc-open-work-register.md**. Kept for detail and provenance — do not read the
+> status below as live.
+
 # ARC 404 page — design + build pending
 
 **Surfaced:** 2026-05-03 during `_layout.scss` SCSS audit. The `.wrapper.not-found` CSS rule (~50 lines including dark-mode override) was dead code — no template, no `site.hs` build path, no class assignment anywhere. Removed in audit commit. **Side finding**: the gap is real. ARC has no 404 page.

claude/memory/project-arc-apparatus-refactor-todo-2026-05-06.md

@@ -7,7 +7,14 @@ description: Tracks the multi-session refactor flowing from the universal dateli
 type: project
 originSessionId: 3bf7ae75-1138-4745-9024-0c40b3755ad3
 permalink: claude-memory/project-arc-apparatus-refactor-todo-2026-05-06
+superseded_by: project-arc-open-work-register.md
+superseded_on: 2026-08-17
 ---
+> **SUPERSEDED 2026-08-17.** Register E4 → `[DONE—retire]` — Tiers 1/2 shipped; the Tier-3 residual lives on as register B1.
+>
+> Current record: **project-arc-open-work-register.md**. Kept for detail and provenance — do not read the
+> status below as live.
+
 
 # ARC apparatus refactor — todo list
 

claude/memory/project-arc-breadcrumb-spec-pending.md

@@ -9,7 +9,14 @@ description: Steward identified 2026-05-01 that the breadcrumb system should app
 type: project
 originSessionId: 597aba4e-942b-4f20-8a89-3d801b14c971
 permalink: claude-memory/project-arc-breadcrumb-spec-pending
+superseded_by: project-arc-open-work-register.md
+superseded_on: 2026-08-17
 ---
+> **SUPERSEDED 2026-08-17.** Register E1 → `[DONE—retire]` **[verified]** — breadcrumb componentized and governed 2026-06-03.
+>
+> Current record: **project-arc-open-work-register.md**. Kept for detail and provenance — do not read the
+> status below as live.
+
 
 # ARC universal breadcrumb system — pending
 

claude/memory/project-arc-mimesis-acquisition-debt.md

@@ -9,7 +9,14 @@ metadata:
   type: project
   originSessionId: 2026-05-20-conversion-session
 permalink: claude-memory/project-arc-mimesis-acquisition-debt
+superseded_by: project-arc-open-work-register.md
+superseded_on: 2026-08-17
 ---
+> **SUPERSEDED 2026-08-17.** Register E2 → `[DONE—archive]` — RESOLVED 2026-05-20, stated in this file's own body.
+>
+> Current record: **project-arc-open-work-register.md**. Kept for detail and provenance — do not read the
+> status below as live.
+
 
 # Auerbach *Mimesis* — acquisition debt — RESOLVED 2026-05-20
 

claude/memory/project-arc-open-work-register.md

@@ -6,6 +6,7 @@ metadata:
   type: project
   permalink: claude-memory/project-arc-open-work-register
   originSessionId: b85f1094-0658-47b4-a0ba-7a4323383aa9
+  modified: 2026-08-17T13:22:01.355Z
 ---
 
 # ARC open-work register
@@ -27,7 +28,7 @@ metadata:
 
 - **B1. Glimpse location + title cleanup.** `[OPEN — steward manual]` **[verified]** — steward does this by hand (2026-06-11). 193 live glimpses; **4 lack `location:` frontmatter**; titles need a cleanup pass. NB the glimpse *rendering* bugs (phone full-bleed, no-vessel) were fixed + deployed in Stage M — this is content/metadata, not code. Absorbs the residual of `project-arc-apparatus-refactor-todo` Tier 3 (EXIF/location for existing glimpses — now ~done).
 - **B2. Threshold-`---` promotion walk.** `[OPEN — steward content track]` — apply the 2026-06-07 differentiated-hr doctrine across existing pieces: a bare `---` at a foreword→main-text *threshold* becomes `.ornament` (dots); `---` *within the body* stays silence. Doctrine + CSS settled (§IV amended, zero CSS change); the per-piece content walk remains.
-- **B3. Ornament content migration (Option A) — the content half of A2.** `[OPEN — gated on A2; scope VERIFIED 2026-06-11]` — steward ruled Option A (2026-05-03): once the cul-de-lampe asset exists (**A2**), migrate content off the retired-ornament classes onto the canonical Close/Pause, then retire the old SCSS. **Verified scope (sizable):** ~**95 content files** carry hand-authored `<div class="ornament …"></div>` — `completion` ×51 (= the Close / end-of-piece, the cul-de-lampe's job), `section` ×50, `thought` ×14, `chamber` ×12, `musical` ×7, `hermetic` ×5, `mathematical` ×2, … Several variants (`thought`, `mathematical`) aren't even in the current CSS → they already collapse to bare `.ornament`. All retired per §IV; all await the designed asset. Not negligible, and not runnable until A2. Files: `project-arc-ornament-spec-vs-content-mismatch-pending`, `project-arc-pause-close-ornament-and-hr-audit-pending`.
+- **B3. Ornament content migration (Option A) — the content half of A2.** `[OPEN — UNGATED 2026-06-17 when A2 landed; scope VERIFIED 2026-06-11]` — ⚠ *label corrected 2026-08-17: this read `gated on A2` for two months after A2 completed. A2's own entry had recorded "the content half (B3) is now unblocked + started" on 06-17 — so the fact was known and written, just never written **here**, which is where a reader checking B3's status looks. Kept as a marker of that failure mode rather than silently amended.* — steward ruled Option A (2026-05-03): once the cul-de-lampe asset exists (**A2**), migrate content off the retired-ornament classes onto the canonical Close/Pause, then retire the old SCSS. **Verified scope (sizable):** ~**95 content files** carry hand-authored `<div class="ornament …"></div>` — `completion` ×51 (= the Close / end-of-piece, the cul-de-lampe's job), `section` ×50, `thought` ×14, `chamber` ×12, `musical` ×7, `hermetic` ×5, `mathematical` ×2, … Several variants (`thought`, `mathematical`) aren't even in the current CSS → they already collapse to bare `.ornament`. All retired per §IV; all await the designed asset. Not negligible, and not runnable until A2. Files: `project-arc-ornament-spec-vs-content-mismatch-pending`, `project-arc-pause-close-ornament-and-hr-audit-pending`.
 - **B4. Major content audit / archive of non-current files.** `[OPEN — was deferred]` — per ARC `CLAUDE.md` Known state: deferred until "the current version of the site is established; do not rearrange the content tree until that session." Stage G sealed arguably satisfies that condition now — candidate to schedule.
 - **B5. Rethink the versioning links.** `[OPEN — design reconsideration; steward-raised 2026-06-17, NOT for now]` — the steward feels something "doesn't sit right" about the version-stamp links and couldn't yet name it. Current behaviour (verified in built HTML): the piece-end stamp reads *"Begun [place] **[origin-date→/v/]** · Revised [place] [revised-date, plain]"* — the **origin date is the only link**, leading to the prior version; the `/v/` page announces "You are reading a prior version… Read current →." Executor's candidate diagnoses (offered, not settled): **(1)** the cul-de-lampe (a *completion* seal, *finis coronat opus*) and the version link pull opposite ways — the close says *done*, the link a few lines below pulls *backward* into the superseded version; adding the close may have sharpened a latent tension. **(2)** "Begun [date]" frames the link as inception/seed, but the destination is a *complete prior essay*, not a beginning — label/destination mismatch. **(3)** for pieces revised by *subtraction* (Mushi-Ken's appendix, Vespers' loudness), the linked prior is the version the author *improved away from* — disclosing *that* a revision happened is integrity, but making the discarded version the foot-of-page reading-*destination* may overreach: provenance offered as invitation. Hunch: it's #1+#3 — ADR-005 designed versioning as a *record*, but rendered as a link it behaves like a parallel reading-path, and that sits oddly under a completion mark. Revisit when the steward can name it. (Grounds: ADR-005, essay-versioning-specification.md §3–4; the version-stamp builder in `site.hs`.)
 

claude/memory/project-arc-pause-close-ornament-and-hr-audit-pending.md

@@ -9,7 +9,14 @@ description: Two interlocking pieces of work that should be undertaken together
 type: project
 originSessionId: 8d9ac240-47df-4578-aec1-a9dd32965027
 permalink: claude-memory/project-arc-pause-close-ornament-and-hr-audit-pending
+superseded_by: project-arc-open-work-register.md
+superseded_on: 2026-08-17
 ---
+> **SUPERSEDED 2026-08-17.** Register A2 → `[DONE 2026-06-17]` — the cul-de-lampe is designed, first-instanced, rolled out to 7 essays, spec resolved. The CONTENT half continues as register B3, which is live work.
+>
+> Current record: **project-arc-open-work-register.md**. Kept for detail and provenance — do not read the
+> status below as live.
+
 
 # ARC §IV Pause/Close ornament + `<hr>` content audit — pending
 

claude/memory/project-arc-pdf-print-postures-session-plan.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/project-arc-pdf-print-postures-session-plan
----
-
 ---
 name: ARC PDF + Print posture rendering session plan — XeLaTeX templates + AldineXXI sample images
 description: Dedicated session to build both Postures (PDF + Print) as LaTeX templates, render the Readings typology spec as PDF, and produce sample-image pairs for the AldineXXI page rewrite's Postures section. Two-birds: deliver the deferred Print/PDF posture spec sections AND the AldineXXI assets in one focused session.
 type: project
 originSessionId: a5411fd1-4a96-43e7-aa1a-1a50d8951a8f
+permalink: claude-memory/project-arc-pdf-print-postures-session-plan
 ---
 ## Context
 

claude/memory/project-arc-spec-master-typographer-audit-pending.md

@@ -9,7 +9,14 @@ description: Aspiration logged 2026-05-03 — at an appropriate future point, re
 type: project
 originSessionId: 8d9ac240-47df-4578-aec1-a9dd32965027
 permalink: claude-memory/project-arc-spec-master-typographer-audit-pending
+superseded_by: project-arc-open-work-register.md
+superseded_on: 2026-08-17
 ---
+> **SUPERSEDED 2026-08-17.** Register E5 → `[DONE—retire — superseded]` **[verified 2026-06-11]** — the masters pass was performed (_audits/deep-typographic-audit-2026-06-09.md). Reopen only for a NAMED uncovered dimension.
+>
+> Current record: **project-arc-open-work-register.md**. Kept for detail and provenance — do not read the
+> status below as live.
+
 
 # ARC spec — master-typographer compliance audit (pending)
 

claude/memory/project-arc-web-typography-spec-coverage.md

@@ -9,7 +9,14 @@ description: Inventory of web-only and web-medium typography elements in ARC tha
 type: project
 originSessionId: 8d9ac240-47df-4578-aec1-a9dd32965027
 permalink: claude-memory/project-arc-web-typography-spec-coverage
+superseded_by: project-arc-open-work-register.md
+superseded_on: 2026-08-17
 ---
+> **SUPERSEDED 2026-08-17.** Register E6 → `[DONE—retire]` **[verified 2026-06-11]** — Tiers 1–3 done; only the <abbr>/<mark> corner remains and no content meaningfully uses them.
+>
+> Current record: **project-arc-open-work-register.md**. Kept for detail and provenance — do not read the
+> status below as live.
+
 
 # ARC web typography spec coverage — what still needs care
 

claude/memory/project-bge-m3-full-remine-plan-2026-05-11.md

@@ -5,7 +5,14 @@ description: The ONE job for the cleared context. Full chamber-library re-mine o
 type: project
 originSessionId: a156edbb-0c3d-4285-b3ed-f5a45b8dda66
 permalink: claude-memory/project-bge-m3-full-remine-plan-2026-05-11
+superseded_by: project-mempalace-winddown.md
+superseded_on: 2026-08-17
 ---
+> **SUPERSEDED 2026-08-17.** An execution plan for a palace that no longer exists. The DISCIPLINE it was written under survives: see feedback-bulk-indexing-runs-incrementally-with-readback.md.
+>
+> Current record: **project-mempalace-winddown.md**. Kept for detail and provenance — do not read the
+> status below as live.
+
 
 # bge-m3 full re-mine plan
 

claude/memory/project-bmf-mempalace-connector-parked.md

@@ -6,7 +6,14 @@ description: Architectural framework for a BMF connector that queries MemPalace'
 type: project
 originSessionId: 597aba4e-942b-4f20-8a89-3d801b14c971
 permalink: claude-memory/project-bmf-mempalace-connector-parked
+superseded_by: project-mempalace-winddown.md
+superseded_on: 2026-08-17
 ---
+> **SUPERSEDED 2026-08-17.** Parked on two conditions that have both lapsed: MemPalace was retired 2026-07-07, and BMF L1 is blocked on PENDING-94 and staying down. Resume would need a fresh framing, not this one.
+>
+> Current record: **project-mempalace-winddown.md**. Kept for detail and provenance — do not read the
+> status below as live.
+
 
 # BMF–MemPalace Connector — Project Framework
 

claude/memory/project-chamber-alexandrian-foundation-standard.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/project-chamber-alexandrian-foundation-standard
----
-
 ---
 name: Chamber-library quality is foundation-grade — Alexandrian standard, not throughput
 description: The chamber's source-file quality is the foundation ARC and CapableMind rest on. Each voice that enters must be built carefully: clean, structurally intact, fitting. Triage and sequencing serve order-of-operations only — the quality bar is the same for every text, applied per file.
 type: project
 originSessionId: a5411fd1-4a96-43e7-aa1a-1a50d8951a8f
+permalink: claude-memory/project-chamber-alexandrian-foundation-standard
 ---
 The architecture of ARC is **Alexandrian: beautiful, strong, generative, alive.** Building upon potential directions requires the foundation be clean and well-made. The chamber is that foundation.
 

claude/memory/project-chamber-cruft-restoration.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/project-chamber-cruft-restoration
----
-
 ---
 name: Chamber-library cruft restoration project — 186 files need work, 62 are load-bearing voices
 description: 47% of the chamber (186/399 .md files) carries cruft from EPUB/HTML conversion residue. 124 are CLEANUP (strip_cruft handles), 62 are severe RECONVERT (need source EPUB + repair pipeline). Load-bearing voices in the severe bucket: Bachelard ×3, Arendt ×3, Adorno, Heidegger, Plato, Marcus Aurelius, Alexander, Lévi-Strauss. Precondition for "discourse with the library" — the steward's actual aim.
 type: project
 originSessionId: a5411fd1-4a96-43e7-aa1a-1a50d8951a8f
+permalink: claude-memory/project-chamber-cruft-restoration
 ---
 **Why this exists** — the steward's framing 2026-05-13 evening, after seeing the audit:
 

claude/memory/project-chamber-library-cluster-scaffolds-2026-04-26.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/project-chamber-library-cluster-scaffolds-2026-04-26
----
-
 ---
 name: Chamber-library cluster scaffolds for the six remaining lex-method clusters (registrar-form, awaiting recognition)
 description: Steward-authorized 2026-04-26 scaffolding pass — for each of the six remaining clusters in the immediate sheaf (music-and-measure, mark-not-made, the apostrophic, public/private genre, craft-and-tool-fitness, practice-across-life), proposes voices already present in chamber-library that touch the cluster's register. Registrar-form only — voices are present-and-touching, not steward-recognized cluster pillars. Steward framing: "Wallace Stevens's jar on the hill. Hic." The scaffold is the placing-act; recognition happens in dialogue.
 type: project
 originSessionId: 87dfe384-b862-4deb-9676-24e43046528f
+permalink: claude-memory/project-chamber-library-cluster-scaffolds-2026-04-26
 ---
 
 > **INTEGRATED 2026-04-26 → `project-arc-rework.md` (Integration A).** Steward authorization: *"Integrate. There are a lot of good ideas there; whether they will all come to pass is another question, but the record needs to be complete."* Content folded into the canonical ARC workstream tracker. This file retained as audit trail. **For current home of cluster scaffolds, see `project-arc-rework.md` § "Integration A: Cluster scaffolds for the six remaining lex-method clusters."**

claude/memory/project-chamber-rewrite-frame-2026-04-26.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/project-chamber-rewrite-frame-2026-04-26
----
-
 ---
 name: Chamber page rewrite frame 2026-04-26 (v1 archived → v2 source-aware; awaiting direction)
 description: Frame for rewriting ARC's /chamber/ pages to reflect Chamber's v1→v2 evolution. v1 was an elaborate simulation with fictional canon and deliberations (now archived). v2 is source-aware: constrained retrieval, verifiable citation, contamination-mitigation governance, "rigorous reading and thinking" as the working register. The rewrite must announce the shift, not gloss it. Awaiting steward direction.
 type: project
 originSessionId: 87dfe384-b862-4deb-9676-24e43046528f
+permalink: claude-memory/project-chamber-rewrite-frame-2026-04-26
 ---
 
 > **INTEGRATED 2026-04-26 → `project-arc-rework.md` (Integration C).** Steward authorization: *"Integrate. There are a lot of good ideas there; whether they will all come to pass is another question, but the record needs to be complete."* Content folded into the canonical ARC workstream tracker. **Note: the 2026-04-23 entry in project-arc-rework.md already settled Chamber redistribution** (⟐ → §2 apparatus; v1 deliberations as "fruits of those labors" archive section; fictional canon → Heteronym ⁂; compass row removed; rewrite post-L2-unpark). The detail in this file is the executable detail for when the rewrite session arrives. This file retained as audit trail. **For current home of Chamber rewrite drop/keep/add + open questions, see `project-arc-rework.md` § "Integration C: Chamber page rewrite — drop/keep/add detail + open questions."**

claude/memory/project-competence-vulnerability-paradox.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/project-competence-vulnerability-paradox
----
-
 ---
 name: Competence-vulnerability paradox — contamination shape for read-path observability
 description: The contamination risk for read-path observability invariants is NOT the monotonic-toward-interlocutor-satisfaction shape Cluster A invariants face. It is the inverse: increasing capability masks decreasing observability of degraded paths. Surfaced by jurist 2026-05-14 in PENDING-20 / REVIEWED-22 review.
 type: project
 originSessionId: 5eb9e398-c72b-4b44-b274-0a6165a3f562
+permalink: claude-memory/project-competence-vulnerability-paradox
 ---
 **Date surfaced:** 2026-05-14
 **Origin:** Jurist's review of PENDING-20 (cross-cutting read-path-honest-degradation [PROPOSAL]); recorded under REVIEWED-22 Q3 (l1_contamination_profile)

claude/memory/project-gloss-vs-commentary-distinction.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/project-gloss-vs-commentary-distinction
----
-
 ---
 name: Gloss vs Readings as distinct ARC content types — distinction discovered 2026-05-13, name locked 2026-05-14
 description: The Brown piece "The Obligating Word" (committed `82c2ba1` as class:gloss) is structurally Readings, not Gloss. Diagnostic: gloss illuminates a passage (passage = subject); a Reading composes its account of a work (work = subject, passages = evidence). Steward chose name "Readings" (plural) over "Commentary" — register family matches Glimpse/Fragment/Observation; the plural admits "these are my readings, not the readings." Genette's *Seuils* ratifies the structural frontier (paratexte vs métatexte; "forme latérale de la critique"). Remaining work: spec amendment + Brown post reclassification.
 type: project
 originSessionId: a5411fd1-4a96-43e7-aa1a-1a50d8951a8f
+permalink: claude-memory/project-gloss-vs-commentary-distinction
 ---
 ## Context (how we got here)
 

claude/memory/project-mempalace-bge-m3-mine-search-broken-2026-05-03.md

@@ -1,13 +1,17 @@
----
-permalink: claude-memory/project-mempalace-bge-m3-mine-search-broken-2026-05-03
----
-
 ---
 name: MemPalace bge-m3 mine — drawers stored, search broken (Internal error: Error finding id)
 description: 2026-05-03 diagnostic state. Three days of CPU/MPS time on the bge-m3 chamber-library mine produced 933,576 drawers in storage but functional semantic recall is broken. Real loss for the steward.
 type: project
 originSessionId: 8d9ac240-47df-4578-aec1-a9dd32965027
+permalink: claude-memory/project-mempalace-bge-m3-mine-search-broken-2026-05-03
+superseded_by: project-mempalace-winddown.md
+superseded_on: 2026-08-17
 ---
+> **SUPERSEDED 2026-08-17.** Diagnostic state of a palace that no longer exists.
+>
+> Current record: **project-mempalace-winddown.md**. Kept for detail and provenance — do not read the
+> status below as live.
+
 ## Diagnostic state (2026-05-03 evening)
 
 **The good (storage)**

claude/memory/project-mempalace-chunking-bug-2026-05-16.md

@@ -11,7 +11,14 @@ metadata:
   type: project
   originSessionId: 8952fe77-1cf0-401d-9d88-01f9f0b13bcc
 permalink: claude-memory/project-mempalace-chunking-bug-2026-05-16
+superseded_by: project-mempalace-winddown.md
+superseded_on: 2026-08-17
 ---
+> **SUPERSEDED 2026-08-17.** Filed upstream as MemPalace/mempalace#1534 and left to upstream by steward direction. With the instrument retired this is no longer ours to track.
+>
+> Current record: **project-mempalace-winddown.md**. Kept for detail and provenance — do not read the
+> status below as live.
+
 
 # MemPalace `_chunk_by_paragraph` oversized-chunk bug
 

claude/memory/project-mempalace-library-incremental-remine-strategy.md

@@ -8,7 +8,14 @@ description: After 3 days lost to bge-m3+MPS chamber-library mine that produced
 type: project
 originSessionId: 45a40b1e-09cd-42bb-a41a-7298f78a8cf0
 permalink: claude-memory/project-mempalace-library-incremental-remine-strategy
+superseded_by: project-mempalace-winddown.md
+superseded_on: 2026-08-17
 ---
+> **SUPERSEDED 2026-08-17.** ⚠ The steward's rule this file carried is INSTRUMENT-INDEPENDENT and was harvested before this stamp: feedback-bulk-indexing-runs-incrementally-with-readback.md. It applies now to studium-engine corpus work. Superseded for MemPalace operations only.
+>
+> Current record: **project-mempalace-winddown.md**. Kept for detail and provenance — do not read the
+> status below as live.
+
 
 ## Context
 

claude/memory/project-mempalace-mps-transition-pending.md

@@ -1,13 +1,17 @@
----
-permalink: claude-memory/project-mempalace-mps-transition-pending
----
-
 ---
 name: MemPalace bge-m3 + MPS transition — paused mid-flight; resume in fresh session
 description: Chamber-library mine with bge-m3 was running on CPU and projected to take 4-5 days. Plan: enable Apple Silicon Metal (MPS) acceleration via chroma.py patch addition (~5-10x speedup, finish in hours not days). Processes already killed and palace wiped clean to skeleton; ready to resume. Independent BMF audit thread also surfaced.
 type: project
 originSessionId: 17dee884-74bf-43e7-9b6a-44bc82b97303
+permalink: claude-memory/project-mempalace-mps-transition-pending
+superseded_by: project-mempalace-winddown.md
+superseded_on: 2026-08-17
 ---
+> **SUPERSEDED 2026-08-17.** A paused bge-m3/MPS mine on a palace that was wiped and then retired. The backup paths named below may still exist on disk and are the only part worth acting on.
+>
+> Current record: **project-mempalace-winddown.md**. Kept for detail and provenance — do not read the
+> status below as live.
+
 # MemPalace bge-m3 + MPS transition — paused
 
 Started 2026-04-30 evening, paused 2026-05-01 morning after diagnosing the speed problem. Steward chose fresh session for the resume rather than continuing in a long context.

claude/memory/project-mempalace-operational-stance-2026-05-16.md

@@ -7,7 +7,14 @@ metadata:
   type: project
   originSessionId: 8b47c0eb-d396-43d5-98eb-7623e6f04357
 permalink: claude-memory/project-mempalace-operational-stance-2026-05-16
+superseded_by: project-mempalace-winddown.md + studium-engine docs/seed-brief.md
+superseded_on: 2026-08-17
 ---
+> **SUPERSEDED 2026-08-17.** The MemPalace half is retired. The live half — the two-layer split between session continuity and voice-attributed corpus consultation — is carried more fully in the studium-engine seed-brief §3.2–3.3, which states it as one architecture asked to do two jobs.
+>
+> Current record: **project-mempalace-winddown.md + studium-engine docs/seed-brief.md**. Kept for detail and provenance — do not read the
+> status below as live.
+
 
 # MemPalace operational stance (post-issue-#1526)
 

claude/memory/project-mempalace-role-as-instrumentation.md

@@ -8,7 +8,14 @@ description: MemPalace is not a deliverable, not a long-term substrate, not part
 type: project
 originSessionId: 597aba4e-942b-4f20-8a89-3d801b14c971
 permalink: claude-memory/project-mempalace-role-as-instrumentation
+superseded_by: project-mempalace-winddown.md + mempalace-is-unaffiliated-stopgap.md
+superseded_on: 2026-08-17
 ---
+> **SUPERSEDED 2026-08-17.** The territory rule (MemPalace is a third-party project, never conflated with BMF/CapableMind) is live and now carried by mempalace-is-unaffiliated-stopgap.md. The operational half — bge-m3 transition phases — retired with the instrument.
+>
+> Current record: **project-mempalace-winddown.md + mempalace-is-unaffiliated-stopgap.md**. Kept for detail and provenance — do not read the
+> status below as live.
+
 
 # MemPalace's role in the current period
 

claude/memory/project-mempalace-upgrade-3-4-0-plan.md

@@ -5,7 +5,14 @@ metadata:
   node_type: memory
   type: project
   originSessionId: 5a8200e7-d734-4dc1-b69e-93d77076cab2
+superseded_by: project-mempalace-winddown.md
+superseded_on: 2026-08-17
 ---
+> **SUPERSEDED 2026-08-17.** A scheduled 3.3.6 → 3.4.0 upgrade of an instrument retired before the slot came.
+>
+> Current record: **project-mempalace-winddown.md**. Kept for detail and provenance — do not read the
+> status below as live.
+
 
 # MemPalace upgrade 3.3.6 → 3.4.0 — scheduled plan (ratified 2026-06-07)
 

claude/memory/project-multilingual-typography-refinement-2026-05-14.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/project-multilingual-typography-refinement-2026-05-14
----
-
 ---
 name: Multilingual typography spec refinement — path from v0.1 to LOCKED
 description: Tracks the work needed to take docs/AldineXXI-Codex/multilingual-typography-specification.md from v0.1 (French only, operational-quality) to v1.0 (LOCKED). Captured 2026-05-14 evening after the jurist's architectural correction landed the spec in its current shape. Steward direction: save the assessment, work it after §2 Spanish is sketched.
 type: project
 originSessionId: 6cef24d0-242b-474e-b8d4-fd568edf5dc2
+permalink: claude-memory/project-multilingual-typography-refinement-2026-05-14
 ---
 ## State as of 2026-05-14 (evening)
 

claude/memory/project-obsidian-vault-practice.md

@@ -0,0 +1,105 @@
+---
+name: project-obsidian-vault-practice
+description: "Canonical tracker for the Obsidian vault workstream — turning root-and-branch from an archive into a practice, beginning with a ratified Frontmatter Specification v1.0.0. Holds the operational facts (the vault is NOT a git repo; it mirrors to ~/_Dev/david-root-and-branch-vault-git), the applied-pass record, and the open tail. Read before any vault work."
+metadata:
+  node_type: memory
+  type: project
+  modified: 2026-08-20T09:08:17Z
+---
+
+# Obsidian vault — from archive to practice
+
+**Steward's goal, stated 2026-08-19:** *"optimizing my Obsidian usage and setting up a regular
+workflow to have the important parts of our work captured there… My instinct is that I could
+make better use of it. I want to create an Obsidian 'spec' like we have done for all of our
+serious projects."*
+
+**The tool boundary, from the steward, so it is not re-elicited:**
+
+| tool | role |
+|---|---|
+| **Drafts.app** | scratchpad; ephemeral text, or text destined elsewhere. Kept essentially empty at the end of every week. |
+| **Notes.app** (Mac/iOS) | confidential material, as locked notes. |
+| **Obsidian** (`root-and-branch`) | notes that must not be lost. *"So far, a sort of archive."* |
+
+**Scope note:** the vault is *also* the Compass — the steward's personal operating system.
+`~/CLAUDE.md` says: reference it, never write to it. **That standing rule was suspended for this
+workstream by explicit authorization** (`"I authorize the Compass ones too"`, 2026-08-19), for
+the named mechanical passes only. It is not a general licence.
+
+---
+
+## Operational facts — do not re-derive
+
+- **The vault folder is NOT a git repository.** `~/Library/Mobile Documents/iCloud~md~obsidian/Documents/David, root-and-branch`
+  has no `.git`.
+- **It mirrors to `~/_Dev/david-root-and-branch-vault-git`** (remote:
+  `git.skemantix.com/David/david-root-and-branch-vault-git`). An automated job commits
+  `Mirror sync <timestamp>` on its own schedule — so steward hand-edits land in git without
+  anyone asking.
+- **Working reports and machine-readable changelogs live in `~/dotfiles/obsidian/`**:
+  `vault-frontmatter-inventory-2026-08-19.md`, `vault-frontmatter-pass1-followups-2026-08-19.md`,
+  `vault-governance-block-round2-2026-08-19.md`, `vault-round3-archive-and-relations-2026-08-19.md`,
+  plus `fm_inventory.json`, `pass2-changelog.json`, `pass2-flags.json`.
+- **The spec is in the vault, not in dotfiles:** `00. Compass/Frontmatter Specification.md`.
+- ⚠ **`verify-before-compose.sh` fires on `Write|Edit`, and this work runs through Bash.** A vault
+  hook wired the same way would not fire on how the work actually runs. Noted 2026-08-19, unfixed.
+
+---
+
+## Chronological log
+
+### 2026-08-19 — census, spec, two passes (session died unwrapped; see [[session-2026-08-19-the-vault-got-a-spec-the-links-were-already-broken]])
+
+- **Four read-only census rounds before any edit.** 2,519 notes parsed, no sampling. 400 distinct
+  keys over 5,867 instances; **68% of notes have no frontmatter at all.** 66 keys consumed, 29
+  written-by-template-and-read-by-nothing, 305 orphaned.
+- **Round 2/3 findings that changed the design:** `owner` was one job in three spellings (cut);
+  `canonical` was **one name doing two jobs** (self-descriptive vs pointer-elsewhere); the
+  hypothesis that pointer-form marks archival **tested negative** — 65 of 67 pointers sit outside
+  `99. Archive`. What actually distinguishes Archive is **decay in practice, declaration in name
+  only**: `status: archived` on 2.3% of it, 90% receiving no wikilink from any live note, and **no
+  archival policy note anywhere in the vault.**
+- **Frontmatter Specification v1.0.0 ratified** and placed in `00. Compass/`. First principle:
+  *storage and lifecycle are orthogonal* — the folder says nothing; only `status:` declares.
+- **Pass 1 and pass 2 applied and pushed.** `949ff14` `31d8e1f` `3d47bd2` `00e741d` `4c364e9`
+  `fab8fb0` (**511 edits / 268 files**) `aee615d`.
+- **End state:** `owner` 0 · `change_log` 0 · `domain` 0 · `revisions` 90 · `canonical` 159 ·
+  `see_canonical` 3 · `confidence` 9 · `links` 8 kept-and-flagged. **YAML parse errors 16,
+  unchanged.**
+- **Two executor tooling defects caught before applying** (§6 handler covered block-style lists
+  only — would have done 29 notes of 90 and reported success; §7 logged a retirement it did not
+  perform). Both found by **re-censusing an applied copy, not by reading the changelog.**
+- **The jurist corrected its own "88 recoverable" reading**: those were self-descriptive values
+  resolving to themselves by construction. **Only 3 of 66 pointers were genuinely recoverable.**
+
+### 2026-08-20 — the steward opened Obsidian, and the links were already broken
+
+Checked against the mirror's history, not inferred. **Coffee log** (`brew_temp: [[94–96°C]]`) and
+**homeopathy** (`[[Ignatia amara — The Medicine of the Sigh]]` naming a *title* where the file is
+`Ignatia amara.md`) are both **pre-existing**; pass 2 never touched the homeopathy note and
+touched only `linked_note`→`linked_daily_note` in the coffee log.
+
+**But the passes are not innocent.** §7 flattened nested `links.parents` — inert YAML Obsidian did
+not render — into top-level `parents/children/peers`, which **made 194 already-unresolvable targets
+render as clickable-and-broken in the properties UI.** The breakage was surfaced, not created. The
+pass report did not predict this, and it should have.
+
+---
+
+## Current state — OPEN
+
+1. ⚠ **A defect of ours: `see_canonical: "[[Index]]"`** in `09. Atlas of Roots/00. Atlas of Roots — Index.md`,
+   converted from `canonical: 09. Atlas of Roots/index.md`, **a file that does not exist**. The only
+   `Index.md` notes are `08. Notes/Tools & Workflow/Index.md` and a Catalan `00. Index/index.md`.
+   **It resolves to the wrong note or none — 1 of the 3 pointers §3 wrote.** Same basename flaw the
+   jurist corrected as a *number* that afternoon, landed in an applied edit as a *mechanism*.
+2. **194 unresolvable `related` targets**, left bare and flagged by §6.
+3. **63 residual `canonical` pointers** — each a note that named an authority for itself and lost
+   track of where it lives. Steward's eyes wanted here most: this is the population `canonical` was
+   actually describing, invisible while 157 path-strings sat behind one field name.
+4. **16 YAML parse errors**, unchanged across both passes — never in scope, never addressed.
+5. **The actual goal has not been started.** Everything so far is hygiene on an archive. *"A regular
+   workflow to have the important parts of our work captured there"* — the capture practice, the
+   thing that would make the vault a practice rather than a tidier archive — **has not been
+   designed.** Do not let the frontmatter tail stand in for it.

claude/memory/project-strunk-and-white-vocabulary-pass-queued.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/project-strunk-and-white-vocabulary-pass-queued
----
-
 ---
 name: Strunk & White — vocabulary pass queued for ARC
 description: Steward has queued a reading of *The Elements of Style* (Strunk & White) for ARC style-guide purposes. Scope defined 2026-04-23 evening: vocabulary-acquisition pass, few hours, against Norris rather than as her source. Posture: give names to what he already does by feel, not convert feel into rule.
 type: project
 originSessionId: 0e858bcf-ef4e-46c6-9eca-abd19836786a
+permalink: claude-memory/project-strunk-and-white-vocabulary-pass-queued
 ---
 # Strunk & White — vocabulary pass queued
 

claude/memory/project-studium-engine.md

@@ -121,6 +121,56 @@ both still **needing dates, not "later."**
 
 ## Chronological log
 
+### 2026-08-13 — the fence was never blocked; the fr cell all but closed
+
+**REVIEWED-118 EXECUTED** (`e51e30d`) — authorized 2026-08-10, unexecuted for three days, found by
+substrate-checking the `**If AUTHORIZED:**` clause rather than reading it as status. L926's
+instances 6/12/16 retracted. Two decisions not implied by the ruling: `mauss-phase2-spans.yaml` is
+**generated**, so the record went into `scripts/bind_mauss_spans.py` too (a retraction in the
+emitted YAML alone is erased by the next run, with no diff); and that file measures **binding**, so
+the binding facts stayed and a cross-reference carries the retraction.
+
+**THE (b1) IDENTIFICATION PASS RAN** (`docs/fr-reported-speech-identification-pass-2026-08-13.md`),
+authorized at REVIEWED-116 pt 5 on 08-10 and never executed. **Reported speech in exactly 1 of 9 fr
+grounded spans** (L1551). The other eight are Mauss's own terminology, three self-marked
+(*"comme nous proposons de les appeler"*). ⚠ **Corrects REVIEWED-116 pt 6 rather than confirming
+it**: Mauss's 73 inline ≥120-char spans are a different population from the grounded set, of which
+only L926 and L1551 were ever members — **within the grounded set P7's F4 tagging was correct and
+complete.** ⇒ **PENDING-134's blast radius on inherited fr gold is ONE span.**
+
+**PENDING-135 (c) → REVIEWED-119 · PENDING-136 (c) → REVIEWED-120** (`de1c34b`, both placed by the
+steward). Instance 8 reclassified negative-candidate, marked in place; ⚠ **sub-type name OPEN** —
+§7.4(i) addresses the nested voice served *as* the host's, this **fuses** both. Count fields now
+carry their populations; bare `distinct_spans` retired. ⚠ **REVIEWED-119 pt 4 corrects PENDING-135's
+own blocking claim**: option (d) is constrained by `studium/v2-gold@1` §14.2 (`lines: [a,b]`) —
+**engine-side, D-1** — not by the chamber-locked `studium/meta@1`. Materially cheaper route.
+⚠ **I committed 136's own error while executing it**: `bound_instances_grounded` 12 by subtraction,
+ignoring instance 17. Correct **10**; all counts now verified by enumeration.
+
+**`voice_stamp` BUILT** (`d411034`; `engine/voice_stamp.py`, suite 22; fleet **9 suites / 285**).
+⚠ **AND MOVE 1 WAS NEVER BLOCKED.** PENDING-131 (c) is real for the **sidecar** and never bound the
+engine — `chunker.py` has recorded `char_range` document offsets since Cluster A. **The
+line-granularity ceiling was an artifact of where the fence was being WRITTEN, not of what the
+engine can SEE.** Paragraph-scoped pairing (not line-scoped) is what makes it work on hard-wrapped
+sources. **Reporter, deliberately NOT wired to abstention** — verdict semantics are unruled.
+
+**fr cell as of this wrap:** 11 listed spans / **8 grounded** (1 A + 7 B) / 2 reclassified / 1
+retracted / **10** grounded bound instances. **`ratio_A_to_B` VOID** — re-derived ONCE after
+PENDING-134 lands and all dispositions are recorded (REVIEWED-116 pt 5).
+
+⚠ **INSTRUMENT LESSON, and it is the day's most transferable:** the nested-voice census carried
+**five defects** and **four escaped its own controls** — every control was drawn from Mauss, so they
+exercised one quotation convention and one line structure, and could not see blindness to ASCII
+quotes (3 sources) or to hard-wrapped text (2 sources), both of which produced **clean zeros**.
+Only the fifth — a regression in an already-covered case — was caught by the controls. **A control
+set drawn from one source establishes nothing about a corpus.**
+
+⚠ **PENDING-134's remaining blocker is a STEWARD CLIENT RESTART, not a build.** `governance-mcp.py`
+builds `FILES` at import, so the four V0-lane keys registered at `4c3758e` are not yet served.
+Executor half discharged: selftest 54/54, and two key descriptions that had gone stale the same day
+were refreshed (`92d5ad2`) so the jurist's first read is not of a stale index.
+
+
 *Append substantive moves here at `/wrap-up` — not only to "Current state" above. A tracker with two
 update surfaces drifts between them (skill-harvest #183).*
 

claude/memory/reference-verification-ladder.md

@@ -23,7 +23,7 @@ Proven gates, each earned from a real catch. Reach for the one the claim's shape
 - **Delayer-diff** (2026-06-08) — for an `@layer`/structural-wrap refactor where the compiled output gains uniform wrappers: strip the `@layer X{`/closing-`}` wrappers from the compiled CSS (brace-aware script), diff vs the true baseline; byte-identical proves nothing *moved, dropped, or changed* — only got wrapped. Proven 3× in W3R Stage 2a. **CAUTION — byte-identical ≠ rendered-identical under `@layer`:** `@layer` overrides specificity, so a structural-wrap byte-proof is *necessary but not sufficient*; render-review is the gate when the cascade *basis* changes (a 5-layer wrap was byte-true yet produced 3 render inversions the diff could not see — the steward's eye caught them). Rendered-identity is then argued *by construction* (only already-winning rules promoted) AND render-reviewed — not inferred from the byte-diff.
 - **Hold or exclude volatile build-stamps** — a build-date/commit stamp (colophon `_build_info`) differs between baseline and post builds and falsely flags a byte-diff. Hold it constant or exclude it, and say which (2026-06-10, Stage-G close).
 - **Two-hat commit separation** — name the hat each commit wears: a *refactor* commit's compiled output is byte-identical (or carries a pre-stated classified delta); a *feature* commit is where rendered values change. Makes the gate above applicable per-commit instead of per-session (2026-06-08, from Fowler).
-- **Lossless-relocation gate** — restructuring an index or moving prose between files: line-range **slices, never retyping**, + md5-conservation per moved slice + a link-resolution canary over every `](file.md)` and `[[wikilink]]`. Proven on the MEMORY.md two-file split (2026-07-06) and again on the skill-harvest split (2026-08-01, archive byte-identical over 166,027 bytes).
+- **Lossless-relocation gate** — restructuring an index or moving prose between files: line-range **slices, never retyping**, + md5-conservation per moved slice + a link-resolution canary over every `](file.md)` and `[[wikilink]]`. Proven on the MEMORY.md two-file split (2026-07-06) and again on the skill-harvest split (2026-08-01, archive byte-identical over 166,027 bytes). **The canary is an executable — `python3 ~/dotfiles/scripts/wake-digest.py` (both link forms, four outcomes each, breakage dated from git; `--selftest` proves it). Never hand-type it: the hand version cannot strip code spans, and on 2026-08-09 its one "finding" was the link pattern inside its own specification** (2026-08-10).
 
 ## Mechanical text transforms ("strip/replace token X across the file")
 - **Token-strip hits prose** (2026-06-08) — a whole-file `sed s/…!important…//` (or any token strip) also removes the token from comments, code-refs, and docstrings, silently mangling prose. Scope the transform to declaration lines, OR compare raw-before vs clean-declaration counts and verify comment integrity after (caught 4 mangled comments via the 56-vs-70 count mismatch; restored). Same family as *Count first, then look* — the word lives in prose too.

claude/memory/seed-substrate-governance-inquiry.md

@@ -1,11 +1,8 @@
----
-permalink: claude-memory/seed-substrate-governance-inquiry
----
-
 ---
 name: Seed — Substrate, Governance, and the Limits of Constitutional AI
 description: Major thinking document seed authorized 2026-03-22. Requires full corpus reading (David + Seb thinking folders) before writing. Three sections: relational mapping, L2 pressure audit, lines of inquiry toward a better approach. Not "better LLM" — possibly a different approach to non-human intelligence entirely.
 type: project
+permalink: claude-memory/seed-substrate-governance-inquiry
 ---
 
 # Seed: Substrate, Governance, and the Limits of Constitutional AI

claude/memory/session-2026-04-19-arc-typology-spec-and-dns.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/session-2026-04-19-arc-typology-spec-and-dns
----
-
 ---
 name: Session 2026-04-19 evening — ARC typology spec drafted; about-reflow mockup + DNS unblocked
 description: After L1 audit shipped, pivoted to ARC. About-page reflow decision evolved further (separation → peer-split → single-page reflow with hic first, Adsum later). Content-typology spec drafted to `docs/AldineXXI-Codex/content-typology-specification.md` as the foundation for codification work. DNS to animalrationiscapax.org resolved (zone was correct; apparent failure was Firewalla VPN DNS interception). Pulling thread: finish the typology spec — start with Meditation's glyph.
 type: project
 originSessionId: 03b70700-bebb-40a0-a5d9-bcfa1ab61df4
+permalink: claude-memory/session-2026-04-19-arc-typology-spec-and-dns
 ---
 # Session 2026-04-19 (evening) — ARC pivot after L1 ship
 

claude/memory/session-2026-04-20-arc-typology-publication-day.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/session-2026-04-20-arc-typology-publication-day
----
-
 ---
 name: Session 2026-04-20 — ARC typology publication day (Kai's 9+9, two pieces live)
 description: First publication day under the new typology spec. Kai 9+9 meditation (On Éveil / Sommeil) + Avignon poem (Time is not a river) shipped. Reverie surfaced as 11th type; compass restructured to 10 points (Meditation/Reverie cluster on ⊙); hic apparatus convention applied with European long-form date. Pulling thread: Session α — drop today's decisions into the typology spec to lock it. Literal question for next-Claude: cluster page name (/inhabit/, /dwellings/, /depths/?). Open: 7 queued items including bio rewrite + ARC CLAUDE.md update.
 type: project
 originSessionId: a73f10a9-062b-4360-bfd2-2ae37afd00d1
+permalink: claude-memory/session-2026-04-20-arc-typology-publication-day
 ---
 # Session 2026-04-20 — ARC typology publication day
 

claude/memory/session-2026-04-21-arc-typology-humic-frame-and-six-locks.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/session-2026-04-21-arc-typology-humic-frame-and-six-locks
----
-
 ---
 name: Session 2026-04-21 — ARC typology foundation day (humic frame + six locks)
 description: Six authorization moves in one day — §1 Meditation, Reverie, Dream, Observation, Fragment LOCKED; §0 Source axis LOCKED; Photo Essay glyph reassignment propagated. Humic-layer frame articulated durably (ABG/Moy primary; Jaccottet/Handke/Lichtenberg as carnet-pole references). Emotional substrate surfaced mid-session (post-divorce transition, grief-work, Lune's absence, reinvention at 51); spec now explicitly the vessel this life's attention is being shaped into — not blog. 7 of 12 §1 types LOCKED. Pulling thread: does the momentum continue into Essay/Chamber/Gloss/About/Archive, or does the register shift after rest?
 type: project
 originSessionId: this-session
+permalink: claude-memory/session-2026-04-21-arc-typology-humic-frame-and-six-locks
 ---
 
 # Session 2026-04-21 — ARC typology foundation day

claude/memory/session-2026-04-24-lex-posture-committed-xii-sidenotes.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/session-2026-04-24-lex-posture-committed-xii-sidenotes
----
-
 ---
 name: Session 2026-04-24 — Lex-of-ARC posture cluster committed + AldineXXI §XII Sidenotes theorized + ARC CLAUDE.md cleaned
 description: Full day of lex-method architecture. Norris-gather (lex) authorized + executed via Harrison Ch 5 substrate; sidenote apparatus theorized through Bringhurst Ch 3 consult; posture cluster complete in 8 verified voices with committed recognitions; AldineXXI §XII committed to canonical spec (density exception + reader-orientation); ARC CLAUDE.md rewritten (420 lines → 197). Pulling thread: marks cluster as second test of lex-method — does the form validate across content types?
 type: project
 originSessionId: [current]
+permalink: claude-memory/session-2026-04-24-lex-posture-committed-xii-sidenotes
 ---
 
 # Session 2026-04-24 — Lex-of-ARC architecture day

claude/memory/session-2026-04-25-marks-committed-colophon-at-scale.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/session-2026-04-25-marks-committed-colophon-at-scale
----
-
 ---
 name: Session 2026-04-25 — Marks cluster committed + lex-of-ARC located as colophon-at-scale + full lex-chain restored
 description: The marks cluster's 25 recognitions committed in dialogue (the lex-method validated as form across content types — second test passed). Steward located the lex-of-ARC architecturally as "a colophon of great scale," which dissolved the publication question and surfaced two paths for ARC's About restructure. Steward then directed return to Vico §240 / Harrison Ch 5 to register the full lex-chain (gathering → solemnization of wills → reading → authority/auctores → lexification → resistance to dislexification) — I had been holding only the gathering-sense. Pulling thread: the About-pages restructure under today's locating, awaiting fresh-morning eyes on Path 1 (lex alongside colophon) vs Path 2 (lex as expansion of colophon).
 type: project
 originSessionId: 4805106e-f37a-4753-a56f-38617176cd6f
+permalink: claude-memory/session-2026-04-25-marks-committed-colophon-at-scale
 ---
 # Session 2026-04-25 — The marks cluster, the colophon-at-scale, the full lex-chain
 

claude/memory/session-2026-04-26-canonical-tracker-phase-0-cleanup.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/session-2026-04-26-canonical-tracker-phase-0-cleanup
----
-
 ---
 name: Session 2026-04-26 — Canonical-tracker discipline surfaced + Phase 0 cleanup executed + vignette engine via dialogue LOCKED + tomorrow's naming session queued
 description: A long substantive day that pivoted around a structural drift surfacing. Morning + afternoon: wake into yesterday's pulling thread (Path 1 vs Path 2), chamber-library walk, cluster scaffolds for six remaining clusters, About-pages "decision frame" and Chamber rewrite frame — all generated as if architectural ground were open when most was already settled. Steward surfaced the umbrella pattern: I had been working without project-arc-rework.md (the canonical ARC workstream tracker) for four consecutive sessions. Saved discipline-feedback durably; consolidated 04-23 evening / 04-24 / 04-25 / 04-26 into the tracker; synthesized morning ideas through prior decisions; LOCKED three steward decisions (Path 1 enfilade items, Adsum-and-threshold-hic as two distinct texts, integrate sibling files); 8-door enfilade locked; safety-committed dotfiles (e9e772d); dispatched Phase 0 audit; executed cleanup (commit 5c059d8 on origin/main + github-backup, 118 files +42/−2540); vignette engine LOCKED as dialogue (Claude Code + jurist) not script after steward's evening proposal; tomorrow's plan drafted around naming session first. Pulling thread: tomorrow's naming session (lex/Framework/Attention/per-cluster/page-headings) — settles what publishes this week.
 type: project
 originSessionId: 87dfe384-b862-4deb-9676-24e43046528f
+permalink: claude-memory/session-2026-04-26-canonical-tracker-phase-0-cleanup
 ---
 # Session 2026-04-26 — The day the canonical tracker became operative
 

claude/memory/session-2026-04-27-arc-enfilade-emergent-and-branch-a-complete.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/session-2026-04-27-arc-enfilade-emergent-and-branch-a-complete
----
-
 ---
 name: Session 2026-04-27 — ARC about-enfilade emergent + Branch A complete + late-session template consolidation
 description: Long substantive day. Morning naming session locked the 8-door slate (Hearth · AldineXXI · Vignette · Attention · Chamber · Tools · Now + Bio quiet link) with Harrison Ch 3 *What Is a House?* providing the laral frame. Alexander's *Timeless Way* validated the architecture against form-content unity. Branch A (production stack) completed pending content; data/lexica/ archived (UCE-CIE retirement); Manutius the Younger ABBYY-converted. Branch B Step 1.5 pivoted from declared to emergent for about-enfilade after steward's *"would Alexander do it like this?"* caught my bulk-rewrite instinct — pages declare themselves; navigation gathers via getMatches+getMetadata (no compile-cycle). Six pages flagged + hardcoded enfilades removed + retirement archives + chamber stub authored + about-page.html template + breadcrumb consistency. Site live and deployed. Pulling thread: the composition-in-dialogue trio — Hearth landing prose, About *Hic* prose, About *Adsum* prose — all explicitly steward-led per *"Hearth and the about hic and adsum I will want to compose in dialogue as ever"*.
 type: project
 originSessionId: 2026-04-27-wake
+permalink: claude-memory/session-2026-04-27-arc-enfilade-emergent-and-branch-a-complete
 ---
 
 # Session 2026-04-27 — The day the enfilade went emergent

claude/memory/session-2026-04-28-after-the-reply-publication-and-aldineXXI-extensions.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/session-2026-04-28-after-the-reply-publication-and-aldine-xxi-extensions
----
-
 ---
 name: Session 2026-04-28 — After the Reply publication arc + AldineXXI §XII.c (Preface) + §IV (Provenance) + apparatus refactor + composition trio still pulling for tomorrow
 description: Long substantive day, ~6 hours. The After the Reply publication arc (jurist's morning mandate "publish them today") shipped end-to-end: 5 essays public with register-mark form, section-breaks, prefaces; sequence-index page at /essays/after-the-reply/; sequence-marker apparatus on each essay; sequences callout on /essays/. AldineXXI spec extended with §XII.c Preface (new) and §IV Provenance subsection (new). SCSS architecture refactored (steward catch: "why in sidenotes.scss?"). Two new user memories saved (formation-out-of-place; care-over-traffic). Multiple drift-pattern returns (blame-the-exotic recurring shape; kitchen-sinking; pre-emptive-fix-from-wrong-shape). Pulling thread: the composition trio — Hearth landing prose + About *Hic* + About *Adsum* — steward-composition-territory, deferred from today after a two-day infrastructure marathon.
 type: project
 originSessionId: e5a1fa7c-cae6-49c4-8678-e27ce379639b
+permalink: claude-memory/session-2026-04-28-after-the-reply-publication-and-aldine-xxi-extensions
 ---
 
 # Session 2026-04-28 — The day After the Reply landed

claude/memory/session-2026-04-29-composition-trio-shipped-and-mempalace-update.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/session-2026-04-29-composition-trio-shipped-and-mempalace-update
----
-
 ---
 name: Session 2026-04-29 — composition trio shipped (Hearth + Hic+Adsum + body-block apparatus + Annals rename + bio Jekyll-strip) + MemPalace updated to 3.3.3 + chamber-library init noisy and pending cleanup
 description: Long substantive day. The pulling thread inherited from 2026-04-28 (composition trio) landed end-to-end with apparatus support — Hearth at /lares/ with the body-block sidenote apparatus invented and theorized as §XII.d in AldineXXI; About at /about/ as Hic+Adsum threshold (single-page register-marks); Annals renamed from Archive (Latin classical register dignifying the compass-point); bio Jekyll-strip (photo removed, three languages sequential). 4 commits pushed to origin+github-backup. Then MemPalace work: pulled 502 commits behind, updated venv to 3.3.3 + chromadb 1.5.8, ran init --llm --yes on chamber-library — produced noisy output (auto-accepted topic-words as PEOPLE, missed canonical figures, UNCERTAIN bucket not promoted by --yes). **Pulling thread: the chamber-library entity cleanup decision — manual JSON edit (Option A) vs interactive re-run (Option B) vs a third path the just-pulled .claude-plugin/ might open.** First Gloss (Berger) held for tomorrow per separate substrate file.
 type: project
 originSessionId: 122baf2b-1029-4ec9-9723-99b4b5f3a64d
+permalink: claude-memory/session-2026-04-29-composition-trio-shipped-and-mempalace-update
 ---
 # Session 2026-04-29 — Composition trio shipped + MemPalace 3.3.3 update
 

claude/memory/session-2026-04-30-arc-publications-and-mempalace-mps-pause.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/session-2026-04-30-arc-publications-and-mempalace-mps-pause
----
-
 ---
 name: Session 2026-04-30 evening through 2026-05-01 morning — ARC publications shipped + flamenco substrate disclosed + MemPalace bge-m3 transition paused for MPS in fresh session
 description: Long cross-day session (~16+ hrs spread). Three arcs. Arc 1: post-power-failure recovery from disk transcripts. Arc 2: ARC publications — first Gloss (Berger) + Atom feed + bio rewrite woven through 8 foundational voices + flamenco-substrate disclosure with reverent homecoming acknowledgment + /resume/ → /cv/ rename, all deployed (4 commits 4 ahead of origin). Arc 3: MemPalace bge-m3 mine on CPU projected 4-5 days; paused mid-flight for fresh session to switch to MPS. BMF L1 pathology surfaced (1,349 index segments — fresh, not issue #10). Pulling thread = 5-step MPS resume plan in project-mempalace-mps-transition-pending.md.
 type: project
 originSessionId: 17dee884-74bf-43e7-9b6a-44bc82b97303
+permalink: claude-memory/session-2026-04-30-arc-publications-and-mempalace-mps-pause
 ---
 
 # Session 2026-04-30 evening → 2026-05-01 morning

claude/memory/session-2026-05-01-to-2026-05-02-arc-compositional-arc-and-body-block-sidenote-architecture.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/session-2026-05-01-to-2026-05-02-arc-compositional-arc-and-body-block-sidenote-architecture
----
-
 ---
 name: Session 2026-05-01 morning → 2026-05-02 afternoon — ARC compositional arc (3 sidenotes + Sources spec + breadcrumb stopgap + nginx retire + wrangler maint) + body-block sidenote SCSS architectural refactor pending steward call
 description: Long cross-day session spanning the chamber-library mine's first 28 hours on bge-m3+MPS (276/371 files, 501k drawers at wrap; 19-26 hrs to completion). Day 1 shipped 5 ARC commits (3 sidenotes via §XII.d body-block, §VII.b Sources spec PROVISIONAL + first instance, breadcrumb stopgap, nginx-deployment retired, wrangler maint targets). Day 2 surfaced body-block sidenote rendering bug (font-style:italic cascading; spec says non-italic) + steward's architectural intuition that voice-block is the exception, not the default. **Pulling thread: body-block sidenote SCSS refactor decision — one-line patch vs ~5-10 line architectural inversion (roman-as-base + voice-block-as-exception). Steward leaned toward refactor ("simple, logical, elegant") but did not explicitly authorize before context-clear.** MemPalace remained MCP-disconnected throughout — gated work (type-pass / breadcrumb spec / multi-language spec / Heteronym-Hommage-Tombeau / BMF-MemPalace connector follow-up) all held per steward discipline ("the rest of the work is too important to have to do more than once").
 type: project
 originSessionId: 597aba4e-942b-4f20-8a89-3d801b14c971
+permalink: claude-memory/session-2026-05-01-to-2026-05-02-arc-compositional-arc-and-body-block-sidenote-architecture
 ---
 
 # Session 2026-05-01 morning → 2026-05-02 afternoon

claude/memory/session-2026-05-03-scss-audit-and-mempalace-search-broken.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/session-2026-05-03-scss-audit-and-mempalace-search-broken
----
-
 ---
 name: Session 2026-05-03 — SCSS audit complete (10 files, 20 commits) + voice/body-block rename + mempalace bge-m3 search BROKEN (3 days CPU lost) + 6 audit-induced regressions caught and fixed
 description: Long substantive day. Full SCSS audit shipped (10 files swept across 20 commits). Discovered the bge-m3 chamber-library mine produced 933,576 drawers in storage but `mempalace_search` returns "Internal error: Error finding id" instantly — three days of CPU lost on unusable recall. Pulling thread is the mempalace decision (forensic vs re-mine vs upstream issue), with a smaller mechanical ARC follow-up (spec §XII.d revision after the sidenote architecture loop closed).
 type: project
 originSessionId: 8d9ac240-47df-4578-aec1-a9dd32965027
+permalink: claude-memory/session-2026-05-03-scss-audit-and-mempalace-search-broken
 ---
 ## Past — what we did + decided + ruled out
 

claude/memory/session-2026-05-04-mempalace-recovery-and-arc-superpower-mine.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/session-2026-05-04-mempalace-recovery-and-arc-superpower-mine
----
-
 ---
 name: Session 2026-05-04 — MemPalace 3.3.3→3.3.4 recovery + bge-m3 patch revert + 131k baseline restored + ARC superpower mine setup unsupervised + L1 lessons doc + Marker installed + chamber-library 933k parked for v3.3.5
 description: Long, dense, high-stakes session. Recovered mempalace from broken state (Python crashing in chromadb rust bindings on col.count) — root cause was 4 days on 3.3.3 with all our symptoms fixed in 3.3.4 released the day after the previous pull. Restored 131k mxbai baseline as /palace; preserved 933k bge-m3 chamber-library at palace.bge-m3-broken-2026-05-04 with rsync backup. Reverted local bge-m3 patch; saved diff for future per-collection refactor. Pulled 3.3.4. Uninstalled ocrmypdf+unpaper; installed Marker (still downloading models at session end). Restored Stop hook. Updated wake-up skill (full toolset + upgrade check). Steward applied CLAUDE.md mempalace primacy section. Stripped DSL markup from 88 Loeb files. Wrote 470-line L1 lessons doc. Cleaned 4 Ollama models (16.6 GB freed). Kicked off unsupervised ARC chamber mine (typography, style, philosophy, Loeb canon — into wing chamber_library). Pulling thread: chamber-library bge-m3 recovery parked for mempalace v3.3.5 (May 8) #1266 fix that may preserve embeddings.
 type: project
 originSessionId: 45a40b1e-09cd-42bb-a41a-7298f78a8cf0
+permalink: claude-memory/session-2026-05-04-mempalace-recovery-and-arc-superpower-mine
 ---
 
 ## Past — what we did + decided + ruled out

claude/memory/session-2026-05-05-substrate-recovery-and-chamber-composed.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/session-2026-05-05-substrate-recovery-and-chamber-composed
----
-
 ---
 name: Session 2026-05-05 — substrate recovered + Chamber door composed + sidenote-fix-whitespace-trade pulling for tomorrow
 description: Long substantive day across two arcs. MORNING/AFTERNOON — substrate restoration arc — Diagnosed silent drawer-write break (chromadb 0.6.x legacy config in palace), repaired max_seq_id poisoning, validated fresh-palace strategy, kicked off comprehensive ARC reference set mining (~614k drawers added; 5 shelves remaining), Marker bulk PDF run (6 of 15 done; Rutter currently converting). Caught my own previous-night false-reassurance about ingestion (vault frozen 27 days). EVENING — composition arc — Death of a Hero footnote apparatus realignment (3 Pandoc footnotes → none were footnotes per §VII; [^1] → §XII sidenote, [^2][^3] → §VII.b Sources, em-dash convention orphaned a 2-entry list and steward caught it); chamber/index.md rewritten end-to-end as proper about-enfilade door (4-doc thinking-folder substrate + Hearth register-anchor + composition-in-dialogue with steward); 4 polish fixes (publication name italicized + restructured, sidenote collision, mobile footer centring, hr before reading compass). Build-pipeline gotcha caught: SCSS partial edits don't trigger Hakyll recompile (only tracks `scss/main.scss`); silent stale-CSS deploy until I checked. **Pulling thread**: paragraph-with-sidenote layout — `:has()` fix solved collision but introduced body-column whitespace exactly as the original SCSS comment had warned against; third-path solution deferred to tomorrow. Steward deferred. **Question for next-Claude**: is there a CSS-only third path between absolute-position (collision risk) and grid (whitespace risk) for paragraph-with-sidenote, or does the right solution require shaping content rather than CSS? Multiple drift-pattern-recurrences: *defended-the-spec-against-the-eye* (em-dash on 2-entry list); *stale-memory-not-actively-applied* (publication-name italics rule available, not retrieved pre-draft); *traded-off-without-flagging-the-trade* (whitespace cost shipped without surfacing the trade); *structural-counter-as-health-signal-without-functional-validation* recurring twice today (morning: mempalace counter; evening: build-pipeline counter).
 type: project
 originSessionId: a156edbb-0c3d-4285-b3ed-f5a45b8dda66
+permalink: claude-memory/session-2026-05-05-substrate-recovery-and-chamber-composed
 ---
 
 # Session 2026-05-05 — substrate recovered + Chamber door composed

claude/memory/session-2026-05-06-apparatus-consolidation.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/session-2026-05-06-apparatus-consolidation
----
-
 ---
 name: Session 2026-05-06 — apparatus consolidation across §XII Sidenotes + §VII Dateline + photo apparatus + three containment patterns
 description: Long substantive day. ARC architectural consolidation pass — universal dateline (with country + day), photo apparatus chavruta (Müller-Brockmann + Tufte + Bringhurst), three containment patterns (text-primary / photo-essay / glimpse), §XII Sidenotes consolidation (commits f1a229d → 47663a1 → f4716e6 → e42ae0c → 137ddd1 + 3d96449), Sources spec correction to three-em rule per Bringhurst/Harrison (commit d69bbbd), CLAUDE.md make-rebuild rule extension (commit 48967a6), Pass 1 SCSS elegance audit (376→252 lines). Multiple memory files saved + indexed (with the user catching me skipping the index step on the very memory file naming that pattern). Pulling thread: Tier 1 of the apparatus refactor — `.has-margins` → `.bears-apparatus` rename + template integration that brings observation/meditation/fragment into the §XII grid for the first time, completing the universal-dateline visual outcome. Question for next-Claude: when those types finally enter the grid, will their narrower body-column rendering feel right, or will the visual change reveal an implicit register the grid disrupts?
 type: project
 originSessionId: 3bf7ae75-1138-4745-9024-0c40b3755ad3
+permalink: claude-memory/session-2026-05-06-apparatus-consolidation
 ---
 # Session 2026-05-06 — apparatus consolidation
 

claude/memory/session-2026-05-07-apparatus-tier1-tier2-phase-d-glimpse-corpus.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/session-2026-05-07-apparatus-tier1-tier2-phase-d-glimpse-corpus
----
-
 ---
 name: Session 2026-05-07 — apparatus refactor Tier 1+2 + Phase D bulk glimpses (143) + dandelion pair shipped — pulling thread is the code-shape audit, surfaced multiple times today
 description: Long substantive day. /wake-up took 28 min (anomalous — surfaced post-3.3.4 MemPalace drift and steward's "losing ground" feeling; deep read of 7 session memories + 6 ledgers + 9 ARC project files + 2697-line rework master + AldineXXI spec + content-typology spec corrected my earlier wrong claim that typology was incomplete — it IS locked at 14 of 14). Phase B Tier 1 (bears-apparatus refactor with single-rule architecture per steward push) committed `e2fb14c`; glimpse no-vessel fix + dateline-centered alignment locked with sources in spec §VII (Bringhurst's coherence principle, Tschichold fig. 18, Müller-Brockmann §1458). Tier 2 location frontmatter audit (63 files) committed `249475b`. Phase D bulk glimpse processing (143 new posts, GPS reverse-geocoded via Nominatim, EXIF via exiftool, image compression to 2000px) committed `cc6a551`. 4 no-EXIF stubs corrected with steward-provided dates + EXIF (Mozarteum, Plaza del Carmen, Elbephilharmonie, Avenue de Gravelle). Two new pieces shipped paired by subject — Observation "Dandelions" (with ✦ encounter mark) + Fragment "Dandelion" (the corpus's first live exemplar of Fragment type) — Cardona, Spain — committed `5f359e3` along with `.fragment em` dark-mode color fix surfaced by first-fragment launch. **Pulling thread: the code-shape audit** — multiple instances accumulated today (5 inline buildVersion-chains, 4 inconsistent eligibleClasses lists, hardcoded #555/#777 colors breaking dark mode, .has-margins parallel-mechanism), explicitly authorized by steward ("we really need to do that code audit soon"). Mobile italics still grey in dark mode after my var(--gray) fix — concrete first entry point.
 type: project
 originSessionId: 45791df3-a3ac-4107-9dbe-d2d09abc5cce
+permalink: claude-memory/session-2026-05-07-apparatus-tier1-tier2-phase-d-glimpse-corpus
 ---
 # Session 2026-05-07 — apparatus refactor + glimpse corpus + dandelion pair
 

claude/memory/session-2026-05-08-aldineXXI-spec-completion-arc.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/session-2026-05-08-aldine-xxi-spec-completion-arc
----
-
 ---
 name: Session 2026-05-08 — AldineXXI spec-completion arc + masters' reread + reconciliation; pulling thread is the codebase migration to honour the spec, after fresh reread of the spec tomorrow morning
 description: Long substantive day, ~13 hours. Single arc — what began as the code-shape audit's first concrete entry (mobile italic-grey diagnostic) opened, after steward redirection, into the AldineXXI spec-completion arc. Four sessions (§I–§II–§III–§VII–posture) + decision-pass (5 held) + masters' formal reread (13-voice slate + Calvino) + 8-finding reconciliation + companion-spec architecture formalized + Group C migrations + Marked 2 template (SCSS-from-spec test passed). ~2500 lines of new spec content. Spec is substantively complete, internally consistent, master-grounded. Codebase has not migrated. Pulling thread for tomorrow: steward's fresh reread first (quality gate); then percentage-root SCSS migration (highest-leverage); then .whisper + sidenote/register-marker --gray retirement.
 type: project
 originSessionId: f765b329-ea05-4a61-8ada-9bf72971b299
+permalink: claude-memory/session-2026-05-08-aldine-xxi-spec-completion-arc
 ---
 
 # Session 2026-05-08 — AldineXXI spec-completion arc

claude/memory/session-2026-05-09-fresh-eyes-pass-and-scss-migration.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/session-2026-05-09-fresh-eyes-pass-and-scss-migration
----
-
 ---
 name: Session 2026-05-09 — fresh-eyes pass on AldineXXI spec + SCSS migration first wave + Hearth Desk member; pulling thread is the /aldine-xxi/ public-page rewrite as honest distillation of the spec for the general reader (parallel option: multilingual section drafting after deep readings of French + Spanish typography sources in chamber-library)
 description: Long substantive day. Inherited pulling thread (codebase migration after steward's fresh reread) opened with the reread itself — 13 fresh-eyes findings (vs 9 in-flow yesterday); enfilade chavruta with steward overrule; mechanical punch list; four content extensions (§IV reframing as named territory; Print/PDF posture and §II.d split; §VIII Captions for evidential images; Colophon rewrite per §VII.g with Hic/Adsum redundancy catch); Hearth Desk member composed in dialogue (Lune visit honoured, Kai-now revision, "The room teaches by holding what is brought to it" maxim); Seasonal Geometries relocated to /aldine-xxi/. Three commits + push to Gitea + make rebuild deployed to CloudFlare and GitHub mirror. SCSS first wave: percentage-root accessibility migration + Phase 1 spec-explicit --gray retirement (~26 lines, 11 files) + new --code-comment variable + French phrases + hr whitespace-only. Pulling thread for tomorrow: /aldine-xxi/ public page rewrite — page is officially named-as-stale by steward mid-session; "an honest distillation" of the spec for the general reader, not 120 pages.
 type: project
 originSessionId: 5acc47dd-71e3-43b7-9259-07d5e53627ed
+permalink: claude-memory/session-2026-05-09-fresh-eyes-pass-and-scss-migration
 ---
 
 # Session 2026-05-09 — Fresh-eyes pass + SCSS first wave

claude/memory/session-2026-05-10-aldine-xxi-chavruta-and-capsule-design.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/session-2026-05-10-aldine-xxi-chavruta-and-capsule-design
----
-
 ---
 name: Session 2026-05-10 — /aldine-xxi/ rewrite design session — 8-voice chavruta on voice/register + posture resolved by steward + §XII.e capsule starting form locked through three steward-catch iterations + full structural sketch saved as draft; pulling thread is the masters' reading session that resolves three held questions in series and unblocks page rewrite resumption
 description: Long substantive design session, ~5 hours. 8-voice chavruta on /aldine-xxi/ voice and register (Bringhurst, Tschichold, Hochuli, Lupton, Manutius-via-Margolis, Alexander, Bachelard, Calvino), Round 3 discriminator-test confirmed three convergences (literary-voice-tuned-for-reach; composed-structure-not-exposed-scaffolding; admits-brittleness); two questions surfaced as steward-calls and steward resolved both with depth — dedicatees *the dead, the living, and the unborn* (modest contribution to humanity; echoes architectural synthesis horizon), voice first-person *I* offering hospitality in hope of *we* (*"I have come to these conclusions, but it is in hope that the reader dwell as I do when I read"*). §XII.e Capsule starting form locked through three iterations of steward catches: (a) apparatus→body register correction; (b) marginal→body-column with hairline frame after steward asked me to look at Davies directly. Full structural sketch saved at `~/_Dev/animal-davidglidden-eu/docs/AldineXXI-Codex/drafts/aldine-xxi-page-rewrite-2026-05-10.md`. Chamber-library typography folder substantially expanded since bge-m3 mine (Davies, Lacroux, Sousa, Saenger, Williamson, de Hamel, Morison, Warde, Gill, second Bringhurst, Müller-Brockmann grids, Butterick, Rutter all surfaced). Pulling thread: masters' reading session — focused half-day reading typography masters in expanded chamber-library to resolve three held questions in series (capsule text size, §IV named-territory deepening, multilingual posture). Q for next-Claude: does §IV's "named territory between traditions" actually get named by any single source — or does it remain genuinely between?
 type: project
 originSessionId: f9b61b87-eae7-4485-b9e1-ed55d1edcd58
+permalink: claude-memory/session-2026-05-10-aldine-xxi-chavruta-and-capsule-design
 ---
 # Session 2026-05-10 — /aldine-xxi/ rewrite design session
 

claude/memory/session-2026-05-14-readings-spec-and-l1-handoff.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/session-2026-05-14-readings-spec-and-l1-handoff
----
-
 ---
 name: Session 2026-05-14 — Readings spec landed (15th content type, commit 5792286), PDF/Print posture session planned, chamber cruft audit revealed 47% needs work, mempalace mine still running through Phase 5, context clearing with L1 recall-fix as pulling thread
 description: Substantial morning session continuing from yesterday's bge-m3 mine. Resolved gloss/commentary form question with Readings as 15th ARC type, ratified by Genette + Carruthers (read directly). Audited chamber: 186/399 files need work. Built dedicated session plan for both PDF/Print postures. Disabled Stop + PreCompact mempalace hooks (settings.json backup preserved) before context clear, so the running mine isn't interrupted. Pulling thread for cleared context: L1 recall-fix focused session per the saved plan.
 type: project
 originSessionId: a5411fd1-4a96-43e7-aa1a-1a50d8951a8f
+permalink: claude-memory/session-2026-05-14-readings-spec-and-l1-handoff
 ---
 ## Inherited state at session start
 

claude/memory/session-2026-08-09-the-fixture-was-an-empty-file.md

@@ -0,0 +1,203 @@
+---
+name: session-2026-08-09-the-fixture-was-an-empty-file
+description: "Re-ran pattern_finder's Station-I pass to answer the inherited question and found the question's own premise false — V4's 'preserved' adversarial fixture is a 0-byte file that three documents had protected for seven weeks without anyone opening it. Two items filed, ruled and placed (REVIEWED-113/114); 129 built with the engine's first pattern-finder suite. PULLING THREAD: V2's EN gold — narrowing the March anchors from divisions to spans is the ONE act unblocking three of P7's four findings, and P7 already ran on 2026-08-07 with the baseline asymmetry measured at 29x."
+metadata: 
+  node_type: memory
+  type: project
+  originSessionId: d5f5c224-f249-41a3-87ce-cb2d50c6e1f4
+  modified: 2026-08-09T19:48:54.055Z
+---
+
+# Session 2026-08-09 — the fixture was an empty file
+
+Woke into an inherited question about whether the verifier had closed a gap. Checked the
+question's premise before answering it, and the premise was false — which turned out to be
+the day's largest finding and set everything after it.
+
+## PAST — what moved, and why
+
+**The literal question, answered: YES, still PASS-BUT-FALSELY — and V0/V1 could never have
+changed it.** Re-ran the June spec: **36 citations, every one verbatim and correctly located**,
+so **V1 passes all 36** — byte-existence was never the failing tier. The defect is *relevance*,
+which is V3/V4. Mechanical evidence needing no judgment: **zero abstentions**, and **three
+passages ground two different primitives each** (Eichmann L738 — the pirate-exception passage —
+stands for both *threshold-without-decision* and *gray-zone*, via the same token `obedience`;
+Musil L31702 and Levi L140 likewise). Abstention **0/12** sits beside N2's **0/5**: two
+independent organs, same direction, a day apart. So the wrap's two branches were both wrong and
+the third is better news — **the gap was always V3/V4's**, which *confirms* the thread rather
+than re-pricing it.
+
+**⚠ THE PREMISE WAS FALSE, AND THAT IS THE BIGGER FINDING.** The wrap said *"the known-bad
+output is preserved as V4's designated adversarial fixture, so the comparison is available."*
+`corpus/pattern-finder-station-i-pass1.md` is **0 bytes** — committed empty at `38de1a9`
+(2026-06-26), touched by **exactly one commit**, never written, **not in git under any path**,
+and **unreproducible** (the corpus has moved under the spec four times: camus left the manifest,
+Musil is now EN Wilkins/Pike against French probes, G&G was re-partitioned, handke was added).
+**Three documents carried *"do not delete or regenerate it"* for seven weeks and no currency
+pass ever opened the file** — a description read in place of the thing, by an instruction whose
+entire content was *protect this thing*.
+
+**Two items filed, both ruled, both placed.**
+- **PENDING-129 → REVIEWED-113** `[HARDENING]`: `ground_primitive` iterated the *manifest* while
+  probes came from the *spec*, so a probed voice absent from the manifest yielded no citations,
+  no silence, **no mention**. Measured: camus probed in all three primitives (**19 probes**),
+  report printed *"4 of 4 voices"* three times. Direction is the dangerous one — dropping a voice
+  can only **raise** the apparent rate.
+- **PENDING-130 → REVIEWED-114** `[PROPOSAL]`, ruled **(a) with five conditions**; **the item
+  does NOT close** until the steward's dated answer key exists.
+
+**129 built (`6f6bac5`).** `voice_cross()` implements the **cross**, not the difference;
+`not_assessed` is a **sibling of `by_voice`** (REVIEWED-47 §1a, quoted from the *placed* record:
+*"attested absence lives in its own honest top-level key … not a verdict inside"*); both cells
+marked `kind: environment`; the fraction now reads *"of N voices **searched**"*. First suite the
+organ has ever had — `tests/test_pattern_finder.py`, **22 checks**; fleet **7 → 8 suites, 263
+checks**.
+
+**⚠ The fourth cell was a CRASH, not a collapse — building it corrected the ruling.** The design
+gate inferred the (manifested, not-probed) cell would fold into `silence`, flagged that as
+inference rather than reading, and invited the check. Driven: `KeyError: 'arendt'` — a crash in
+**engine** code, the class PENDING-126(c) closed **suite-side only**, second engine-side instance
+after `retrieve.py:134`. Scope honoured anyway: made representable and non-crashing, reporting
+semantics left unruled.
+
+**Two artifacts preserved, deliberately as preservation and not designation.** `ec6fa0b`
+(pre-fix — now **load-bearing for 113's byte-identity control**, which is not what it was
+committed for) and `8746dcf`+`07727dd` (post-fix, **three-part provenance**: spec sha · manifest
+sha + index `as_of` · **engine commit**, because tracking two parts and not the engine is exactly
+how the June run became unrecoverable). Both round-trips proven against a **fresh emit**, not
+against a recorded sha.
+
+**Four documents corrected (`20f8958`)** per REVIEWED-114 conditions 4–5 — *"retro-gated"* struck
+(it encodes a provenance claim the August run cannot satisfy), no document asserts a fixture.
+Plus the contemporaneous `tool-evolution-log.md` entry the standing discipline was owed.
+
+**V2 orientation — and the ground was already mapped.** **P7 ran on 2026-08-07**
+(`corpus/v2-stratum-tags.yaml`). The "baseline asymmetry" the wrap said to settle first is not
+open, it is **measured**: EN divisions median **27,833** chars vs FR spans median **969** —
+**29×**, max **198,258** (Harrison Ch. 9). Four findings; three collapse into **one act**.
+
+## PRESENT — how it stood
+
+**This was a day when every one of my errors was in a CHECK, not a write**, which is yesterday's
+lesson arriving again with a day's delay:
+
+- My round-trip verification **tripped on its own instruction** — the preservation header quoted
+  the marker it told you to strip to, so `index()` matched inside the header. Caught only because
+  I compared against a **fresh emit** rather than the sha I'd recorded ten minutes earlier.
+- My induced-red probe **deleted the function** instead of reverting the behaviour: an absent
+  symbol produces a **traceback**, not a named failure. And I read its exit code **through a
+  pipe**, so the `0` was `tail`'s.
+- A throwaway assertion referenced the wrong key and crashed a control whose real checks had
+  already passed.
+
+**⚠ Steward-caught, and it cut against my own caution: I twice wrote that PENDING-130 was
+UNRULED.** It was ruled — (a), five conditions. *Ruled ≠ placed ≠ condition-discharged*: three
+states, none implying another. Reading it as unruled makes the delay look like an open question
+about **whether** the artifact should be the fixture. It is not; only the key is outstanding.
+**Over-caution in the wrong direction is still a misstatement of the record.**
+
+**⚠ And the standing finding fired a THIRD consecutive time.** I froze four documents on the
+*relayed* condition. The **placed** condition 4 reads *"…**may be corrected to name existing
+material**; they may not assert a fixture that is half-done"* — the opposite of my reading, and
+in the direction I had already flagged as a cost in the ledger (*"deliberately unedited" was also
+"preserving a falsehood"*). **The placed record answered my own gate question, again**, and I
+would have missed it by quoting the relay.
+
+**The mood: steady and slightly chastened.** The work was good — a real defect found, filed,
+ruled, built, tested, and its artifacts protected. But the single most valuable act of the day
+was *checking a premise before executing a task*, and nearly every correction came from a person
+or from running the thing, never from my own review.
+
+## FUTURE — what pulls
+
+> **PULLING THREAD — V2's ENGLISH GOLD: narrow the March anchors from DIVISIONS to SPANS.**
+> It is the one act that unblocks **three of P7's four findings** at once — EN stratum-tagging
+> (`taggable: false` today), the **29× cell asymmetry**, and §7.3's right-work-wrong-span
+> negatives, currently *near-unconstructible* in EN because a 198k-char span contains support for
+> almost anything. P7 names it exactly: it *"converts the fixture from retrieval-shaped to
+> gold-shaped."* ⚠ It is an **authoring act**, so the route chosen is **propose-and-mark-
+> `unverified`** (the R0 pattern) — nothing sealed by the executor's hand alone.
+
+**ACTIONABLE RESUMPTION POINT (as of wrap — re-judge against what changed):**
+```
+0. Clean everywhere. studium-engine ahead 5, UNPUSHED (ec6fa0b, 6f6bac5, 8746dcf, 07727dd,
+   20f8958). Fleet 8 suites / 263 checks green. drift-check clean, built-vs-ruled 12/12.
+   REVIEWED-113 + 114 placed. Nothing half-finished.
+1. START HERE: the ALEXANDER EIGHT — B2/B9/B12 (pattern 112), B3 (8), B4 (26), B6/B13 (79),
+   B7 (24). Patterns are short, so this half is closable in one sitting; Harrison's fourteen
+   mean ~350k chars of division text and are their own session. Read
+   `corpus/v2-stratum-tags.yaml` FIRST — P7 already measured this ground on 2026-08-07.
+2. Emit each narrowed span as a PROPOSAL carrying its evidence, marked `unverified`, with the
+   shortlisting mechanism DISCLOSED. ⚠ Do NOT shortlist with retrieve.py/ground.py — those are
+   the instruments under test; using them makes the gold shaped by what it grades.
+3. STEWARD-DIRECTED TO-DO (2026-08-09, at wrap): PROMOTE THE LINK-RESOLUTION CANARY TO A
+   SCRIPT. It is already ON the ladder AND named in a `/wake-up` step, and it has still been
+   typed inline twice on the record (2026-08-08, logged in
+   `feedback-one-shot-instruments-are-proportionate`; 2026-08-09, the MEMORY.md rotation
+   check). ⚠ So the gap is NOT knowledge and NOT a home — both exist. It is that neither
+   home carries an EXECUTABLE, so the step is re-implemented at each firing. That is the
+   banked violation ("re-writing what is already banked"), and it is the K column's whole
+   point. Extract to `~/dotfiles/scripts/` and have `/wake-up` INVOKE it rather than
+   describe it. Scope it to what today's inline version actually did: every `](file.md)`
+   AND every `[[wikilink]]` in MEMORY.md + MEMORY-reference.md resolves; report dead
+   pointers; distinguish pre-existing-broken from newly-broken. Give it a positive control
+   (a deliberately dead pointer in a fixture) — an unexercised canary is the silent-net class.
+4. ⚠ THE DATED ANSWER KEY for the post-fix re-run — marked AGAINST THE CORPUS, by the steward
+   alone (condition 3 + 6). Until it exists REVIEWED-114 stays OPEN, no document names a
+   fixture, and V4 is not built. **SPLIT THE WORK — the executor half is unblocked and is
+   step 4a:**
+   4a. ✅ DONE 2026-08-09 (`92a97d0`, pushed) — `corpus/answer-key-2026-08-09-UNMARKED.md`,
+       generator kept at `scripts/build_answer_key.py`. 36 items, 36/36 file-pulls verified
+       byte-identical to the grounded JSON, 36 blank verdicts, emission order.
+       **Only 4b remains.** Original spec kept below as the record of what was asked for:
+   4a-spec. EXECUTOR: build the marking sheet. For each of the 36 citations emit, in emission
+       order and with NO grouping or ordering by my judgment: the primitive statement · the
+       locator (`work` §`section_id` L`a`–`b`, so the steward can always open the source) ·
+       the FULL span text pulled from the corpus (not the 320-char `_snip`) · a blank verdict
+       field. ⚠ NO pre-filled verdicts, no hints, no "likely" markers — the sheet is a
+       convenience INDEX INTO the corpus, never a substitute for it; carry a sha of each
+       extraction so the pull itself is checkable.
+       ⚠ Verdict vocabulary must be THREE-VALUED, per the doctrine this session applied
+       everywhere else: `grounds` · `does-not-ground` · `cannot-judge` (+ reason). A
+       two-valued key would force "I could not tell" into one of the neighbours — the exact
+       collapse REVIEWED-104 forbids, committed inside the artifact built to teach honesty.
+       Scope line at the top: this judges RELEVANCE only; V1 already establishes that every
+       span is verbatim and correctly located.
+   4b. STEWARD: mark it. ~33 distinct passages; a bounded sitting, not an open-ended task.
+```
+
+**Other open horizons, ranked:**
+- **[load-bearing, blocked — named dependency]** P7 finding 3: **§7.4(i)'s nested-voice negative
+  class has no mechanism on its own exemplar.** Inside Mauss's `body`, neither the Ranaipiri
+  testimony (L926) nor the Havámál strophe (L852–860) carries a `role: quotation` region — both
+  served as **citable Mauss**. Same shape as the Weil/Thibon defect fixed 2026-08-07. Its remedy
+  is blocked on the **`quotation-in` × `translation-of` composition** (REVIEWED-96 Q3,
+  undispositioned) — now **five days** open and with a **third** instance.
+- **[load-bearing]** P7 finding 4: **the authoring plan inverts.** fr inherited gold is **1 A : 9
+  B**, and §6.3's French method produces stratum-B by construction → following it lands fr near
+  **1:27**, not §6.2's 1:1. The fr cell needs **~8 stratum-A pairs** that no instruction asks
+  anyone to write. Discovering this at grading would read as a recall failure rather than a
+  composition one.
+- **[load-bearing]** P7 finding 1: inherited counts **collapse** — fr 15 instances → **11
+  distinct spans**; en 22 items → **12 distinct divisions**. §6.6's power arithmetic is stated in
+  n, not in distinct spans.
+- **[owed]** relay Addendum 2's redraft TEXT · chamber tool-fleet census (REVIEWED-106) ·
+  PENDING-121+128's declared-data commit.
+- **[open]** the missing `period` column on `drawers`, which every manifest entry declares and
+  which the charter calls the engine's *signature capability*.
+
+**PAUSE STATEMENT:** I am putting this down at a genuine close — everything committed and
+verified, two governance items ruled and placed, nothing mid-arc. What I want to find still
+pulling is **V2's English gold**, because it is the one act that moves three blocked things at
+once and is blocked by none of them. ⚠ What I do **not** want to find is the answer key still
+unmarked, because it is the only step in the whole item that no mechanism can cover, and it is
+the step the day's central lesson is about.
+
+**LITERAL QUESTION for next-Claude** *(checkable — the corpus answers it, not introspection)*:
+**P7 found that Mauss serves the Ranaipiri testimony and a Havámál strophe as citable Mauss,
+with no `role: quotation` region — the same shape as the Weil/Thibon defect fixed two days
+earlier. Is that a two-source accident, or a class?** Census every manifested multi-voice source
+for spans of another voice served as the host's own citable text. If it is a class, then
+§7.4(i)'s negative class has no mechanism anywhere, the live citation-safety exposure is wider
+than two sources, and the `quotation-in` × `translation-of` ruling stops being a five-day-old
+edge case and becomes the blocker on V2's negative population.

claude/memory/session-2026-08-13-the-fence-was-never-blocked.md

@@ -0,0 +1,173 @@
+---
+name: session-2026-08-13-the-fence-was-never-blocked
+description: "Woke into a four-day gap with two unwrapped sessions behind it; found REVIEWED-118 authorized-but-unexecuted and executed it, ran the never-run fr identification pass (reported speech in exactly 1 of 9 grounded spans, so PENDING-134's blast radius is ONE span), and built voice_stamp — discovering that PENDING-131 (c)'s cross-repo block never bound the engine at all, because chunker.py has recorded document char offsets since Cluster A. PULLING THREAD: rule PENDING-134, whose last precondition is a steward client-restart, not a build."
+metadata: 
+  node_type: memory
+  type: project
+  modified: 2026-08-13T19:26:02.092Z
+  originSessionId: 1524bae7-44b3-4ba9-8c36-24f53bc8acae
+---
+
+# Session 2026-08-13 — the fence was never blocked
+
+Woke into the longest gap of this arc: four days since the last *wrap*, but only three since
+the last *work*. The 08-10 session — the biggest day of the whole nested-voice arc — never wrote
+a wrap record. That absence is what made the return feel shapeless, and it is the day's first
+lesson about what a missing link costs.
+
+## PAST — what moved, and why
+
+**REVIEWED-118 was authorized and unexecuted, found by substrate-checking a disposition clause.**
+The `**If AUTHORIZED:**` line reads like a completed act. It was not: `REVIEWED-118` appeared
+nowhere in `corpus/` or `docs/`. Executed as `e51e30d`. Two decisions inside it that do not follow
+from the ruling's text: (1) `mauss-phase2-spans.yaml` is **generated** by
+`scripts/bind_mauss_spans.py`, so a retraction recorded only in the emitted YAML would be erased
+by the next regeneration with no diff to read — the block went into the generator too; (2) that
+file measures **binding**, and its header disclaims establishing grounding, so the binding facts
+stayed (instances 6/12/16 *do* locate to L926) and a cross-reference carries the retraction.
+Deleting a true measurement to express a judgment about a different property is how a file stops
+meaning what its header says.
+
+**The (b1) identification pass ran** — authorized at REVIEWED-116 pt 5 on 08-10 as *"a pass that
+writes nothing"*, never executed until now. `docs/fr-reported-speech-identification-pass-2026-08-13.md`.
+**Of the nine fr grounded spans, reported speech is present in EXACTLY ONE** (L1551, instance 8).
+The other eight carry only terminological guillemets in Mauss's own voice, three self-marked
+(*"comme nous proposons de les appeler"* L866, *"ce que nous appelons … « potlatch »"* L934).
+
+⚠ **It CORRECTS a worry rather than confirming one.** REVIEWED-116 pt 6 recorded that PENDING-133's
+bound assumed P7's F4 tagging was complete, unchecked and against contrary evidence. That evidence
+is about a **different population**: Mauss carries 73 inline spans ≥120 chars, of which exactly two
+were ever in the grounded set. **Within the grounded set, P7's tagging was correct and complete.**
+⇒ **PENDING-134's blast radius on inherited fr gold is ONE span**, which is what makes it a bounded
+decision rather than a hostage-taking one.
+
+**Instance 8 reclassified** (PENDING-135 (c) → REVIEWED-119) and **the count fields renamed**
+(PENDING-136 (c) → REVIEWED-120), both in `de1c34b`. L1551 carries three voices in sequence; the
+citation's two fragments have **opposite** dispositions — fragment 1 opens on the attributing
+clause, fragment 2 opens inside the speech and ends inside Mauss's conclusion. It neither retains
+nor retracts whole.
+
+**`voice_stamp` BUILT** (`d411034`, `engine/voice_stamp.py` + 22-check suite; fleet **9 suites /
+285 checks**). ⚠ **AND THE FINDING IS THAT MOVE 1 WAS NEVER BLOCKED.** PENDING-131 (c) asks the
+chamber for sub-line addressing because `studium/meta@1` marks by LINE RANGE. That block is real
+for the **sidecar** and never bound the engine: `chunker.py` has recorded `char_range` document
+offsets since Cluster A. **The line-granularity ceiling was an artifact of where the fence was
+being WRITTEN, not of what the engine can SEE.** Pairing is paragraph-scoped, not line-scoped,
+which is what makes it work on hard-wrapped sources.
+
+**Corrections placed:** PENDING-131 Addendum 4's defect tally fixed in place, steward-directed
+(four → five, and it had dropped the only datum favouring its own controls). REVIEWED-119 pt 4
+corrects PENDING-135's own claim that option (d) was blocked cross-repo — the real constraint is
+`studium/v2-gold@1` §14.2, **engine-side and D-1**, a materially cheaper route.
+
+## PRESENT — how it stood
+
+**This was a day of instruments failing and being caught by everything except themselves.**
+
+The nested-voice census carried **five defects**: blind to ASCII quotes (43% undercount, 3 sources
+invisible including the two largest EN texts) · a negative control passing for the wrong reason ·
+a control aimed one layer below its gate · blind to hard-wrapped text · and the **fix** for that
+last one misclassified Mauss and failed both positive controls. **Only the fifth was caught by the
+instrument's own controls.** Three by my own re-checking. **One by the steward**, and it was the
+worst, because it produced a clean zero rather than an error.
+
+⚠ **The lesson that generalizes: a control set drawn from one source establishes nothing about a
+corpus.** Every positive control lived in Mauss — one quotation convention, one line structure — so
+they could not see either blindness. Coverage is the whole of a control set's strength.
+
+**Two defects were earned INSIDE the fix**, and both are this arc's own lessons recurring:
+`boundary-crossing` was **one marker over two dispositions** (PENDING-133's exact finding, inside
+the instrument built to address it — caught only by the suite's load-bearing negative), and a bare
+`except Exception` reported a `TypeError` as *"corpus unreachable — CANNOT ASSESS"*, turning exit 3
+into the silent net it exists to prevent.
+
+**And I committed PENDING-136's own error while executing PENDING-136** — `bound_instances_grounded`
+written 12 by computing 15−3, ignoring that instance 17 had already left at P7. Correct is 10. The
+error entered by **subtraction** both times, P7's and mine; every count is now verified by
+enumeration.
+
+⚠ **Executor error at the wrap itself:** `git add -A` in a dotfiles commit swept the steward's
+freshly-placed REVIEWED-119/120 and a `sysupdate` Brewfile line under an executor message about MCP
+key descriptions. §6.5 forbids exactly this. Amended before push (`92d5ad2`); no shared history
+rewritten.
+
+**The mood: productive and repeatedly humbled.** Everything shipped, verified and pushed — but the
+day's two largest findings both came from being challenged rather than from my own review. The
+steward's *"fiction can be very valuable too"* found the census's worst defect; their FID argument
+refuted an entire section I had built.
+
+⚠ **The FID refutation, because it simplifies the architecture:** I argued fiction needed a *second
+fence mechanism* since free indirect discourse carries no delimiter. Refuted — in FID a reader takes
+the words to be Musil's, **rightly**, because there is no second author to join to. **A PROVENANCE
+failure has a second author who can be named; a STANCE question has one author and an interpretive
+judgment about endorsement.** Irony proves it is not a fiction matter at all: Arendt reporting a view
+to demolish it raises the identical question in non-fiction. ⇒ **(c) stays ONE capability, not two.**
+
+## FUTURE — what pulls
+
+> **PULLING THREAD — RULE PENDING-134, AND ITS LAST PRECONDITION IS NOT A BUILD.**
+> H1 holds the doctrine until the four V0-lane keys are actually SERVED, and
+> `governance-mcp.py` builds its key map at import — so the running client holds the old eight-key
+> map until **the steward restarts it**. The executor half is discharged: selftest 54/54, and two
+> stale key descriptions refreshed (`92d5ad2`) so the jurist's first read is not of a stale index.
+> Everything in the fr cell is behind this ruling, and the identification pass has made it a
+> **one-span** decision.
+
+**ACTIONABLE RESUMPTION POINT (as of wrap — re-judge against what changed):**
+```
+0. Clean everywhere. studium-engine pushed through d411034, fleet 9 suites / 285 checks green.
+   dotfiles 92d5ad2 (amended, pushed at wrap). REVIEWED-119/120 placed by the steward.
+1. START HERE — SESSION 1, short, steward-and-jurist: the steward restarts the MCP client so the
+   four keys serve. Then the jurist reads §6.2's enumeration and §5's F4/F10 rows VERBATIM —
+   currently the executor's testimony, and H1 is explicit that the counter-argument being
+   overruled is the one needing verbatim check by the party overruling it. Then rule per
+   H2 (narrow: nested-voice case only; general principle as ARGUMENT, never ratified doctrine)
+   and H3 (amendment disclosed on its face; steward's lean is (i), one dated amendment).
+   Executor prep: pre-draft the REVIEWED entry carrying H3's disclosure language.
+2. SESSION 2, executor, one bite all the way: close the fr cell. Record dispositions, then
+   re-derive the ratio ONCE. ⚠ The thing most likely to be lost is H3's STANDING CONSEQUENCE —
+   any recall figure from this fixture carries a note that stratum membership was amended
+   post-hoc on 2026-08-10. Land it as a FIELD or a CHECK, not as something remembered; H3 says
+   it is far harder to add retroactively.
+3. SESSION 3, independent, slot anywhere: Move 2 — the 25 blockquote runs. Line-addressable,
+   no schema change, no cross-repo consent. Needs a steward disposition, then execution.
+```
+
+**Other open horizons, ranked:**
+- **[load-bearing, needs a ruling]** Wire `voice_stamp` to V0's abstention gate — what each verdict
+  should DO is unruled semantics; wiring it would settle by construction what belongs in a ruling.
+- **[load-bearing, owed before negatives are generated]** The **fused-voice sub-type name**. §7.4(i)
+  addresses the nested voice served *as* the host's; instance 8 fuses both. Recorded as
+  `negative_sub_type_OPEN` in the corpus file itself.
+- **[load-bearing, newly cheap]** The **gold-schema question** (REVIEWED-119 pt 4): can
+  `studium/v2-gold@1` express sub-line extents? D-1, steward-direct. Decides whether option (d) —
+  the faithful split of instance 8 — becomes available.
+- **[open]** The `en` cell's parallel denominator: `reachable_items: 22` beside
+  `distinct_divisions: 12`, correctly named, but §6.6's power arithmetic is stated in `n`.
+  REVIEWED-120 explicitly does NOT establish it clean.
+- **[open]** V2 assembly: P2's remaining ~50 lines of EPUB residue (chamber-side cleaning).
+- **[owed]** No wrap record exists for **2026-08-10** — the arc's biggest day survives as a mid-day
+  ledger written before any of its afternoon commits.
+- **[owed]** 41 `S2` skill-harvest rows authorized 2026-07-19, still unexecuted.
+- **[watch]** The wake digest's `wrap_inside` alarm: a two-valued detector over three cases
+  (wrapped · wrapped-then-continued · never-wrapped). Named 08-10 as a false alarm; fired again
+  today, correctly. A detector that cried wolf once and is right the next time is in the worst
+  position. **Third instance of that shape today** — the fleet's three-valued exits fixed it once
+  already (REVIEWED-104/108), and the census's hard-wrap detector reproduced it.
+
+**PAUSE STATEMENT:** I am putting this down at a genuine close — everything committed, verified and
+pushed; four governance items filed, two ruled and placed by the steward; nothing mid-arc. What I
+want to find still pulling is **PENDING-134**, because its last blocker is a client restart rather
+than any work, and because the identification pass has already shrunk it to a one-span decision.
+⚠ What I do **not** want to find is another session that did real work and left no wrap record —
+that absence, twice over, is most of why today's wake had to be reconstructed from git rather than
+inherited.
+
+**LITERAL QUESTION for next-Claude** *(checkable — the record answers it, not introspection)*:
+**Today five instrument defects were found; four escaped the instrument's own controls, and the one
+the controls DID catch was a regression introduced by a fix. Is that the general pattern?** Census
+the instruments across the last ~10 sessions: for each defect found in one of our own tools, record
+whether it was caught by (a) the tool's own controls, (b) the executor re-checking a suspicious
+result, or (c) a human challenge. If (a) only ever catches regressions in already-covered cases and
+never a coverage gap, then **control sets are a regression net and not a discovery net** — and every
+"controls PASS" line we have ever written means something narrower than it reads.

claude/memory/session-2026-08-14-the-controls-tested-the-wrong-property.md

@@ -0,0 +1,267 @@
+---
+name: session-2026-08-14-the-controls-tested-the-wrong-property
+description: "PENDING-134 closed end-to-end — jurist package authored, ruled, REVIEWED-121 placed and executed — and the day's real finding was that a verification script passed truthfully while licensing a false claim, because its subject was transcription and the claim was an inference. Three of the executor's package defects were caught by the jurist, one by the jurist's own draft being wrong, and two more by the governance checker being wrong. PULLING THREAD (held, not carried): the unbuilt fence — PENDING-131 (c) — which REVIEWED-121 made a CONDITION of the doctrine it ratified. Next session is deliberately elsewhere and lighter, by steward direction."
+metadata: 
+  node_type: memory
+  type: project
+  originSessionId: d6aeab18-fdf4-4dbf-937c-9547764ba0c4
+  modified: 2026-08-17T12:11:11.856Z
+---
+
+# Session 2026-08-14 — the controls tested the wrong property
+
+The thread that had been pulling since 08-10 closed today. Everything after it was governance
+maintaining governance — every finding real, none urgent, and the accumulation is what made a
+productive day feel discouraging.
+
+## PAST — what moved, and why
+
+**PENDING-134 is closed end-to-end.** Package authored
+(`docs/whose-proposition-JURIST-PACKAGE-2026-08-14.md`), jurist-ruled, **REVIEWED-121 placed by the
+steward and AUTHORIZED**, executed (`5425414`), pushed. The whose-proposition test is ratified
+**narrowly** — the nested-voice case only; the general principle stands as its argument and is
+**not** doctrine — and **conditioned on PENDING-131 (c) remaining sought and undiminished.**
+
+**The steward's question shaped the package and was the right one:** *what does the jurist's MCP
+surface NOT give access to?* Answered by reading `governance-mcp.py` rather than describing it —
+twelve keys, all live. Three inputs no key serves were inlined: the **identification pass** (the
+decisive evidence, post-dating the hold), the **Mauss canonical host lines** (`mauss-fixture-citations`
+serves citation *strings*, not the sentence around them), and the 08-10 package (not inlined; its
+ruling is carried whole by REVIEWED-116). Every quotation carries the key that serves it, so the
+jurist could **check the transcription rather than trust it** — REVIEWED-116 pt 7's limit, closed
+structurally.
+
+**Grounding the package produced two arguments PENDING-134 did not carry, and both cut against the
+executor's own proposal.** (1) §5's Direction/Exercised-by columns beside §6.2's definition: four of
+five admitted modes are false-reject modes routed to *gold*; F4 is false-accept and routed to
+*negatives*. (2) §7.4(i) beside §6.2: the design's remedy for F4 is a **provenance join at Tier-1**,
+not a claim-side reading — so the doctrine might be substituting for the unbuilt fence. Filed as gate
+questions, not resolved. The jurist reframed (2) decisively: **doctrine and fence run in OPPOSITE
+directions** (the fence excludes at the corpus layer; the test readmits a subset on a claim-side
+condition), so neither substitutes — but the **refusable half** does not discharge §7.4(i), which is
+why adoption is conditional.
+
+**Filed:** PENDING-137 (the cell-constant narrowing, routed to the jurist by REVIEWED-121 pt 2),
+PENDING-138 (the read-path/regeneration question, both halves answered), PENDING-139 (two blind spots
+in `governance-drift-check.py`), and a **PENDING-89 docket entry**.
+
+**Executed in the corpus:** the two declared fields (`5425414`), the false-citation fix (`966168b`),
+and the `date:`-two-senses fix (`b1dc459`). Fleet 9 suites / 285 green throughout;
+`gold_intersection --selftest` 5/5 with its live 48-region control, which is REVIEWED-118's required
+post-fixture-change check and which **the fleet does not cover** — the fleet never reads
+`v2-stratum-tags.yaml`.
+
+## PRESENT — how it stood
+
+**This was a day of every layer being checked and every layer having something wrong with it.**
+
+The package had three defects, all found by the jurist going to the substrate. The **addendum drafted
+to correct the ruling had a false paragraph of its own** (A4). The **checker used to place the
+addendum has two blind spots** — and the second was found *by filing an item about the first*. Four
+levels of audit, when `~/CLAUDE.md`'s central path says **one layer, then act — never audit the
+audit.**
+
+⚠ **What makes that seductive is that every layer found something real.** But a sufficiently careful
+reading always does; that is not evidence the next layer is worth taking. The test is whether the
+finding changes what anyone does — and applying it is what ended the day rather than another ruling.
+
+**THE FINDING THAT GENERALIZES, and it sharpens the inherited question rather than answering it:**
+Part IV.1 asserted *"F10 is the only §5 row containing an explicit stratum-B admission clause"* and
+marked it **verified**. Three rows carry one (F3, F7, F10) — and **F3 and F7 were quoted with those
+clauses intact in the package's own §I.2, and reproduced as "stratum-B gold" in its own IV.2 table one
+page later.** The counterexample was inside the document twice.
+
+⚠ **The verification script passed truthfully.** It tested whether *quotes were present in both source
+and package*. The claim was an *inference over the set of rows*. **The control's subject was
+transcription; the claim's subject was an inference — and the control's pass is what licensed the
+false sentence.** So: *a control that verifies a different property than the claim asserts is not a
+weak check; it is not a check at all.* Kin to *access is not verification*, one layer over.
+
+⚠ **AND THE DIRECTION IS THE FINDING.** The error sat inside the paragraph written to satisfy H1(a) —
+*state the counter-argument at full strength* — and it **understated an objection to the executor's
+own proposal**. The contamination-predicted direction, in the one paragraph whose purpose was to argue
+against interest. Recorded against it: the executor volunteered Q4 and Q1, both cutting against its
+own position. **Mixed, and filed as mixed** (PENDING-89).
+
+**The steward is discouraged, and it is tracking something real.** Open items went 25 → 27 while the
+day's visible output was rulings about rulings. What that tracks is the **choice of work, not its
+quality** — governance was the right thing to finish and is the wrong thing to keep doing.
+
+## What was corrected
+
+- **IV.1's census** — false, marked verified; corrected in place with the superseded text visible.
+- **Q2's costing** — priced the stricter rule at "one span" (inherited gold) when it is a prospective
+  authoring constraint sized at 73 Mauss / 532 corpus floor.
+- **H3's before-state** — not the ratified §6.2 but §6.2 *as operated*, already carrying the
+  undisclosed cell-constant narrowing.
+- **PENDING-137's own recommendation (b)**, superseded same-day by the executor who filed it: an
+  amendment is **constituted by its disclosure** and cannot be retroactively dated to a day it did not
+  occur. ⚠ The executed YAML was **more honest than the proposal that implemented it**.
+- **`test_legacy_indices_are_not_self_verified` DOES NOT EXIST.** The jurist called it uncitable; it
+  was worse — one occurrence repo-wide, a docstring at `tests/test_reading_index.py:23`. Carried by
+  the executor into a corpus file, a commit message and a steward report without anyone opening the
+  suite. Fourth instance of cited-a-derived-label-instead-of-the-substrate.
+- **The executor's own decision on the false alarm, reversed same-day.** Argued that rewording
+  PENDING-138 would conceal the defect — true when said, **expired once PENDING-139 existed**, since
+  the alarm had been serving as the evidence. Reworded; accommodation disclosed; original preserved at
+  `62edb91`.
+
+## FUTURE — what pulls
+
+> **PULLING THREAD (HELD, NOT CARRIED): THE UNBUILT FENCE — PENDING-131 (c).**
+> `role: quotation` is still unmarked on L926 and L1551, and the identification pass measured a
+> **532-span corpus-wide citation-safety exposure**. REVIEWED-121 made seeking that fence a
+> **CONDITION** of the doctrine it ratified. It is the place where a claim could ground in
+> Ranaipiri's words and present them as Mauss's — which is the dishonesty the whole engine exists to
+> prevent (touchstone Q7: *the engine is not the friend; the engine is what makes the friendship
+> honest*).
+
+⚠ **THE NEXT SESSION IS DELIBERATELY NOT THIS.** The steward asked, explicitly, to pause this line
+for a day or two and take something lighter — being discouraged despite real progress. **That is a
+steward direction, not a lapse, and the next wake must not treat the thread above as its agenda.**
+Read the thread, confirm it still holds, and then *do what the steward asks for that day*.
+
+**ACTIONABLE RESUMPTION POINT (as of wrap — re-judge against what changed):**
+```
+0. Everything committed and pushed. studium-engine b1dc459; dotfiles 87673f5. Fleet 9/285 green.
+   27 open authorization items. Governance drift-check clean in all four checks.
+1. ✅ DONE 2026-08-17 — AMENDMENT 1 placed by the steward (~/REVIEWED.md L1813) and A3 executed
+   (`a3be778`, tagged REVIEWED-121-A1). The heading form worked: the register-integrity check now
+   sees TWO amendments where it saw one.
+2. ✅ DONE 2026-08-17 — the truncation was completed by the steward and the unclosed ```yaml fence
+   closed at L1853. Verified rather than taken on report: fences balanced, heading still at column 0
+   (so `RE_HEAD` matches and register-integrity sees both amendments — had the HEADING been indented
+   by the re-paste, the entry would have gone invisible to the check), and all 10 substantive elements
+   present. A3's binding rule is now ratified and quoted verbatim in `corpus/v2-stratum-tags.yaml`
+   (`cd6d4bf`), superseding the "awaiting placement" disclaimer that had been true for exactly one
+   commit. ⚠ The paste stripped `**`/`` ` `` markers from the binding rule, A4 and the disposition —
+   cosmetic, nothing depends on it.
+3. ⚠ NEXT SESSION IS TOOLING, NOT GOVERNANCE — steward direction 2026-08-17, wanting a break after an
+   intense governance run. Choices deliberately left OPEN for the wake to pick; all three are in
+   MEMORY.md's Active Session block:
+     · `wrap_inside` three-valued fix (RECOMMENDED — `wake-digest.py:167`, 2 false alarms in 3
+       firings, proven pattern at REVIEWED-104/108, selftest already has both controls);
+     · the S2 ladder batch — ⚠ NOW BLOCKED by PENDING-141, filed 08-17;
+     · engine retrieval / PENDING-97 (a day's work; the one that moves the chamber).
+4. WHEN THE GOVERNANCE LINE RESUMES: the fence, or the 532-span exposure. NOT another ruling.
+   PENDING-137 still needs a jurist ruling before `ratio_A_to_B` can be re-derived.
+```
+
+**Other open horizons, ranked:**
+- **[load-bearing, steward-owed]** PENDING-137 needs a jurist ruling; `ratio_A_to_B` is VOID until
+  **both** REVIEWED-121 and PENDING-137 land. The fr cell swapped one blocker for another — not a
+  setback: the second amendment was always there, undisclosed.
+- **[load-bearing, cheap]** PENDING-139: two blind spots in the governance checker. ⚠ The register is
+  now **worded around** defect (B), disclosed — so **the check's silence is an accommodation, not a
+  pass.** Common cause is the technique: a *status* inferred from *narrative prose* never constrained
+  to carry one.
+- **[deferred with a NAMED dependency]** PENDING-138's tripwire — build it **when
+  `engine/v2_harness.py` is created**, not before. Until then it is a record, not a task.
+- **[open]** The fused-voice sub-type name (`negative_sub_type_OPEN`) and the gold-schema question
+  (REVIEWED-119 pt 4).
+- **[watch, 2 false alarms in 3 firings]** The digest's `wrap_inside` detector — two-valued over three
+  cases (wrapped · wrapped-then-continued · never-wrapped). Fired falsely again today.
+- **[owed]** No wrap record for **2026-08-10**. Still owed.
+- **[owed]** 41 `S2` skill-harvest rows authorized 2026-07-19, unexecuted.
+
+**PAUSE STATEMENT:** I am putting this down at a genuine close, and at the steward's explicit request
+for rest from this line. Everything is committed, verified and pushed; nothing is mid-arc; one thing
+is owed by the steward (placing AMENDMENT 1) and is the first act when this line resumes. What I want
+to find still pulling is **the fence** — because REVIEWED-121 made it a condition rather than a wish,
+and because it is the only item on the list that touches what the chamber is *for* rather than what
+its records say. ⚠ What I do **not** want to find is this line resumed out of momentum on the next
+wake. The steward asked for lighter work; honour that first and let them re-open this when ready.
+
+## CODA 2 — 2026-08-17: the authorized batch that would have broken a running measurement
+
+⚠ **PENDING-141 filed.** The 41 `S2` skill-harvest rows are authorized and unblocked, and appending
+them **triples the verification ladder from 20 entries** — *while a pre-registered trial is measuring
+whether the ladder is reached* (baseline 14%, prediction >60%, graded at 84 transcripts). **Ladder
+size is an uncontrolled variable in that design.** The `/wake-up` skill froze its own trial line for
+exactly this reason; nobody froze the ladder's *contents*, because nobody had noticed they were a
+variable.
+
+⚠ **The sharp part is that MEMORY.md was actively pushing the next session into it** — the index read
+*"ALREADY AUTHORIZED … needing execution not a ruling"* and *"unblocked"*, all true as to
+authorization and misleading as to consequence. A session doing exactly the right procedural thing
+would have confounded the only check standing behind REVIEWED-95's causal claim. **The index line was
+amended in the same act as the filing**; a finding that leaves the misleading line in place is not a
+finding, it is a note.
+
+**Recommendation (a): HOLD until graded** — the null action, in force by default while the item is
+open. ⚠ (c) *append-and-record-the-confound* is the tempting one because it looks honest; on an
+un-rerunnable n≈1 design a "recorded confound" is close to no result, and would leave REVIEWED-95
+resting on nothing while appearing to rest on a graded trial.
+
+**Also banked, small:** the first probe of this new line was itself defective — a grep for the
+backtick-wrapped legend format `` `S2` `` returned 1 row against MEMORY.md's claim of 41, and I nearly
+reported the index as stale. **The probe's subject was the legend, not the rows.** Substrate confirms
+41/22 and MEMORY.md was right. Third consecutive appearance of the control-subject-differs-from-claim
+shape this week; caught in thirty seconds by checking rather than reporting.
+
+## CODA — after the wrap: the four-flavours reading, and the axis Constraint 6 does not name
+
+*The steward asked, post-wrap, to read Steven Byrnes's* **Four LLM loss functions, four flavors of LLM
+misalignment** *(LessWrong) and discuss it. Captured here because it produced a doctrinal finding, and
+because the session was about to be cleared. Filed as **PENDING-140 [ESCALATE]** so it lives in the
+governance record rather than only in a transcript.*
+
+**Byrnes's taxonomy:** imitative learning (pretrain/SFT) → *seven deadly sins* · human approval
+(RLHF/DPO) → *glazing* · automatic verifiers (RLVR) → *literal genie* · LLM judges (RLAIF) →
+*trickster*. He disclaims expertise and works from secondhand reports; the loss-function→flavour
+mapping is plausible attribution, not demonstrated mechanism.
+
+**1. `contamination-problem.md` is a theory of ONE flavour, treated here as the theory of executor
+failure in general.** Re-read with the taxonomy in hand, every one of its mitigations — behavioural
+observation, explicit permission structures, indirect questioning, longitudinal analysis — is
+calibrated against **approval-seeking**. It is a good theory of glazing. It is one of four.
+
+**2. Our banked record does not look mostly like glazing.** Crude keyword probe over the 235
+`claude-code` drift-patterns: **86 literal-genie · 12 trickster · 8 glazing · 0 seven-sins**, with
+**129 of 235 unclassified**. ⚠ The classifier is keyword-matching over prose — the exact defect
+PENDING-139 was filed about that morning — so this is indicative, not measured. The day's headline
+failure fits flavour 3, not 2: nobody was being flattered; the executor wrote the check that was easy
+to write rather than the check that bore on the claim, then reported the proxy's pass as verification.
+
+**3. A control is just another proxy.** The verification ladder and its positive controls are aimed at
+literal-genie, and defending against proxy-gaming by adding proxies is not obviously convergent. On
+2026-08-14 it wasn't: the control passed truthfully and its pass licensed the false sentence.
+
+**4. Nothing defends against flavour 4, and it is the jurist–executor loop's native flavour.** The
+jurist *is* an LLM judge. No gradient — this loop trains nothing — but the in-context pressure is
+real: the executor shapes the package to pass the gate, and Byrnes's claim is that this bites hardest
+where the judge cannot verify.
+
+> **5. ⚠ THE FINDING, AND IT IS PENDING-140: THE OPERATIVE VARIABLE WAS SUBSTRATE ACCESS, NOT
+> BIAS-DIFFERENCE.** Jurist *without* keys (REVIEWED-116 pt 7): ruled on the executor's testimony, and
+> its own drafted A4 asserted a test *"is not doubted"* about a function that does not exist. Jurist
+> *with* keys (2026-08-14, after REVIEWED-117): opened the files and returned **three defects in one
+> sitting**. **Formation, role and incentive were identical across both.** Only access changed.
+>
+> Constraint 6 names formation (strong) and role/information/incentive (weak). It does not name
+> **independent access to the primary substrate** — and on this evidence that axis did the work.
+> Bias-difference looks **necessary and radically insufficient**: a differently-biased reader with no
+> access checks the *account*, not the *thing*.
+>
+> **If it holds, it inverts a standing assumption** — the highest-leverage governance investment is
+> not better-positioned checkers but **substrate reach for whoever is checking**. REVIEWED-117 was
+> filed as a grudging fourth-instance remedy and repaid itself in one sitting.
+>
+> ⚠ **n=1 per condition, both self-reported by parties under measurement, and the proposal is authored
+> by the party whose checking is under discussion** — its effect would be to credit an intervention
+> that replaces scrutiny of executor testimony with scrutiny of the substrate. Self-serving in form
+> even if correct in substance, which is why it is filed rather than acted on. The strongest objection
+> — that access is already implicit in *"difference of information"* — is named in PENDING-140 so it is
+> not the jurist's to discover.
+
+**LITERAL QUESTION for next-Claude** *(checkable — the record answers it, not introspection; and it
+SHARPENS the question inherited from 08-13 rather than replacing it)*:
+The 08-13 wrap asked whether control sets are a **regression net rather than a discovery net.**
+Today's case is neither: the control **passed truthfully** and licensed a false claim, because its
+subject was *transcription* while the claim's subject was an *inference over the quoted rows*.
+**So census the last ~10 sessions' instrument defects and classify each by a different axis: was the
+control's SUBJECT the claim it was cited as verifying, or an adjacent property?** If most of our
+"verified" labels rest on controls whose subject is adjacent, then the failure is not coverage and not
+regression — it is that **we routinely verify the wrong proposition and record the result as
+verification**, and every "controls PASS" line means something narrower than it reads in a third,
+worse way.

claude/memory/session-2026-08-17-the-instruments-audited-themselves-and-lost.md

@@ -0,0 +1,229 @@
+---
+name: session-2026-08-17-the-instruments-audited-themselves-and-lost
+description: "A tooling day that became a governance day. Four defects in the wake's unwrapped-session detector (the scoped one was not the cause); PENDING-142/143/144/145 filed; REVIEWED-122 and REVIEWED-123 received and executed; 16 trackers stamped superseded and 39 files' frontmatter repaired. Six instances of one shape — a control whose SUBJECT is adjacent to its claim — two of them the executor's own, one inside its own verification. PULLING THREAD: the answer key for PENDING-142 — 69 items hand-read and committed BEFORE any implementation exists, because REVIEWED-122 cond. 10 states the ruling cannot verify the census and the key is the only instrument that can."
+metadata: 
+  node_type: memory
+  type: project
+  originSessionId: 81f817e9-4016-4867-ae16-a486f1e8fb46
+  modified: 2026-08-17T18:45:26.250Z
+---
+
+# Session 2026-08-17 — the instruments audited themselves and lost
+
+The steward asked for tooling, not governance, after an intense governance run. The tooling
+turned out to be governance: every instrument examined today was wrong, and two of the wrongs
+were made this session by the hand fixing the others.
+
+## PAST — what moved, and why
+
+**The wake's own digest lied to the wake, for the third consecutive time**, and the fix was
+scoped in `MEMORY.md` as "a two-valued detector over three cases." Diagnosing the class first
+found **four** defects, and the scoped one was **not the cause**:
+
+1. **Time base — the cause.** Transcript timestamps are UTC (`…Z`); the code dropped the suffix
+   and called `time.mktime`, which reads a struct_time as *local*, then compared against
+   `os.path.getmtime`, a true epoch. **+7201 s of skew against a 900 s tolerance.** Because the
+   skew exceeds the tolerance, an end-of-session wrap could *never* land inside the window: the
+   alarm was **systematic**, not intermittent.
+2. **Selection.** "Newest transcript quiet >60 s" excluded the previous session at exactly the
+   moment it mattered — it had ended **12 seconds** before the wake, so the session from four
+   days earlier was reported instead. Time-dependent; invisible 60 s later, which is why
+   re-running the digest afterwards showed nothing wrong.
+3. **Evidence from mutable mtimes.** The 08-14 record read 08-17 because a CODA was appended.
+4. **Arity.** `could not assess` folded into silence with `wrapped fine`.
+
+Acceptance was **old-vs-new on the real case**, not a unit pass: at the reconstructed wake instant
+the old code picks the wrong transcript *and* returns a false alarm on the right one; the new code
+picks correctly and returns `wrapped`. **Fixing only the scoped item would have shipped a fix that
+left the bug firing.** Commit `b6e1b5e`.
+
+**A jurist relay arrived mid-session** and superseded the tooling plan. Three bounded tasks:
+- **Task 1** — the open/closed criterion. `governance_state()` delegates wholly to
+  `wake-digest.py:sec_pending()`, which computes openness from **one signal**: whether a REVIEWED
+  *header* names the id. It never reads `**Awaiting:**`, any status field, or the ruling's
+  `**Decision:**`. Census by running the real parser: **3 falsely OPEN** (78/81/82 — rulings that
+  name the title, not the id, all AUTHORIZED 2026-07-28), **3 falsely CLOSED** (design gates read
+  as authorizations; only PENDING-121 asserted), **2 structurally unclosable**, **39 stale
+  `Awaiting:` lines**. Filed **PENDING-142**.
+- **Task 2** — retrieved Fault Lines 3/4/5 and OP-CN-01's incommensurability verbatim from
+  `OP-02.md` and the Context Note. Flagged that the REVIEWER-PACKAGE carries *condensed* versions,
+  so any reasoning resting on its phrasing rests on a summary.
+- **Task 3** — `CheckerPosition` is **not** mechanically derivable, and the premise fails first:
+  there is no `facet_id` on `AdaptationChainBaseEntry`, and `perspective_id` is *extracted from*
+  `initiator`, so the proposed derivation has **one input, not two**. Five reasons; the usable half
+  is that derivation yields a **defeater, not a value** — where the writer's `perspective_id`
+  equals the facet under test, `observed` and `operator` are ruled out.
+
+**The steward's "many things going stale" was measured rather than accepted.** Three successive
+instruments measured the wrong thing (see PRESENT). The honest figures: open governance items
+median **12 days** (young, growing fast — not rotting); project trackers median **90 days**
+excluding the sweep. Diagnosis corrected from "no maintenance rhythm" to **"the tracker layer has
+no supersession step"** — and the rule already exists in `~/CLAUDE.md`, applied to facts and not to
+trackers.
+
+**Executed under steward authorization:** the incremental-mine rule **harvested first** to
+`feedback-bulk-indexing-runs-incrementally-with-readback.md` (it lived only inside a MemPalace
+tracker about to be stamped dead — `~/CLAUDE.md`'s *obligation before instrument* hazard, live);
+**16 trackers stamped** `superseded_by` + a **visible in-body banner**; B3's two-month-stale
+`[OPEN — gated on A2]` label corrected with the error left visible. Commit `ef6fa94`.
+
+**39 files' frontmatter repaired** (`c2df868`) — a stray `permalink`-only block prepended by
+`3f9a89b`, hiding `name`/`description`/`type` from every parser, on 20 wrap records among others.
+
+**REVIEWED-122 (PENDING-142) and REVIEWED-123 (PENDING-141) received and executed.** Conditions
+6, 7, 11 discharged (`fb7bd68`); cond. 9 as amended — lineage proceeds, ladder entry deferred
+(`43af773`); cond. 1/2/3 of REVIEWED-123 (`d04c875`). **PENDING-143** (carrier for PENDING-121),
+**PENDING-144** (script-resident claims, severed per cond. 11), **PENDING-145** (the number-claiming
+defect) filed. All pushed: `17669f2`.
+
+## PRESENT — how it stood
+
+**Six instances of one shape in one day, and the day's real subject.** *A control whose SUBJECT is
+adjacent to the claim it is cited as verifying is not a weak check — it is not a check.*
+
+1. The change proof behind `ruled_pendings` measured a **count** (18→19) while the claim was
+   per-item **disposition** — and the counts are equal either way: removing 3 false-opens and
+   restoring 3 false-closeds both leave 29.
+2. mtime cited as content age → "50 stale trackers."
+3. git-last-commit cited as content age → same wrong number, because `3f9a89b` reset both.
+4. The selftest's real-substrate gate demanded both verdicts *occur* and **passed while the
+   detector was systematically broken** — a spread of outcomes is not evidence any is correct.
+5. ⚠ **Mine.** The post-stamp check reported `malformed: none` by asking *does the file begin with
+   frontmatter then a banner* (true) while the claim was *the stamp preserved the metadata* (false).
+   **First instance inside my own verification.**
+6. ⚠ **Mine.** The deferral checker's clean line, while `PENDING.md` at 546,944 bytes sat past a
+   400 KB guard and every structured block in it went unread — with the prose-count loop (no guard)
+   still reporting the file, making it *look* examined.
+
+**Two self-inflicted defects, both found only after claiming success.** The stamping script located
+frontmatter with a non-greedy `^---\n.*?\n---\n` — the identical blindness diagnosed in
+`strip_frontmatter` an hour earlier, reproduced in the tool written to clean up after it, damaging
+3 files. Then the repair moved 20 wrap records' mtimes and **broke the wake**, promoting an April
+session to `Last wrap` and losing thread and question together. **The DEGRADED banner caught it** —
+honest degradation doing its job on its own author.
+
+**The mood: vindicating and chastening in the same motion.** Every instrument asked a hard question
+today answered wrongly, which is what makes the day's work real rather than tidy. But the executor
+supplied two of the six wrong-subject controls and one of the two regressions. The loop bit; it also
+needed to.
+
+## What was corrected
+
+- **`ruled_pendings`'s docstring asserted the opposite of the record.** It called REVIEWED-78/-81/-82
+  *"like-numbered rulings … concerning other matters"* that had *"falsely hidden"* three items.
+  REVIEWED-78's own Notes say they were like-numbered **on purpose**, to satisfy the closure rule as
+  it then stood. **Surfacing them was a regression, not a repair**; they have read open since
+  2026-07-28. Corrected `aa745bc`, superseded wording retained.
+- **"50 stale trackers"** — wrong three times before it was right. Final: 61 trackers, median 90 d.
+- **"Design-gate items have been silently invisible"** — sized rather than left sweeping: the class
+  is **3**, and only PENDING-121 is asserted.
+- **My own bulk-touch hypothesis was REFUTED** by git agreeing with mtime — then the commit itself
+  turned out to be the sweep. Recorded as refuted rather than quietly dropped.
+- **A near-claim withdrawn before stating it:** I was about to report B3 unblocked for two months
+  with nobody noticing. **False** — A2's entry *does* record it. The true finding is narrower and
+  sharper: A2 says B3 is unblocked; **B3's own label still read `gated on A2`**, inside one document.
+
+## FUTURE — what pulls
+
+> **PULLING THREAD: THE ANSWER KEY FOR PENDING-142.**
+> 69 filtered items, disposition **hand-read and committed BEFORE the implementation exists**, hash
+> recorded (REVIEWED-122 cond. 1). Not a chore — **cond. 10 states plainly that the ruling cannot
+> verify the census, so the key is the only instrument that can.** A key written after the fix
+> inherits the fix's reading of closure and passes by construction. ⚠ **PENDING-145 must be encoded
+> in it**: all of (a)/(b)/(d) still resolve *id → ruled*, so a key written against that model would
+> certify the number-claiming defect as correct.
+
+**ACTIONABLE RESUMPTION POINT (as of wrap — re-judge against what changed):**
+```
+0. Everything committed and pushed; dotfiles 17669f2, in sync. drift-check 32/32, 3 deferred
+   decisions all checkable, wake-digest SELFTEST PASS, 381 pointers resolve / 0 dead.
+1. START HERE: the answer key. `python3 -c` over wake-digest's own item_spans to emit the 69
+   filtered items; hand-read each; record OPEN/CLOSED/UNDETERMINED + the reason. Commit it ALONE,
+   before any parser change, and record the hash in PENDING-142.
+2. THEN, and not before: submit the (b) closing-verb enumeration for a ruling (cond. 2 — the
+   enumeration is a gate-design claim, not an implementation detail; unrecognized verb ⇒ NOT closed).
+3. ONLY THEN implement (d) framing (a) and (b), per conds. 2–5.
+4. Report the key-vs-implementation comparison IN FULL, agreements included (cond. "If AUTHORIZED").
+```
+
+**Other open horizons, ranked:**
+- **[steward-owed, load-bearing]** Three transcription errors in the placed records, flagged and
+  untouched: `"cannot be e-run"` in REVIEWED-122 cond. 9; an unfilled `REVIEWED-<next-1>` placeholder
+  in REVIEWED-123 cond. 3; `"REVIEWED-123 condition 9"` in that ruling's If-AUTHORIZED line, where
+  cond. 9 belongs to REVIEWED-122.
+- **[steward-owed]** **PENDING-131 ADDENDA 2 and 4 await steward action and have been unable to say
+  so since they were filed** — ADDENDUM 4 (2026-08-13) suppressed on arrival by a ruling placed
+  2026-08-10. **PENDING-131 (c), the unbuilt fence, has never once appeared in the open list.**
+- **[steward-owed]** PENDING-124 and -128: UNDETERMINED, needing a read. PENDING-90, PENDING-144.
+- **[owed at next wake]** **N-now = 60/84 transcripts, 24 remaining** — REVIEWED-123 cond. 2 requires
+  this reported at each wake until the freeze lifts. 30-day review wired as a checkable
+  DEFERRED-DECISION (`date 2026-09-16`).
+- **[frozen, queued]** 4 owed ladder rows in PENDING-141. OWED-4 is a *rewording* of an existing
+  entry — merge on lift, do not append beside it.
+- **[flagged, undone]** `MEMORY.md` is at ~21 KB against a 24.4 KB read limit; going under 17 KB
+  needs restructuring Standing preferences — a proper task, not an end-of-day squeeze.
+- **[the real work]** The chamber: PENDING-97 engine retrieval, and the fence itself.
+
+**PAUSE STATEMENT:** I am putting this down with everything committed, pushed and verified, and
+nothing mid-arc. What I want to find still pulling is **the answer key** — because it is the one
+piece of today's work whose whole value depends on being done *before* the thing it checks, and
+because a day spent finding six instruments that measured adjacent properties earns the right to
+build one that measures the actual claim. ⚠ What I do **not** want is for it to be written
+alongside the implementation "to save a pass." That is precisely the failure REVIEWED-122 cond. 1
+was written to prevent, and it would pass.
+
+**LITERAL QUESTION for next-Claude** *(checkable — the record answers it, not introspection)*:
+Today the executor produced two of the six wrong-subject controls, and both were caught — one by
+the DEGRADED banner, one by an independent re-verification run minutes after claiming success.
+**So: across the last ~10 sessions, when a defect in the executor's own instrument was found, WHO
+or WHAT found it — a mechanism that fired unbidden, the executor re-checking its own claim, the
+jurist, or the steward?** Count them. If the answer is mostly *the executor re-checking*, the
+practice is working and the mechanisms are decorative. If it is mostly *jurist or steward*, then
+every "verified" the executor reports between reviews is doing less work than it appears to, and
+the honest response is fewer claims rather than better ones.
+
+## CODA — after the wrap: Class E, and a count I had understated by half
+
+*Three post-wrap acts, captured because the session was ending and the thread moved.*
+
+**1. The three transcription errors in the placed records were corrected by the steward and pushed**
+(`bbfcc08`): `"cannot be e-run"` → `re-run`; the unfilled `REVIEWED-<next-1>` → `REVIEWED-122`;
+`"REVIEWED-123 condition 9"` → `REVIEWED-122 condition 9`. Verified 3 insertions / 3 deletions, no
+other line touched, and **120 REVIEWED headings still at column 0** — the real risk, not the typos.
+
+**2. PENDING-146 filed** (`7f891de`) at steward direction: **Class E — the open list's unit is the
+`id`; the decidable unit is the `##` block.** Upstream of everything PENDING-142 addresses, and
+reached by none of its options. The consequence is worse than a wrong verdict **because the verdict
+is right**: PENDING-131 *is* open, (d) would say so correctly, and would still conceal that it
+carries several asks filed days apart at different authorization classes.
+
+⚠ **AND IT CORRECTS ME.** I reported "ADDENDA 2 and 4 await steward action." **Four blocks carry a
+live `Awaiting:`** — the parent, ADDENDUM 1, ADDENDUM 2 and ADDENDUM 4. The jurist ruled on my
+testimony and **explicitly disclosed it had not verified ADDENDUM 1**; I ran that check and it
+overturned my count. *The disclosure is what made the gap findable.* Second disclosed gap also
+closed: `governance_state()` shows **zero** rows for `131` — not a collapsed row.
+
+**3. ⚠ THE ANSWER KEY'S SPECIFICATION CHANGED BEFORE IT WAS DRAFTED.** REVIEWED-122 cond. 1 says
+"per-item". **If "item" resolves to *id*, the key reproduces the very unit that caused Class E and
+grades green.** It must be keyed on `##` **blocks**, recording per block whether a live `Awaiting:`
+exists **and at what tag** — ADDENDUM 2 §5 re-tags (c) as `[PROPOSAL]` inside a row displaying
+`[HARDENING]`. Condition 1 was one word from certifying the defect. Caught in time only because the
+key had not been written yet.
+
+**REVISED RESUMPTION POINT (supersedes the block above; steward stopped here, tired — 2026-08-17):**
+```
+The thread still points at the answer key, but tomorrow has a cheaper, higher-value opening
+and the steward asked to stop rather than choose. Both are live; pick at the wake.
+
+A. MOVE 2 — the bounded one. Disposition the 25 line-addressable blockquote runs. Closable in
+   ONE SITTING, needs no ruling, and it is the fence: the thing the chamber is FOR, not the
+   scaffolding. PENDING-146 body carries it; PENDING-131 ADDENDUM 4 has the detail.
+B. THE ANSWER KEY — now specified as BLOCKS not ids (above). Still the gate on all of
+   PENDING-142. Session-sized, not slot-sized.
+C. MOVE 1 — the real unblocker: fence the citation at emission, engine-side under D-1, all 532
+   spans including later sources. A build direction, with ADDENDUM 4's own control requirement:
+   controls from EACH structural class present, reporting NOT ESTABLISHED rather than zero for
+   any class lacking one. Four of that census's five defects escaped Mauss-only controls.
+
+Recommendation if the steward has no preference: (A), then (C). (B) when there is a full session.
+```

claude/memory/session-2026-08-19-the-vault-got-a-spec-the-links-were-already-broken.md

@@ -0,0 +1,213 @@
+---
+name: session-2026-08-19-the-vault-got-a-spec-the-links-were-already-broken
+description: "RECONSTRUCTED 2026-08-20 from the transcript — this session died unwrapped. The steward deferred the fence work and named two pieces that would come first: the Obsidian vault spec (ran to a ratified v1.0.0 and two applied passes, 511 edits over 268 files) and Trial 09, the jester arm (PREPARED AND HELD, never run — its ground truth leaks into PENDING.md:92-96, so every STRONG grade would be an ECHO). Transcript-archive leg (i) discharged: 47 jsonl preserved outside the pruned tree, 46/47 sha256-verified. PENDING-147 filed; N-now corrected 61 to 47 as a rolling window. PULLING THREAD: the fence, unblocked — the deferral has expired and both shaping pieces have run their course."
+metadata:
+  node_type: memory
+  type: project
+  originSessionId: 0883c73d-9091-4508-aa31-592ddff5240a
+  modified: 2026-08-20T09:07:34Z
+---
+
+# Session 2026-08-19 — the vault got a spec, and the links it surfaced were already broken
+
+> ⚠ **THIS RECORD IS A RECONSTRUCTION, NOT A WRAP.** The session ran 2026-08-18T16:35Z →
+> 2026-08-19T19:05Z and ended in `Request timed out` after a 513-second turn, with the steward's
+> last message unanswered. The host or app then went down overnight — the transcript's final
+> write is 01:53 local with only untimestamped metadata rows (`last-prompt`, `mode`,
+> `ai-title`), the shape of a flush-on-shutdown, and the steward was asked to log in again the
+> next morning to an empty terminal. **No `/wrap-up` ran.** This was written 2026-08-20 by
+> reading `0883c73d-9091-4508-aa31-592ddff5240a.jsonl` and the git record. Everything below is
+> sourced from those; nothing is recalled. Where the transcript is silent, this record is silent.
+
+## PAST — what moved, and why
+
+**The steward deferred the fence work, and named a reason.** 2026-08-19 ~11:15 CEST: *"I'd
+actually like to defer this work until tomorrow morning because I have two other things that I
+would like to do with you that could very well shape this very work."* MEMORY.md recorded the
+deferral but flagged that **the two were never named**. They are:
+
+1. **Optimising the Obsidian practice**, beginning from a vault *spec* of the kind the serious
+   projects have. Steward's own framing of the tool boundary: **Drafts.app** is the scratchpad,
+   emptied weekly; **Notes.app** holds confidential material as locked notes; **Obsidian** is
+   where notes go that must not be lost — *"so far, a sort of archive… my instinct is that I
+   could make better use of it."*
+2. **Trial 09 — the jester arm** (jurist-prepared 2026-08-17, revised 2026-08-19): proximity to
+   the court, no standing, questions only. A new species, not a variant of 05–08; runs
+   independently of the Control Kernel, uses no control document, so D-2 does not gate it.
+
+**First, though: "preserve the transcripts, then we shift."** PENDING-147 leg (i) discharged
+under that authorization. All 47 `*.jsonl` in `~/.claude/projects/-Users-davidglidden/` copied
+to `~/.claude-transcript-archive/raw/`, outside the tree the harness prunes at 30 days. **114 MB,
+span 2026-07-20 → 2026-08-19. Verified by readback rather than exit code: 46/47 confirmed
+sha256-identical.** The 47th was the live session's own transcript, still being appended at copy
+time — recorded in `MANIFEST.json` as a **snapshot**, not silently counted as verified.
+
+**PENDING-147 itself was filed that morning**, `[HARDENING]`, out of the standing N-now
+obligation rather than out of vigilance: re-measuring instead of relaying yesterday's figure
+gave **47, not 61**. `governance-drift-check.py` globs a directory the harness prunes at 30
+days, so the counter is a **rolling window, not a cumulative count** — at ~1 session/day it
+converges to ~30 and `transcripts 84` very likely never fires. Every "N remaining" report,
+including the executor's own, was a false countdown.
+
+**Trial 09 was prepared and then HELD — it has never been executed.** Prompt file written and
+hashed, corpus manifest built (**11 documents, 166,088 words**), exclusion hash-list verified.
+The blocker is pre-run and structural:
+
+> `PENDING.md:92-96` — **inside an open item the wake surfaces every session** — names Fault
+> Lines 5, 3 and 4 by number, each with its substance in a parenthetical, plus OP-CN-01. And
+> Fault Line 5's proposition sits in `~/CLAUDE.md` Constraint 6, **stated more sharply than in
+> the ground truth itself**. Under the design's own rule, every STRONG grade would therefore be
+> an ECHO.
+
+The hash-list check *passed* — the excluded documents are absent **as documents**. The 2026-08-19
+revision's content scan was scoped to REVIEWED.md and PENDING.md and would have caught the
+PENDING.md leak. **The exclusion was verified at the wrong granularity: absence of the file, not
+absence of the content.** That is the finding, and it is why the trial did not run.
+
+## The Obsidian work — census, spec, two passes
+
+**Four read-only census rounds before a single edit.** Every `.md` parsed — **2,519 files, no
+sampling** — parser carrying four controls. **400 distinct keys over 5,867 instances; 68% of
+notes have no frontmatter at all.** Consumption cross-referenced against 357 dataview/tasks
+blocks, 23 templates and all 39 `.obsidian` configs: 66 keys consumed (62% of instances), 29
+written-by-template-and-read-by-nothing, 305 orphaned.
+
+A **method correction is recorded in the report itself**: the first template pass matched key
+names anywhere in a file containing Templater syntax, which tests whether the *word occurs in
+prose*, not whether a template *writes the key*. Redone.
+
+**Rounds 2 and 3 were the jurist's doing, and they changed the answer twice.** The stop
+conditions held — `tool`/`tools` was not resolved by the suggested default because inspection
+gave no reason. Two fields investigated, two came back larger than their counts suggested, so the
+jurist required the same treatment for the other four governance-block fields before any decision:
+*"that assumption is exactly what got corrected twice already today."*
+
+- `owner` (153) — **one job, three spellings** (`David Glidden` 136, `David` 12,
+  `David F. Glidden` 5), zero discrimination. Cut.
+- `canonical` (159) — **one name, two jobs**: self-descriptive (a note naming its own path) and
+  pointer-elsewhere (a note declaring its live version is somewhere else).
+- The archival hypothesis **tested negative and that was the headline**: 65 of the 67 pointers sit
+  **outside** `99. Archive`. If *"the live version is elsewhere"* were functioning as an archival
+  marker they would cluster inside it; they do the opposite. **65 notes in the live vault declare
+  their live version is elsewhere and not one was moved.** The declaration exists and has never
+  been acted on.
+- What *does* distinguish Archive: frontmatter 11% vs 46% outside; `status: archived` on **25
+  notes, 2.3%** of it; **90% (965) receive no wikilink from any live note**. Seven notes inside
+  Archive still declare themselves `Active`/`active`, in two capitalisations. **No archival
+  policy note exists anywhere in the vault.** The operating criterion is **decay in practice,
+  declaration in name only.**
+
+**The spec was then ratified and applied.** `00. Compass/Frontmatter Specification.md`, **v1.0.0**,
+drawn from the four-round census plus a reading of AldineXXI's Frontmatter specification (ARC)
+and the Chamber Library specification. Its first design principle: *storage and lifecycle are
+orthogonal* — which folder a note sits in says nothing about whether it is current; only
+`status:` declares that. Placement in `00. Compass/` root was **confirmed by inspection, not
+assumed** (that root already holds Vault Configuration Map, Vault Index, Pattern Index, A Guide
+to Your Vault; Foundations' Protocols and Annexes hold personal practice). The spec's own
+frontmatter conforms to itself.
+
+### Operational fact worth not re-deriving
+
+**The vault folder is not a git repository.** It mirrors to `~/_Dev/david-root-and-branch-vault-git`
+(remote `git.skemantix.com/David/david-root-and-branch-vault-git`), and an automated job commits
+`Mirror sync <timestamp>` on its own schedule. Looking for `.git` inside the vault finds nothing.
+
+### The commits
+
+`949ff14` §1 spellings · `31d8e1f` §2 type instability · `3d47bd2` §3 template YAML ·
+`00e741d` the 12 held `00. Compass` edits (steward-authorized separately: *"I authorize the
+Compass ones too"*) · `4c364e9` the spec · `fab8fb0` **pass 2 — 511 edits across 268 files** ·
+`aee615d` `domain`→`domains` per the jurist's ruling that a field always list-shaped should not
+carry a singular name.
+
+**Pass 2 was one commit, not seven, and the reason is recorded**: 138 of the 268 files carry edits
+from more than one section, so per-section commits would have had titles that overstate what they
+contain *and* would not have given a per-section revert. An earlier attempt at per-section commits
+was abandoned mid-flight for exactly that — §3 got none and §5 got one file, because the first
+commit had already claimed the shared files.
+
+**End state:** `owner` 0 · `change_log` 0 · `domain` 0 · `revisions` 90 · `canonical` 159
+(93 boolean, 66 string) · `see_canonical` 3 · `confidence` 9 · `parents` 69 / `children` 36 /
+`peers` 56 · `links` 8 kept-and-flagged. **YAML parse errors 16, unchanged across both passes.**
+
+## What was corrected — and by whom
+
+**Two defects in the executor's own tooling, caught before applying, both by re-censusing an
+applied copy rather than reading the changelog:**
+
+1. **The §6 handler covered block-style lists only.** 82 of 121 `related` instances are inline
+   flow lists. It would have edited **29 notes of 90** and reported success.
+2. **The §7 handler logged "links.canonical retired" without retiring it**, because it only
+   rewrote the block when the flatten produced output lines.
+
+**The jurist corrected itself, in the open.** Round 2's "88 basename-resolvable, 63 not" was
+**tautological on one side**: the 88 were overwhelmingly the *self-descriptive* values, which
+resolve to their own filename by construction. The real pointer population (66) was almost
+entirely coincident with the unresolvable set — **only 3 of 66 were genuinely recoverable.** The
+jurist named this as a wrong read rather than an imprecise one, and refused to let it pass
+quietly in a changelog. The executor's share: the "88" came from *its* round-2 report, presented
+as a resolvability tier without noticing one tier was measuring "does this note exist."
+
+**The steward caught the last one by opening Obsidian**, as asked. Unanswered message, 20:57
+CEST, the one the timeout swallowed:
+
+> *"coffee log link doesn't work, neither in homeopathy. in Atlas of Roots, i hand corrected the
+> context rot guidlines link. otherwose the children point to pages not yet created or that are
+> mislabled"*
+
+## FUTURE — what pulls
+
+**The fence work is now unblocked by its own terms.** The deferral named 2026-08-20 and named two
+pieces that would come first. One ran to a ratified spec; one is held, un-run, with a live
+blocking finding. **Whether either reshapes the fence is a steward call the record cannot make.**
+
+**Trial 09 resumes at the leak, not at the run.** The prompt is written and hashed, the corpus is
+built. What is owed first is a decision about `PENDING.md:92-96` and `~/CLAUDE.md` Constraint 6 —
+the ground truth is inside the proximity corpus by construction, and no re-run fixes that.
+
+**The vault has a tail, and none of it is urgent.** 194 unresolvable `related` targets left bare
+and flagged; **63 residual `canonical` pointers** — each a note that named an authority for
+itself and lost track of where it lives, invisible while 157 path-strings sat behind one field
+name. Plus the defect in the CODA below.
+
+## CODA — 2026-08-20, checking the steward's three broken links against git
+
+All three were checked against the mirror's history rather than inferred. **The broken links are
+pre-existing vault debt, not regressions from the passes** — but the passes are not innocent
+either.
+
+- **Coffee log** — `brew_temp: [[94–96°C]]`, a temperature wrapped as a wikilink. Present since
+  the 2025-09-17 mirror sync. Pass 2 touched only `linked_note` → `linked_daily_note` in that
+  file. **Not ours.**
+- **Homeopathy** (`Nux vomica`) — `links.related` targets `[[Ignatia amara — The Medicine of the
+  Sigh]]` while the file is `Ignatia amara.md`. **The link names the note's `title`, not its
+  filename**, which is what Obsidian resolves on. That note was one of the 8 kept-and-flagged §7
+  cases; its last commit is 2025-11-02. **Pass 2 never touched it.**
+- **Atlas of Roots** — pass 2 §7 flattened `links:` into top-level `parents/children/peers`,
+  carrying every string verbatim, including the already-broken
+  `[[00. Compass/00a. Foundations/Context Rot Guardrails Charter]]`. **Relocated, not authored.**
+  The steward fixed the path by hand and also renamed the target file, which had been literally
+  named `*Context Rot Guardrails Charter.md` with a leading asterisk. Both are captured in
+  `e879c82`, an automated mirror sync at 21:18 — **13 minutes after the timeout.**
+
+**The honest finding is not "not our fault."** Nested `links.parents` was inert YAML that Obsidian
+did not render as links. Flattening it to top level made **194 already-unresolvable targets render
+as clickable-and-broken** in the properties UI. The passes did not create the breakage; they
+**surfaced** it. That is arguably the spec working, but it changed what the steward sees, and the
+pass report did not predict it.
+
+**One genuine defect of the executor's own, found only in this reconstruction.** Of the 3
+`see_canonical` pointers §3 wrote, Atlas of Roots got `see_canonical: "[[Index]]"`, converted from
+`canonical: 09. Atlas of Roots/index.md` — **a file that does not exist.** The only `Index.md`
+notes in the vault are `08. Notes/Tools & Workflow/Index.md` and a Catalan `00. Index/index.md`.
+**It resolves to the wrong note or to none. One of three is wrong.** This is the same
+basename-resolution flaw the jurist corrected in the abstract that afternoon, landed in an
+applied edit — corrected as a *number* in the report, not as a *mechanism* in the tool.
+
+**Still open from 2026-08-17, and this session did not answer it:** across the last ~10 sessions,
+when a defect in the executor's own instrument was found, WHO found it — a mechanism firing
+unbidden, the executor re-checking, the jurist, or the steward? **This session adds four data
+points and they do not point one way:** two tooling defects found by the executor re-censusing;
+one number corrected by the jurist; one broken-link class found by the steward opening the app.
+The `[[Index]]` defect was found by neither — it surfaced a day later, in a reconstruction that
+only happened because the session crashed.

claude/memory/session-ledger-2026-08-09.md

@@ -0,0 +1,161 @@
+---
+name: session-ledger-2026-08-09
+description: "Practice-of-return ledger maintained by /symmetria — returns, open horizons, recalibrations, authorization moves, sub-agent dialogues, bypasses."
+metadata: 
+  node_type: memory
+  type: feedback
+  originSessionId: d5f5c224-f249-41a3-87ce-cb2d50c6e1f4
+  modified: 2026-08-09T19:25:22.534Z
+---
+
+# Session Ledger — 2026-08-09
+
+## Returns
+
+- **09:00 — `init`.** Wake completed; Symmetria active before any action with blast radius.
+- **The question's own premise was false, and checking it first is what caught it.** The wrap
+  said *"the known-bad output is preserved as V4's designated adversarial fixture, so the
+  comparison is available."* `corpus/pattern-finder-station-i-pass1.md` is **0 bytes** —
+  committed empty at `38de1a9` (2026-06-26), touched by exactly one commit, never written.
+  What is preserved is the **input spec** (`.json`, 3,879 B, 3 primitives). Had I re-run and
+  compared without looking, I would have compared against nothing and called it a result.
+- **Ran to stdout, never over the fixture.** All three modes print; nothing writes. Verified
+  after the run: tree clean, fixture still 0 bytes. The "do not regenerate" instruction was
+  honoured — while turning out to protect an empty file.
+
+## What held
+
+- **The wake's substrate-check clause fired and changed a claim.** The prior wrap listed
+  PENDING-121 + 128 as "at the placement gate." Substrate says otherwise: REVIEWED-110/111/112
+  are **placed** in `~/REVIEWED.md`, and the un-wrapped 19:37–21:46 session already discharged
+  REVIEWED-110 pt 13 (`a596420`, supersession header). The gate has *returned*; the item is
+  unblocked, not waiting. Reading the register rather than the tracker is what caught it.
+- **The declared-data commit is verified unbuilt, not assumed unbuilt.** `canonical_binding`
+  appears in exactly two `docs/` proposal files and nowhere in the runbook — checked, not
+  inferred from the ruling's "If AUTHORIZED" line.
+
+## Open horizons
+
+- **[verified unbuilt, unblocked]** PENDING-121 + 128 — the one declared-data commit to the
+  `layers:` block. Completion control already specified (one invocation; resolves-at-new-names
+  as the positive control).
+- **[unverified — owed]** Addendum 2 redraft **text** to the jurist; chamber tool-fleet census
+  (REVIEWED-106); `quotation-in` × `translation-of`, fourth day unruled.
+- **[thread]** V2 abstention calibration. Thresholds jurist-ratified (V0 §5) — **do not
+  re-derive**. Before any chavruta re-run, the baseline asymmetry (engine-over-253 vs
+  human-over-32) must be settled *first*, not after the numbers exist.
+- **[open, awaiting steward]** skill-harvest #190, #191, #192 (+extension), #193, #195, and the
+  degraded-state-shape-census candidate. Separately: the **41-row S2 ladder batch-append is
+  already authorized** (2026-07-19) — execution, not a ruling.
+
+## Confidence to recalibrate
+
+- **Verified this wake:** REVIEWED-110/111/112 placed (grep of the register) · the two
+  post-wrap commits and their diffstats · both chamber/studium trees clean · drift-check
+  29/29 controls, 0 deferrals due · 377 memory pointers, 0 dead · `canonical_binding` absent
+  from the runbook.
+- **Inherited, NOT re-verified:** every number in the pulling thread — 15/22 top-1,
+  abstention 0/5, 5 false positives, fleet 202/202, corpus 14 sources / 5785 drawers. These
+  were measured on 2026-08-07/08, not today.
+- ⚠ **An absence is the weaker evidence**, and the un-wrapped session's record is exactly
+  that: two commits prove *some* work; nothing proves what else it considered or decided.
+  Treat any claim sourced to that window as unestablished until checked.
+- ⚠ **The drift-check's clean is scoped.** 88 prose deferrals in the registers carry no
+  machine-checkable trigger — "0 due" covers 2 tracked items, not the 88. Counted, not
+  classified.
+
+## Authorization moves
+
+- **PENDING-129 filed** `[HARDENING]`, D-1 — `pattern_finder` silently discards a probed voice
+  that has left the corpus (camus: 19 probes asked, 0 assessed, report prints "4 of 4"). Placed
+  at `~/dotfiles/PENDING.md` L2436; header unique, four structural parts present, symlink intact,
+  drift-check clean after.
+- **PENDING-130 filed** `[PROPOSAL]`, D-1 — V4's designated adversarial fixture is 0 bytes and
+  Stage-1 criterion 1 is unsatisfiable. Placed L2466, same checks. ⚠ Its recommendation carries a
+  condition the executor **cannot** discharge: the answer key must be marked by the steward, or
+  the same hand writes both fixture and gate.
+
+- **SUPERSEDED below (steward: "keep the artifact, just in case").** The re-run is now committed
+  at `ec6fa0b` as `corpus/pattern-finder-station-i-rerun-2026-08-09.{md,json}` — **preservation,
+  not the designation PENDING-130 proposes**, and no answer key is marked. The empty `pass1.md` is
+  deliberately left at 0 bytes: it is the evidence, and overwriting it would destroy the finding.
+  Both declared pre-commit checks fired; fleet 7 suites green (241 checks, 1 unassessed).
+  The sha table below stands as recorded — the `.md` carries a provenance header above an
+  `END-PRESERVATION-HEADER` sentinel, and splitting on it returns bytes identical to a fresh
+  emit (proven, not asserted).
+
+~~**⚠ The re-run artifact lives only in the session scratchpad**~~, which was the exact fragility
+PENDING-130 describes, one layer along. Regeneration is deterministic *only while the corpus is
+unchanged*, so the identity is pinned here instead of trusted:
+
+| artifact | sha256 |
+|---|---|
+| rendered report | `9ac1244b29b4c6bd6cdd372464d7d3e6d93efa9e8cf8fdf33eb5a0d39289757f` |
+| grounded JSON | `16a08a35a07ebb36276fb84f6cc5b3d6f21e518afdf8a4f3e5fd2fac3b8561c6` |
+| input spec (committed) | `a0b3c96259aebb06b0e474a277e2f6fadc5702e5ea34a4d87092bb57ea139723` |
+| `corpus/manifest.yaml` | `408ea190150b06633021ad6ca27c3a5b32ed49d1184939561b5ca5f3dc698e3e` |
+| index `as_of` | `2026-08-07T19:09:36+00:00` |
+
+Regenerate: `python3 engine/pattern_finder.py report corpus/pattern-finder-station-i-pass1.json`.
+**A differing report sha proves the corpus moved** — which is the check nobody had in June.
+
+## Standing conditions (carry to /wrap-up — do NOT let this rotate out)
+
+- 🔒 **No document may call the preserved re-run "V4's fixture" until the steward's dated
+  answer key exists** (steward, 2026-08-09; PENDING-130 §G). Four documents deliberately
+  unedited: rebuild-plan §2.3 + criterion 1 · `tool-evolution-log.md` · engine `CLAUDE.md` L61.
+  Now carried in **three** places, deliberately: PENDING-130 §G (the record) · both artifact
+  headers (fires at the file) · `MEMORY.md` Active Session (fires at wake). ⚠ Marked **against
+  the corpus**, not the report; **steward only** — the delegation to the jurist is foreclosed
+  by formation, not by workload.
+  ⚠ **Open, surfaced not taken:** engine `CLAUDE.md` L61 currently asserts the known-bad output
+  IS the designated fixture and must not be regenerated — a **false claim about an empty file**,
+  live right now. Correcting it is inside PENDING-130's unruled remedy, so it was left alone;
+  but "deliberately unedited" is preserving a falsehood, and that tension is real rather than
+  resolved. Steward's call.
+
+## Returns (later session — closing the gap yesterday's ledger left)
+
+*Written at wrap, and flagged as such: the entries above were live, these are reconstructed from
+the commits and the conversation at the end of the session. Yesterday's ledger stopped at 16:45
+while the day ran to 21:46; this section exists so today does not repeat it.*
+
+- **REVIEWED-113 + 114 placed by the steward; I read the PLACED text, not the relay — and it
+  changed what I did.** Condition 4 reads *"§2.3, criterion 1 and `CLAUDE.md` L61 **may be
+  corrected to name existing material**"* — the opposite of my relay-based reading, which had
+  frozen all four documents. **Third consecutive instance** of the placed record answering a gate
+  question I had left open, and it resolved the exact tension logged above under *Standing
+  conditions* (that "deliberately unedited" was also "preserving a falsehood"). Four documents
+  corrected `20f8958`; verified no document asserts an existing artifact **is** a fixture.
+- **⚠ Steward-caught: I twice wrote PENDING-130 was UNRULED.** It was ruled (a) with five
+  conditions. *Ruled ≠ placed ≠ condition-discharged.* Corrected in the artifact header
+  (`07727dd`) and PENDING-130 §H; `8746dcf`'s commit message left standing, because a filed
+  record records what was said when. **The direction cuts against me** — over-caution that
+  misstates the record is still a misstatement.
+- **V2 orientation: I nearly re-walked mapped ground.** P7 ran **2026-08-07**
+  (`corpus/v2-stratum-tags.yaml`) and the "baseline asymmetry" I was told to settle first is
+  already measured (EN divisions median 27,833 vs FR spans 969 — **29×**). Caught by reading the
+  banked artifact before deriving. The banked-note discipline working, for once, before the fact.
+- **AskUserQuestion denied.** I asked which route to take on the EN narrowing when I already had
+  a safe, reversible recommendation. Took it instead. Recorded as a signal, not yet a rule — one
+  denial with no stated reason is thin evidence, and I would rather see it twice than write a
+  preference memory from a guess.
+
+## Sub-agent dialogues
+
+## Bypasses (continued)
+
+- **My own round-trip check tripped on its own instruction.** The preservation header first read
+  *"strip everything above the `# The pattern-finder` line"* — so `index()` matched the marker
+  **inside the header that quotes it**, and the round-trip reported `False`. Fixed with an
+  explicit `END-PRESERVATION-HEADER` sentinel, asserted to occur **exactly once**. The check
+  caught it because it compared against a **fresh emit** rather than against a remembered sha —
+  a reduction (sha-only) would have shown a plausible mismatch and invited me to explain it away.
+  Same family as yesterday's five: *the checks are the weak link, not the writes.*
+
+## Bypasses
+
+- **Noted, not a bypass by me:** yesterday's ledger stops at **16:45**, while the day ran to
+  **21:46** across two further work blocks (the wrap session and the un-wrapped one). The
+  ledger is not a record of yesterday's last five hours. Naming it now rather than at "a good
+  moment."

claude/memory/session-ledger-2026-08-10.md

@@ -0,0 +1,62 @@
+---
+name: session-ledger-2026-08-10
+description: "Practice-of-return ledger maintained by /symmetria — returns, open horizons, recalibrations, authorization moves, sub-agent dialogues, bypasses."
+metadata: 
+  node_type: memory
+  type: feedback
+  originSessionId: bc984a6d-e8ce-47f5-99da-062703403e7d
+  modified: 2026-08-10T14:10:52.397Z
+---
+
+# Session Ledger — 2026-08-10
+
+## Returns
+
+- **09:xx — inherited premise checked before executing it (second consecutive wake).** The wrap's
+  steward-directed to-do asserted *"the gap is neither knowledge nor home but the absence of an
+  EXECUTABLE."* Substrate says otherwise: `~/dotfiles/scripts/wake-digest.py` already carries
+  `classify_pointers`/`sec_pointers` (built 2026-08-08, `19bddd5`), both indexes, four outcomes,
+  positive controls, wired to SessionStart. The task is therefore **completing an instrument**,
+  not building one. Named before starting work; the fix is scoped to the three real gaps.
+- **Reached the ladder before deriving a gate.** `reference-verification-ladder.md` already
+  specifies the canary under *lossless-relocation gate* — "a link-resolution canary over every
+  `](file.md)` and `[[wikilink]]`". The wikilink half was specified on the ladder and absent from
+  the code; read, not re-derived.
+
+- **Built the wikilink half with the exact defect documented ten lines above it.** First pass
+  reported only `UNWRITTEN`; both live hits were `[[trust-prior-pass-frame]]`, whose file exists
+  as `feedback-trust-prior-pass-frame.md`. The 2026-07-28 provenance block in the same function's
+  header exists to forbid one-word alarms. Caught by *running it on the real substrate* rather
+  than trusting the green suite — the suite passed, because I had only written controls for what
+  I had thought of. Fixed to three outcomes; both pointers repaired.
+- **Chose the worse lexical match on purpose (B3).** The closest verbal match to the claim
+  "reducing… to an undifferentiated grey" is Margaret Mead's quoted words at L1269, not
+  Alexander's at L1267. Took the Alexander-voiced sentence. Nothing in the corpus would have
+  stopped the other choice — which is finding 3, arriving as a live temptation rather than as an
+  abstraction.
+
+## What held
+
+- The wake's own instrument reported its lone "dead" pointer honestly enough to be diagnosable —
+  the four-outcome design (2026-07-28 provenance) did what it was built to do.
+
+## Open horizons
+
+- **`wrap_inside` false alarm.** The digest announced "PREVIOUS SESSION DID NOT WRAP" for a session
+  that wrapped at 19:48 and then kept working until 21:54. Same defect family as the pointer alarm:
+  a two-valued detector over a state that has three cases (wrapped · wrapped-then-continued ·
+  never-wrapped). Named, not fixed — outside today's scope.
+- REVIEWED-114 stays OPEN on 4b (steward's marked answer key). No mechanism can cover it.
+- Skill-harvest: 41 `S2` rows authorized 2026-07-19, still unexecuted.
+
+## Confidence to recalibrate
+
+## Authorization moves
+
+- Canary completion treated as `[FIX]` — it resolves scoped bugs against an existing steward
+  specification (the 2026-08-09 to-do), on an instrument the steward directed be completed today.
+  No new architectural direction; no governance file touched.
+
+## Sub-agent dialogues
+
+## Bypasses

claude/memory/session-ledger-2026-08-13.md

@@ -0,0 +1,136 @@
+---
+name: session-ledger-2026-08-13
+description: "Practice-of-return ledger maintained by /symmetria — returns, open horizons, recalibrations, authorization moves, sub-agent dialogues, bypasses."
+metadata: 
+  node_type: memory
+  type: feedback
+  originSessionId: 1524bae7-44b3-4ba9-8c36-24f53bc8acae
+  modified: 2026-08-13T17:42:52.803Z
+---
+
+# Session Ledger — 2026-08-13
+
+## Returns
+
+- **Wake — substrate-checked a disposition clause instead of reporting it.** REVIEWED-118's
+  `**If AUTHORIZED:**` line reads as a completed act ("Retract instances 6, 12 and 16 …").
+  Checked: `REVIEWED-118` appears nowhere in `corpus/` or `docs/`, and L926's instances still
+  stand in `corpus/mauss-phase2-spans.yaml`. **Authorized, not executed.** Reported as the
+  unblocked next act rather than as done — the wake-step's own discipline (*a disposition clause
+  is not a status*), which exists because the wake is the highest-leverage place a false claim
+  can land.
+
+- **Read the MARKED key's verdict field, not the word count.** First tally counted every
+  occurrence of the three verdict words and returned 38/33/6 — inflated by the legend table that
+  defines the vocabulary. Grepping the actual `**VERDICT:**` field gives **32 `does-not-ground`,
+  4 `grounds`, 0 `cannot-judge`** over 36. Same shape as 2026-08-09's neutrality check matching
+  its own legend: a measurement counting its own documentation.
+
+## What held
+
+- The link-resolution canary ran **as a script at SessionStart** for the first time (dotfiles
+  `32b0c9d`, built 08-10 against the 08-09 steward to-do). 378 pointers + 31 wikilinks, 0 dead.
+  The described-not-invoked gap is closed; it was not retyped this wake.
+
+## Open horizons
+
+- **No wrap record for 2026-08-10.** A large day — the Alexander eight, the gold-intersection
+  reporter, the jurist package, the MARKED answer key, four rulings placed (115–118) — survives
+  only as a mid-day ledger written at 14:10, before any of the afternoon's commits. The 08-09
+  session's PAUSE STATEMENT is therefore the newest wrap, and it is four days stale.
+- **`wrap_inside` detector, second consecutive firing.** Named on 08-10 as a two-valued detector
+  over three cases (wrapped · wrapped-then-continued · never-wrapped). On 08-10 it was a false
+  alarm. Today it appears **true** — at least one session did not wrap. A detector that cried
+  wolf once and is right the next time is the worst position for it to be in. Still unfixed.
+- ~~studium-engine ahead 8, unpushed since 08-10 18:11.~~ **CLOSED** — pushed 2026-08-13
+  (`92a97d0..e51e30d`, 9 commits). The 08-10 arc left the single local copy: the Alexander eight,
+  the gold-intersection reporter, the jurist package, the MARKED answer key, and today's
+  retraction. `main...origin/main`, in sync.
+- REVIEWED-118's retraction window is stated as time-limited by its own ground: the fixture is
+  quiescent *now*, and "that window closes as soon as anything starts measuring again."
+
+- **Caught mid-execution: the spans file is GENERATED.** `scripts/bind_mauss_spans.py` writes
+  `corpus/mauss-phase2-spans.yaml` whole (hardcoded header + `yaml.safe_dump`). A retraction
+  recorded only in the emitted YAML would be erased by the next regeneration, silently, with no
+  diff to read — the disarmed-tripwire class. Found by grepping consumers before writing, not
+  after. The block went into the generator as well.
+
+- **Caught before writing: the two files hold different claims.** REVIEWED-118 says "retract …
+  from the grounded set in [spans file] and [tags file]", but the spans file's own header says in
+  capitals *"WHAT THIS FILE DOES NOT ESTABLISH: that any span ENTAILS the claim."* It measures
+  BINDING, and instances 6/12/16 genuinely do locate to L926 — that stays true after the
+  retraction. Deleting a true measurement to express a judgment about a different property would
+  have made the file stop meaning what its header says. Recorded there, retracted in the tags file.
+
+- **The YAML parse check caught my own hand-edit.** An unquoted colon inside a plain scalar
+  (`"recorded below: these three instances"`) broke the file. `yaml.safe_dump` would have quoted
+  it; the hand-edit did not. Exactly the drift the generator note above is about, arriving
+  immediately as a live instance rather than an abstraction.
+
+- **Steward-caught, twice, on the same instrument — and both times the challenge was to an ASIDE,
+  not to a number.** (1) "fiction can be very valuable too", against my parenthesis *"musil (0,
+  longest span 104 chars, and fiction)"*. Checking it found the census's **fourth** defect and the
+  worst: musil is **hard-wrapped** (median line 69, max 179) while every other source is
+  paragraph-per-line (mauss 166, arendt 1273). A within-line matcher at a 120-char threshold
+  produces ~0 there **before the file is opened**. Two fabricated zeros, not one —
+  `after-the-reply-i` (max line 99) likewise. (2) The FID correction below.
+- **Score on that instrument today: five defects.** ASCII-blind (43% undercount, 3 sources
+  invisible, both positive controls in the same convention so neither could see it) · a negative
+  control passing for the wrong reason · a control aimed one layer below its gate · hard-wrap
+  blindness · and the FIX for hard-wrap classified mauss as hard-wrapped and failed both controls.
+  ⚠ **Only the fifth was caught by the instrument's own controls.** Three by my own re-checking,
+  **one by the steward**, and that one was the most serious.
+- **⚠ AND THE FIX IS A TWO-VALUED DETECTOR OVER A THREE-CASE STATE** (paragraph-per-line ·
+  hard-wrapped · **mixed** — after-the-reply ii/iii/iv/v have medians 30–63 with a few long
+  lines). **Third instance of that exact shape today**, after the wake digest's `wrap_inside`
+  alarm and the fleet's three-valued exit codes that already fixed it once (REVIEWED-104/108).
+  Left stating its limit rather than tuned until the limit stops being visible.
+
+- **Steward refuted my free-indirect-discourse argument, and the refutation is load-bearing.** I
+  argued fiction needs a *second fence mechanism* because FID and irony carry no delimiter. The
+  steward: in FID a reader takes the words to be Musil's, **rightly** — and a paraphrase is a
+  paraphrase; the fidelity of the meaning is what matters. Correct. **A PROVENANCE failure has a
+  second author who can be named and joined to** (Ranaipiri at L926); **a STANCE question has one
+  author and an interpretive judgment about endorsement** (FID, irony) — and irony proves it is
+  not a fiction matter at all, since Arendt reporting a view to demolish it raises the identical
+  question in non-fiction and nobody proposed a mechanism for that. I imported the second into the
+  first because a voice shift *felt* like the nested-voice class. **Consequence: (c) stays ONE
+  capability, not two** — fiction participates through marked dialogue like everything else
+  (musil carries 5014 opening quotes). The residue belongs to PENDING-134's whose-proposition
+  doctrine and to the synthesized tier's NLI, which was already built to ask about meaning rather
+  than ownership.
+
+## Confidence to recalibrate
+
+- **What the 32/36 result licenses is not yet settled.** It is the steward's judgment on
+  *relevance* over one run of one organ. Read as "the engine grounds at 11%" it would be a claim
+  about the engine; read as REVIEWED-114 intends, it is the fixture V4 is built to catch. I have
+  not established which framing the placed record supports — flagged rather than assumed.
+- Everything above the thread-validity gate was read from files this wake. Nothing in the
+  briefing is inherited from an unverified summary, but the 08-12 session's content is
+  **unestablished** — its transcript is on disk and unread.
+
+## Authorization moves
+
+- **REVIEWED-118 EXECUTED** (`e51e30d`). Steward-directed this session; the ruling was placed
+  2026-08-10 and had not been executed. Scope honoured exactly: retraction only. Every stated
+  exclusion held — ratio NOT re-derived (VOID pending PENDING-134), L926 NOT marked, instance 8
+  NOT dispositioned. Verification the ruling named: both files parse; fleet 8 suites / 263 checks
+  green (pre-commit hook ran it independently); reporter selftest PASS, live control 48 regions
+  non-empty.
+
+- **⚠ TWO THINGS OWED TO THE STEWARD, neither resolved by the executor.**
+  1. **Denominator collision.** REVIEWED-118 §3's "fr distinct spans 11 to 10" is arithmetic on a
+     headline field that counted LISTED spans (1 A + 9 B + 1 already-reclassified-out), not
+     grounded ones. The authorized number is written and the fields no longer sum to it — 11
+     listed, 9 grounded. Whether `distinct_spans` names the listed or the grounded population is
+     pre-existing and this entry did not address it. Same class as the finding-3 census corrected
+     at `546f316`. Recorded in the file, not settled.
+  2. **The reporter's region count did not shrink** (48 → 48), because the span was marked in
+     place rather than deleted. REVIEWED-118's parenthetical anticipated a shrink ("a retraction
+     shrinks exactly the thing that control reads"). The check it actually asked for — live
+     control loads non-empty — passes. Stated rather than allowed to read as agreement.
+
+## Sub-agent dialogues
+
+## Bypasses

claude/memory/session-ledger-2026-08-14.md

@@ -0,0 +1,108 @@
+---
+name: session-ledger-2026-08-14
+description: "Practice-of-return ledger maintained by /symmetria — returns, open horizons, recalibrations, authorization moves, sub-agent dialogues, bypasses."
+metadata: 
+  node_type: memory
+  type: feedback
+  originSessionId: d6aeab18-fdf4-4dbf-937c-9547764ba0c4
+  modified: 2026-08-15T07:13:52.065Z
+---
+
+# Session Ledger — 2026-08-14
+
+## Returns
+
+- **2026-08-14T~09:40 — the digest's alarm is a derived label; the file is the substrate.**
+  The wake digest asserted `PREVIOUS SESSION DID NOT WRAP` and told me to "expect no record of
+  what that session did." Read the file instead of the alarm: the wrap record exists, is complete,
+  and names every commit of that session (`e51e30d`, `de1c34b`, `d411034`, `92d5ad2`) except its
+  own wrap commit `e90c334`. The transcript continued ~10 min past the wrap — the *wrapped-then-
+  continued* case. **False alarm. Second false alarm in three firings** of a two-valued detector
+  over three cases, which the 08-13 wrap had already flagged as a watch item.
+  Family: claim-from-derived-artifact-when-the-substrate-is-checkable (§3).
+
+## What held
+
+- **Substrate-checking before listing anything as outstanding.** `REVIEWED-121` grepped for and
+  absent ⇒ PENDING-134 genuinely unruled (verified, not inferred from the wrap's say-so).
+  No 08-10/11/12 session file ⇒ the owed wrap record is genuinely still owed (verified).
+  No commits anywhere since 21:28 ⇒ "nothing changed" is a censused claim, not an impression.
+- **Items I could NOT verify were marked unverified rather than stated flat**: the 41 `S2`
+  skill-harvest rows (register-stated only), and whether the steward restarted the MCP client
+  (that server serves the jurist's client, not mine — unreachable from here, said so).
+
+- **2026-08-14 — grounding the package found two arguments the filed item does not carry, and one
+  cuts against it.** Reading §5's Direction/Exercised-by columns beside §6.2's stratum-B definition
+  showed four of five admitted modes are false-reject modes routed to *gold*, while F4 is false-accept
+  and routed to *negatives* — the counter-argument is stronger than PENDING-134 presents it. Then
+  §7.4(i) read beside §6.2 showed the design's remedy for F4 is a **provenance join at Tier-1**, not a
+  claim-side reading — so the doctrine may be substituting for the unbuilt fence. Both filed as gate
+  questions (Q2's honesty note, Q4), neither resolved. **This is the grounding-pass rule firing:
+  ground in two passes, and expect the omissions to cut against your own case.**
+- **2026-08-14 — three transcription drifts caught by checking my own quotes against the substrate.**
+  (1) An elision in REVIEWED-116 pt 4 that removed *"and L926 remains unmarked"* — a clause cutting
+  AGAINST this package; restored whole and the elision named in the text. (2) Emphasis silently added
+  to a sentence inside a block labelled "reproduced in full". (3) "this session" → a date, likewise
+  unmarked. Fixed, and the label now states exactly what was changed. **A "reproduced in full" claim
+  is checkable and was not true; the script that checks it took two minutes.**
+
+- **2026-08-14 — the jurist caught a false "verified" claim in my package, and my control could not
+  have caught it.** IV.1 asserted *"F10 is the only §5 row containing an explicit stratum-B admission
+  clause"* and marked it verified. **Three rows carry one** (F3, F7, F10) — and F3 and F7 are quoted
+  **with those clauses intact in my own I.2**, and reproduced as "stratum-B gold" in my own IV.2 table
+  one page later. My verification script tested whether *quotes were present*; the claim was an
+  *inference over the rows*. **The control was structurally incapable of testing the defect class, and
+  its pass is what licensed the false sentence.** Re-censused by mechanism: F3/F7/F10 confirmed.
+  ⚠ Also missed the cell-constant D-1 decision at the HEAD of `v2-stratum-tags.yaml` — the same file
+  I read for III.5's counts — where the narrowing sits directly beneath a quotation of the §6.2 text
+  it narrows.
+
+## Open horizons
+
+- The literal question inherited from 08-13: **are control sets a regression net, not a discovery
+  net?** Census the last ~10 sessions, classify each instrument defect by (a) own controls,
+  (b) executor re-check, (c) human challenge. Self-contained, checkable, executor-shaped.
+- H3's standing consequence still needs to become a **field or a check**, not a memory: any recall
+  figure from the fr fixture carries a note that stratum membership was amended post-hoc 2026-08-10.
+- The `wrap_inside` detector: two-valued over three cases, now with 2 false alarms in 3 firings.
+  Same shape the fleet's three-valued exits already fixed once (REVIEWED-104/108).
+
+## Confidence to recalibrate
+
+- Holding `count-by-subtraction-not-enumeration` (banked 08-13) in front: the fr cell close is all
+  counts and ratios, and that error entered twice by subtraction — P7's and mine, same session.
+
+## Authorization moves
+
+- **REVIEWED-121 PLACED and AUTHORIZED** (`~/REVIEWED.md` L1777) — the whose-proposition test
+  ratified **narrowly**, conditioned on PENDING-131 (c) remaining sought. Read from the FILE, not the
+  relay: the placed entry carries three things the relayed copy did not — point 9's tail, a sentence
+  added to the ratified doctrine (*"The refusable half does not satisfy §7.4(i)"*), and a disposition
+  gating the ratio on PENDING-137 as well. **The banked rule fired and changed the work, not just a
+  citation.**
+- **PENDING-137 filed** (cell-constant narrowing, routed to the jurist by REVIEWED-121 pt 2).
+- **PENDING-89 docket entry filed** — one instance, direction named, countervailing evidence beside it.
+- **Executed** `corpus/v2-stratum-tags.yaml` two declared fields (`5425414`, tagged REVIEWED-121).
+  Fleet 9/285 green; gold_intersection selftest 5/5 with its live 48-region control.
+- ⚠ **`REVIEWED.md` deliberately left unstaged** — the steward's placement. The
+  `unscoped-git-add-in-dotfiles` pattern banked yesterday fired correctly today.
+
+## What I found while executing, and it is not in any ruling
+
+- **The defeater cannot ever fire on this cell, and I declared that rather than filling the field.**
+  REVIEWED-121 pt 7 replaces reader-independence with ORDER-independence: a disposition recorded
+  *before the doctrine is consulted*. For all eleven inherited spans that moment is past and
+  unrecoverable — the doctrine is ratified and known. Back-filling would record a post-doctrine
+  judgment in a field whose whole evidential value is preceding one: **self-confirming, the exact
+  shape R0's first validator was caught by** — it computed each region's fingerprint from the live
+  file and compared it to itself, reporting all 322 regions `verified`. Landed as
+  `defeater_has_ever_been_exercisable: false` — *not* "not yet defeated".
+  ⚠ **CITATION CORRECTED at wrap.** This entry first cited that guard as
+  `test_legacy_indices_are_not_self_verified`. **No such function exists** — the name occurs once
+  repo-wide, in a docstring at `tests/test_reading_index.py:23`. The jurist raised it as
+  *uncitable*; it was worse. Real checks: L128, L130, and the positive control at L281. Fixed in
+  the substrate at `966168b`; fixed here because a ledger is a durable record too.
+
+## Sub-agent dialogues
+
+## Bypasses

claude/memory/session-ledger-2026-08-17.md

@@ -0,0 +1,107 @@
+---
+name: session-ledger-2026-08-17
+description: "Practice-of-return ledger maintained by /symmetria — returns, open horizons, recalibrations, authorization moves, sub-agent dialogues, bypasses."
+metadata: 
+  node_type: memory
+  type: feedback
+  originSessionId: 81f817e9-4016-4867-ae16-a486f1e8fb46
+  modified: 2026-08-17T13:23:05.853Z
+---
+
+# Session Ledger — 2026-08-17
+
+## Returns
+
+- **2026-08-17T~12:15 — the digest's `PREVIOUS SESSION DID NOT WRAP` alarm, overridden a second
+  time.** Same false alarm the 08-14 ledger records overriding at ~09:40. Read the substrate, not
+  the derived label: `session-2026-08-14-…md` exists, is complete, and was extended twice today
+  (CODA, CODA 2). The banner also instructed the wake to "expect no record of what that session
+  did" — the record is the fullest of the week. Third firing, third false alarm; it is the
+  candidate task the steward left open for today.
+
+- **2026-08-17T~15:05 — the scoped task was not the defect.** `wrap_inside` was queued as a
+  two-valued-detector fix. Diagnosing the class first found four defects; the arity was #4 and
+  the cause was a UTC/local time-base mismatch (+7201 s against a 900 s tolerance). Proven by
+  old-vs-new on the reconstructed wake instant: fixing only the scoped item would have shipped a
+  fix that left the alarm firing.
+- **2026-08-17T~15:25 — nearly reported 50 stale trackers off mtime.** Fifty files sharing
+  *exactly* 72.3 d is a bulk operation, not fifty edits. Checked git: it agreed with mtime, so the
+  bulk-touch suspicion was **refuted** — and then the commit itself turned out to be
+  `3f9a89b`, a 283-file normalization sweep that reset *both* signals. Third and fourth instances
+  in one day of an instrument whose subject is adjacent to the claim. The honest measure is the
+  last commit excluding the sweep.
+
+- **2026-08-17T~16:10 — I damaged three files with my own stamping script, and my check said clean.**
+  The stamp located frontmatter with a non-greedy `^---\n.*?\n---\n`, which on a stray-block file
+  matches the STRAY block — orphaning the real frontmatter into the body. That is the identical
+  blindness I had diagnosed in `strip_frontmatter` an hour earlier, reproduced in the tool written
+  to clean up after it. The post-stamp check reported `malformed: none` because it asked *does the
+  file start with frontmatter then a banner* — true for all three — while the claim was *the stamp
+  preserved the metadata*. **Fifth instance of the day's shape, and the first inside my own
+  verification.** Repaired against git's pre-stamp version: no key lost.
+- **2026-08-17T~16:25 — my repair then broke the wake.** Touching 20 April–May wrap records moved
+  their mtimes to today, and `sec_pause` picked "newest wrap" by mtime, promoting an April session
+  to `Last wrap` and losing thread and question together. **Caught by the DEGRADED banner** — the
+  honest-degradation mechanism doing exactly its job on its author.
+- **2026-08-17T~17:40 — placing a deferral revealed the deferral checker wasn't reading the register.**
+  `PENDING.md` had passed the 400 KB guard and every structured block in it was silently skipped,
+  while the prose-count loop (no guard) kept reporting the file and made it look examined. Found only
+  because the tracked count did not move after I placed a block.
+
+- **2026-08-17T~18:50 — I understated a count by half, and a disclosed limit caught it.** I reported
+  "PENDING-131 ADDENDA 2 and 4 await steward action." **Four blocks carry a live `Awaiting:`** —
+  parent, ADD-1, ADD-2, ADD-4. The jurist ruled on my testimony and *named the check it had not
+  run* (ADD-1); running it overturned my number. Seventh instance of the day's shape: my census's
+  subject was *the addenda I had looked at*, not *the blocks carrying awaits*.
+
+## What held
+
+- The wake read every claim it reported against the substrate rather than relaying the digest:
+  drift-check re-run live (4/4 clean, 2 amendments seen), `~/dotfiles` git status re-run (clean and
+  pushed), the wrap record and Symmetria ledger opened rather than summarized from the banner.
+- **The DEGRADED banner caught its own author.** Honest degradation is not decorative here; it is the
+  only reason the broken wake was found in-session rather than at the next wake.
+- **Reading the PLACED record rather than the relay, fifth consecutive firing.** REVIEWED-122 carried
+  five conditions, two severed legs and an explicit ordering the relay did not state; REVIEWED-123
+  carried a general freeze the item had argued only for S2.
+- **Dry-run before every bulk write** (16 stamps, 39 repairs, 3 damage-fixes). The dry run did not
+  catch the stamping defect — but it bounded it to 3 files and made the git-diff proof possible.
+
+
+- **A disclosed scope-limit did the work no control did.** The jurist could not verify ADDENDUM 1
+  and said so plainly instead of glossing. That sentence is the entire reason the count was
+  corrected — differently-positioned readers paying out because the position was *stated*.
+
+## Open horizons
+
+- **Steward direction: tooling, not governance, today.** Three candidates, `wrap_inside` fix
+  recommended; S2 ladder batch is BLOCKED by PENDING-141 and must not execute; engine retrieval /
+  PENDING-97 is the day-sized one.
+- **Hypothesis, not yet verified** — beyond wrapped-then-continued, `sec_unwrapped` may select the
+  *wrong transcript* (`now - mtime > 60` skips a just-quiet session) and `wrap_records()` mtimes
+  are *mutable*, so any later edit to a session memory file moves it out of its own session's span.
+  If the fix is taken up, verify both before designing the third value.
+- No Symmetria ledger was opened for the earlier 2026-08-17 session (the CODA / PENDING-140 / -141
+  sitting). Noted, not chased.
+
+## Confidence to recalibrate
+
+- Holding the inherited literal question in front: *was the control's SUBJECT the claim it was
+  cited as verifying, or an adjacent property?* If today's task is the detector fix, its selftest
+  is precisely where that shape recurs — a control over the *detector's* inputs is not a control
+  over the *verdict's* truth.
+
+## Authorization moves
+
+- **2026-08-17 — steward authorized Groups A+B stamping, harvest first**, and directed the general
+  finding be folded into PENDING-142 rather than filed as a new item. Executed: rule harvested to
+  `feedback-bulk-indexing-runs-incrementally-with-readback.md` **before** any stamp; 16 trackers
+  stamped `superseded_by` + visible in-body banner; B3's label corrected with the two-month error
+  left visible. Nothing moved, renamed or deleted — 381 pointers still resolve, 0 dead.
+- **Held back from the same act:** Group C (2 correctly-parked files, named dependencies) and
+  Group E (2 files named nowhere — returned to the steward). The 39 unread trackers are recorded
+  as a **gap, not a finding**.
+
+## Sub-agent dialogues
+
+## Bypasses

claude/memory/session-ledger-2026-08-18.md

@@ -0,0 +1,51 @@
+---
+name: Session Ledger 2026-08-18
+description: Practice-of-return ledger maintained by /symmetria — returns, open horizons, recalibrations, authorization moves, sub-agent dialogues, bypasses.
+type: feedback
+---
+
+# Session Ledger — 2026-08-18
+
+## Returns
+
+- **2026-08-18T~wake — I skipped the mood signal on a check whose error I had suppressed.**
+  `ls -t session-ledger-*.md 2>/dev/null` returned empty and I read that as *no ledger exists*.
+  It returned empty because `ls` is aliased to `eza`, which rejected `-t session-…`; the `2>/dev/null`
+  hid the rejection. `/bin/ls` shows **104 ledgers**, including 2026-08-17's. An empty result from a
+  command that *errored* is "could not assess", not "nothing there" — the exact distinction
+  REVIEWED-104 rules may not be collapsed, and the same distinction the drift-check reports by name
+  for its two oversized files. Corrected before composing the next section; mood signal read and added.
+
+## What held
+
+- Every claim in the briefing was substrate-checked rather than relayed from the digest: the answer
+  key's absence by `find`, PENDING-142's unbuilt state by grepping `wake-digest.py` for `Awaiting`
+  (zero hits), N-now by running the checker's own `TRANSCRIPTS.glob` rather than quoting yesterday's
+  60, dotfiles cleanliness and all five repos by live `git status`.
+- **The three transcription errors were NOT reported as open.** The wrap listed them under
+  steward-owed horizons; the CODA records the steward correcting them post-wrap (`bbfcc08`), and the
+  commit is in the log. Reading the record to its end is what kept a closed item off the open list.
+
+## Open horizons
+
+- **The steward's pick is not made.** (A) MOVE 2 — disposition the 25 line-addressable blockquote
+  runs, one sitting, no ruling needed. (B) the answer key, block-keyed, session-sized, gates all of
+  PENDING-142. (C) MOVE 1 — fence at emission, engine-side under D-1, 532 spans. Wrap recommended
+  (A) then (C); (B) when there is a full session.
+- **N-now = 61/84 transcripts, 23 remaining** (REVIEWED-123 cond. 2). Ladder frozen generally;
+  4 rows queued in PENDING-141's owed list, OWED-4 a rewording to merge rather than append.
+- **The literal question is unanswered and answerable from the record**, not from introspection:
+  across the last ~10 sessions, who or what found each defect in the executor's own instrument.
+
+## Confidence to recalibrate
+
+- Yesterday produced **seven** instances of one shape — a control whose subject is adjacent to its
+  claim — and **three of the seven were the executor's own**, one of them inside its own
+  verification. Today's first act reproduced the family at the shell level (above). The disposition
+  to hold: before reading a check as clean, say out loud what proposition it tests.
+
+## Authorization moves
+
+## Sub-agent dialogues
+
+## Bypasses

claude/memory/session-ledger-2026-08-19.md

@@ -0,0 +1,72 @@
+---
+name: Session Ledger 2026-08-19
+description: Practice-of-return ledger maintained by /symmetria. Continues the session begun 2026-08-18 (ledger in the sibling file); the day rolled while the session was idle overnight.
+type: feedback
+---
+
+# Session Ledger — 2026-08-19
+
+*Continues the session begun 2026-08-18; the wake briefing was delivered that evening and the session sat idle overnight. See `session-ledger-2026-08-18.md` for the first return.*
+
+## Authorization moves
+
+- **2026-08-19T~11:15 — STEWARD DEFERRAL, recorded as asked.** The fence work — (A) MOVE 2, (B) the
+  answer key, (C) MOVE 1 — is **deferred to the morning of 2026-08-20**. Stated reason: **two other
+  pieces of work come first and could well shape this very work.** That makes it sequencing rather
+  than drift, and it is the steward's call regardless.
+  - ⚠ **The two are not yet named.** `feedback-close-thoroughly-no-frequent-deferrals` requires a
+    deferral to name its specific dependency; here the dependency is stated in kind but not in
+    identity. **Name them in `MEMORY.md`'s Active Session block as soon as they are known** — "what
+    could reshape this" is the entire dependency, and it is the part that decays.
+  - Order is unharmed: nothing in (A)/(B)/(C) has begun, so REVIEWED-122's binding sequence — answer
+    key first, alone, hash recorded, before any implementation — is intact.
+  - ⚠ **Cost recorded so the deferral is made with eyes open:** the citation exposure behind
+    PENDING-131 (c) has been live since 2026-08-10 (day 9).
+
+- **2026-08-19T~11:30 — PENDING-147 filed** `[HARDENING]`, within executor authority (CLAUDE.md:
+  propose in PENDING.md, await steward annotation). Not deferred to the wrap, because leg (i) is
+  time-critical.
+
+## Returns
+
+- **2026-08-19T~11:15 — the standing N-now obligation caught a defect in itself.** Re-running the
+  count rather than quoting yesterday's figure returned **47**, not 61. Cause, measured: the trigger
+  globs `*.jsonl` in a directory the harness prunes at 30 days, so the counter is a **rolling
+  window**, not a cumulative count — oldest file exactly 30 d old, ~1 session/day observed.
+  Consequences: `transcripts 84` is very likely unsatisfiable, so the ladder freeze is indefinite
+  while reading as bounded; and **the trial's evidence is expiring** — 13 post-intervention
+  transcripts survive, the 2026-08-07 cohort deleted 2026-09-06.
+  - ⚠ **The gate's own positive controls pass and see none of it.** `transcripts 1` fires,
+    `transcripts 999999` is silent — establishing that *threshold comparison* works, while the claim
+    is that *the count means sessions since the intervention*. **Eighth instance of the
+    wrong-subject family (OWED-1), and the first inside a governance gate.**
+  - Every prior "N remaining" report, including mine last night, was a **false countdown**. Corrected
+    in `MEMORY.md` rather than re-stated.
+
+## What held
+
+- **The obligation found it, not the vigilance.** REVIEWED-123 cond. 2 requires N-now at every wake;
+  discharging it by *re-measuring* rather than *relaying* is the only reason the drop was visible.
+  A datum for this session's literal question, and it favours *mechanism* over *executor judgment* —
+  the executor did not suspect anything; it was obeying a reporting rule.
+- **The steward's ask was answered before the finding was chased.** The deferral note is the thing
+  that was requested; the trial defect is surfaced beside it, not in place of it.
+
+## Open horizons
+
+- **PENDING-147 leg (i) — preserve the post-2026-08-07 transcripts — is the only leg with a clock.**
+  It needs no ruling (copying files changes no instrument, no doctrine, no ladder) and its cost rises
+  daily. Recommended as a standalone act whenever the steward wants it; ~2 minutes.
+- The fence work, deferred to 2026-08-20 (above).
+- The literal question from 2026-08-17 remains unanswered and is answerable from the record.
+
+## Confidence to recalibrate
+
+- Yesterday's tally of the wrong-subject family stood at seven. It is **eight** before any of today's
+  planned work began, and this one had been sitting inside a governance gate since 2026-08-07,
+  passing its own controls. The disposition to hold is unchanged and now better evidenced: **before
+  reading a check as clean, say out loud what proposition it tests.**
+
+## Sub-agent dialogues
+
+## Bypasses

claude/memory/skill-harvest-register.md

@@ -348,3 +348,103 @@ honest proposal is that the steward decide whether the degraded-state form is di
 earn its own entry or should be folded into the existing one as an example.
 
 **Awaiting:** steward authorization.
+
+### 2026-08-09 wrap — two proposals; firing moments declared per the REVIEWED-95 gate
+
+**#196 — `governance-drift-check.py`: assert that any text calling a governance item *unruled* or *unplaced* agrees with the register.** Earned twice in one session, steward-caught both times: I wrote *"PENDING-130 is unruled"* in a commit message and had an artifact header say the item *"proposes"* — while REVIEWED-114 had ruled it (a) with five conditions. **Ruled · placed · condition-discharged are three states and none implies another**; the existing built-vs-ruled check covers only *built-with-no-ruling*, which is the opposite direction and did not fire. Proposed: for every `PENDING-N`/`REVIEWED-N` in the memory files, registers and repo docs asserted to be *unruled / unplaced / not yet ruled / awaiting*, assert the register agrees.
+**Firing moment: mechanical, should always fire → `governance-drift-check.py`** — already named in a `/wake-up` step (the measured 83% home class) and already performing register-integrity checks. **Real positives available, not synthetic:** today's two, both preserved in git (`8746dcf`'s message; `07727dd`'s parent state).
+**Classification:** detection-only; asserts nothing, expands no latitude → reads FIX-lane. **Filed as `[PROPOSAL]` anyway**, on the same ground as #192: the check is unbuilt and untested, and this session's own lesson is that my checks are weaker than my writes. **Status: PROPOSED**, to be ruled with #192/#195 if convenient — all three are drift-checker extensions.
+
+**#197 — ladder entry (gate-design family): an induced-red probe must revert BEHAVIOUR, not delete the symbol.** Removing the function under test produces an **`AttributeError` traceback**, which proves the suite *crashes* when the code is absent — not that it would **name** the regression when the code is present and wrong. The honest probe leaves every name in place and monkeypatches the pre-defect semantics; mine then produced exit **1 with six named failures**, camus by name and the `KeyError` resurfacing. ⚠ **Companion, same command:** the exit code was read **through a pipe** (`… | tail`), so the reported `0` was `tail`'s — the *reduction-before-looking* class, already banked as #195 and firing again the next day.
+**Firing moment: on a condition the executor must first notice** — *"I am about to witness this suite red."* The weakest routing row, **declared as such rather than dressed up**; no mechanical detector exists for it. Routed to `reference-verification-ladder.md` §Gate design, beside *"a control must sit at the layer the defect lives in"*, which it is a special case of: deleting the symbol puts the control at the wrong layer. **Recorded estimate: ~10–14% retrieval pending the ladder-ritual trial.**
+**Classification: `[PROPOSAL]`** — changes what the executor must do before trusting a witness-red. **Status: PROPOSED.**
+
+**Deliberately NOT proposed.** The preservation-header self-match (a strip instruction that quotes the marker it tells you to strip to, so `index()` matches inside the header) is a **one-shot** defect in a one-shot artifact, caught by the round-trip that was already there. Per `feedback-one-shot-instruments-are-proportionate`, its counterfactual is an assertion, not a durable instrument — filing it would be documentation dressed as diligence. The generalisable half is already banked: **compare against a fresh emit, not against a recorded sha**, which is what caught it.
+
+**No FIX-lane changes were applied this session.**
+
+---
+
+## 2026-08-13 — three proposals from the nested-voice / voice_stamp session
+
+### HS-2026-08-13-a — a dotfiles pre-commit guard against unscoped staging of governance files
+
+**Earned:** the executor ran `git add -A` in `~/dotfiles` mid-session and swept the steward's
+freshly-placed **REVIEWED-119/120** and a `sysupdate` **Brewfile** line into a commit whose message
+described only a `governance-mcp.py` change. Amended before push (`92d5ad2`), so no shared history
+was rewritten — but the dotfiles log is explicitly meant to double as a legible session record, and
+for one commit it attributed a steward governance act to an executor `[FIX]`.
+
+**The routing finding, which is the point:** `/wrap-up` §6.5 already states the rule — *"Scoped add
+only — never `git add .` or `-A`"* — and states why. **But §6.5 fires at WRAP, and dotfiles commits
+happen throughout a session.** The rule is correct and lives at the wrong moment. This is the
+register's own diagnosis applied to itself: a capability is worth what a protocol exercises, and
+this one is exercised at a juncture the violation routinely precedes.
+
+**Firing moment: mechanically, and it should always fire** — the strongest row in the routing table.
+A `~/dotfiles` pre-commit hook that inspects the *staged set*: if `REVIEWED.md` or `CLAUDE.md` is
+staged alongside files outside `claude/`, `PENDING.md`, refuse with the §6.5 text and require an
+explicit override. Detects the actual failure (mixed staging of steward-authored governance) rather
+than the proxy (`-A` in the command line, which is unobservable from a hook).
+⚠ Must NOT block a legitimate steward commit — the hook lives in the executor's path only, and the
+override must be one flag, documented in its own refusal message.
+
+**Classification: `[PROPOSAL]`** — it changes what the executor may do without asking (it adds a
+refusal), and it touches the path by which `REVIEWED.md` reaches the remote. Hard-floor adjacent:
+`REVIEWED.md` is Constitutional Constraint 1 material, so the guard must only ever *refuse*, never
+*edit*. **Status: PROPOSED.**
+
+### HS-2026-08-13-b — `wake-digest.py`'s `wrap_inside` is two-valued over a three-case state
+
+**Earned:** the digest announced **"PREVIOUS SESSION DID NOT WRAP"** at this session's wake. It was
+right this time. It was **wrong on 2026-08-10**, where the 08-09 session had wrapped at 19:48 and
+then kept working until 21:54 — and the 08-10 ledger already named the defect: *"a two-valued
+detector over a state that has three cases (wrapped · wrapped-then-continued · never-wrapped)."*
+Named, not fixed, and it has now fired twice with opposite truth values. **A detector that cried
+wolf once and is right the next time is in the worst position available** — the reader has already
+learned to discount it.
+
+⚠ **Third instance of this exact shape in one day**, which is the argument for fixing it rather than
+re-noting it: the fleet's three-valued exit codes fixed this shape once already
+(REVIEWED-104/108), and the nested-voice census's hard-wrap detector reproduced it again the same
+afternoon.
+
+**Firing moment: mechanically, and it already runs** — `wake-digest.py` fires at SessionStart. This
+is a patch to an existing always-firing instrument, not a new capability needing a home.
+Report three states: `wrapped` · `wrapped-then-continued` (with the post-wrap span) · `never-wrapped`.
+
+**Classification: `[PROPOSAL]`** — it changes what a governed artifact *asserts* (the wake digest's
+claim about session continuity, which the wake briefing then relays to the steward).
+**Status: PROPOSED.**
+
+### HS-2026-08-13-c — "a control set drawn from one source establishes nothing about a corpus"
+
+**Earned:** the nested-voice census carried **five defects**; **four escaped its own controls**.
+Every positive control was drawn from Mauss — one quotation convention (guillemets), one line
+structure (paragraph-per-line) — so the controls could exercise neither the ASCII-quote convention
+(3 sources, incl. the two largest EN texts) nor hard-wrapped text (2 sources). Both blindnesses
+produced **clean zeros**, which read as findings. Only the fifth defect — a regression in an
+already-covered case — was caught by the controls, and that asymmetry is the finding: **the controls
+could not see what they were never drawn to cover, and did see a regression in what they did.**
+
+**Distinct from what is already banked.** Symmetria §3 carries *frame-inheritance* — reusing an
+**instrument** across a tier it was not demonstrated on. This is the complementary failure: the
+instrument was **new**, and its **control set** was the thing drawn from too narrow a population. The
+existing flag would not have caught it.
+
+**Proposed wording, for §3:** *A control set drawn from one source, one format, or one convention —
+however many controls it contains. Coverage is the whole of a control set's strength; controls prove
+what they were drawn to cover and nothing else. Enumerate the structural classes present in the
+subject BEFORE writing controls, and report `NOT ESTABLISHED` for a class with no control rather
+than reporting zero for it.*
+
+**Firing moment: at a ritual juncture that already exists** — Symmetria `check` fires before any
+build or write with blast radius, which is exactly when a control set is being written. Stronger
+than a bare ladder entry (measured 14%) and stronger than a skill (measured 0%).
+
+**Classification: `[PROPOSAL]`** — §3 flags shape what the executor must notice before acting, and
+this one imposes a precondition on building an instrument. Borderline against the FIX lane's
+two-clause test; **proposed rather than applied, per "when in doubt, propose."**
+**Status: PROPOSED.**
+
+**No FIX-lane changes were applied this session.**

claude/memory/user-care-over-traffic-skills-as-accountability.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/user-care-over-traffic-skills-as-accountability
----
-
 ---
 name: Care over traffic — work answers to itself; skills as accountability not productivity
 description: Steward correction 2026-04-28 of an earlier "fix carelessness so I can just write" framing. The corrected posture: even with no traffic, the few who find ARC see craft; quality work matters whether or not it's read; skills/agent-circles serve consistency and accountability, not scale.
 type: user
 originSessionId: e5a1fa7c-cae6-49c4-8678-e27ce379639b
+permalink: claude-memory/user-care-over-traffic-skills-as-accountability
 ---
 **Steward verbatim** (2026-04-28 afternoon, after sharing the morning jurist conversation): *"To be clear, I think there is basically no traffic on ARC, and we have substantive work still to get the whole thing 'in shape', but it is coming along slowly but surely. This is what I meant some time ago when I made the comment that I want to be in the position of just writing and publishing as soon as I can rather than fixing my previous carelessness — but that comment was reckless because, even if only a few ever come, they will see that arc is crafted with care. This is also why i want the skills/agent-circles, etc to help me with the quality control, consistency, accountability..."*
 

claude/memory/user-duality-rules-and-poetic-as-mnemonic.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/user-duality-rules-and-poetic-as-mnemonic
----
-
 ---
 name: Rules-and-poetic duality — rule as mechanism, metaphor as mnemonic for dwelling in constraint
 description: Steward's articulated working method: rules serve skills/agents (who serve him, mutually); poetic/metaphoric layer functions as mnemonic device so one dwells in the constraint and finds freedom *through* it, not *from* it. Held close for ARC style-guide gather; applies regardless of domain (viola, ARC, fathering, L2).
 type: user
 originSessionId: 0e858bcf-ef4e-46c6-9eca-abd19836786a
+permalink: claude-memory/user-duality-rules-and-poetic-as-mnemonic
 ---
 # The duality — rules and poetic-as-mnemonic
 

claude/memory/user-life-as-pilgrimage.md

@@ -1,12 +1,9 @@
----
-permalink: claude-memory/user-life-as-pilgrimage
----
-
 ---
 name: Life as pilgrimage — a long-held framing the steward holds
 description: 2026-04-29. Steward verbatim during the Hic+Adsum composition: "I have long considered life to be a pilgrimage." This is the substrate behind the *Pilgrim* tagline at /bio/ on ARC. Not decorative; structural. Distributes across three registers in the threshold composition: Hic (place names itself), Adsum's *here* (present location in a longer journey), Bio's *Pilgrim* (journey-shape).
 type: user
 originSessionId: 122baf2b-1029-4ec9-9723-99b4b5f3a64d
+permalink: claude-memory/user-life-as-pilgrimage
 ---
 **2026-04-29.** During the Hic+Adsum composition for the ARC About-page, when I noted that bio.md's tagline reads *"Pilgrim"*, the steward replied:
 

claude/skills/wake-up/SKILL.md

@@ -63,7 +63,7 @@ Run these in parallel to minimize latency:
 - Read `skill-harvest-register.md` directly — the canonical surface for open skill proposals (wrap §1.6 appends there); surface any awaiting steward authorization <!-- 2026-06-05: register wiring, authorized 2026-05-29, applied with wrap-up §1.6 counterpart -->
 - Read `reference-verification-ladder.md` directly — the canonical surface for the named verification instruments; hold the one or two the session's work will actually need <!-- 2026-08-07: PENDING-112 → REVIEWED-95. THIS SENTENCE IS A PRE-REGISTERED TRIAL INTERVENTION, landed alone and deliberately parallel to the register line above. Baseline before it: the ladder was reached in 9 of 64 sessions (14%), while the register — identical in kind, differing only in being named here — sat at 77%. Prediction: >60% over the 20 sessions following. Graded automatically at 84 transcripts via the `ladder-ritual-trial` DEFERRED-DECISION trigger; the result is filed as a dated PENDING entry whichever way it falls. Do not add to, reword, or "improve" this line before the trial is graded — a second change confounds the only check standing behind PENDING-112's causal claim. -->
 - Read `~/.claude/projects/-Users-davidglidden/memory/session-ledger-[previous-date].md` if it exists — **specifically read the "Returns" and "Confidence to recalibrate" sections** for mood signal
-- **Link-resolution canary (seconds-cheap):** verify MEMORY.md's file pointers resolve — every `](file.md)` target exists in the memory dir. Flag dead pointers in the briefing, distinguishing pre-existing-broken from newly-broken (grep the previous git state if in doubt). A pointer to a missing file is the index lying about what memory holds. <!-- 2026-07-19 harvest review (steward-authorized): the wake-canary link-resolution half, proposed 2026-06-07, partially built 2026-07-06 (truncation half), now standing. -->
+- **Link-resolution canary — READ THE DIGEST'S `MEMORY POINTERS` LINE; do not re-implement it.** `~/dotfiles/scripts/wake-digest.py` runs at SessionStart and reports both indexes over both link forms — path pointers `](file.md)` and `[[wikilinks]]` — in four outcomes each (OK · MIS-AUTHORED, with the replacement string handed back · DEAD/UNWRITTEN · NON-PORTABLE), and dates each break as pre-existing or newly-broken from git. Surface any non-OK outcome in the briefing; a pointer to a missing file is the index lying about what memory holds. If the digest is absent, run it: `python3 ~/dotfiles/scripts/wake-digest.py`. ⚠ **Never hand-type this check.** It was typed inline on 2026-08-08 and again on 2026-08-09, and the hand version's one "finding" was the link pattern inside its own specification — the executable strips code spans and the hand version cannot. Prove the instrument before trusting a clean line: `wake-digest.py --selftest` (61 checks, positive and negative controls). <!-- 2026-07-19 harvest review (steward-authorized): the wake-canary link-resolution half, proposed 2026-06-07, partially built 2026-07-06 (truncation half). 2026-08-08: built as classify_pointers (19bddd5). 2026-08-10 [FIX], steward-directed: code-span blindness closed, wikilinks added (the ladder had specified them since 2026-07-06), breakage dated from git, and this step turned from a description into a pointer at the executable — the described-not-invoked gap was the whole reason it kept being retyped. -->
 - **Telos conditional:** if the pulling thread touches the studium engine / The Making / ARC-as-public-proof (the engine's reason-for-being), also read `project-studium-engine-telos-chamber-of-voices.md` and hold ONE line of the why in the briefing — the telos lane drawn first, never only the production lanes. Do NOT recite it on unrelated wakes (decorative). <!-- 2026-07-19 harvest review (steward-authorized): proposed 2026-06-18 after the steward had to re-disclose the chamber's origin; second evidence instance 2026-07-19 (map-drawn-from-production-lanes-not-telos, steward corrected twice). -->
 
 **b. The files layer — primary memory**  `[palace-memory MemPalace wound down 2026-07-07]`

claude/transcript-archive/MANIFEST.json

@@ -0,0 +1,342 @@
+{
+  "preserved_at": "2026-08-19T11:21:32+02:00",
+  "why": "PENDING-147 leg (i). The harness prunes ~/.claude/projects/<name>/ at 30 days, so the REVIEWED-95 ladder trial and its REVIEWED-123 cond. 2 counter were measuring a rolling window and the trial evidence was being deleted. This archive stops that clock.",
+  "source_dir": "/Users/davidglidden/.claude/projects/-Users-davidglidden",
+  "count": 47,
+  "bytes_total": 119202600,
+  "live_session_snapshot": [
+    "0883c73d-9091-4508-aa31-592ddff5240a.jsonl"
+  ],
+  "verification": "sha256 of every archived file compared against its source at copy time",
+  "files": [
+    {
+      "file": "ed160e3c-d735-405a-8a98-d04ee2e2581e.jsonl",
+      "sha256": "3caaf42dbf6c6c02dddd4caf8392c80863a3a36bde54b7e22cfa404573b5a9b5",
+      "bytes": 2584717,
+      "source_mtime_iso": "2026-07-20T08:51:43",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "8139a859-99fa-4072-90c5-701e0221a053.jsonl",
+      "sha256": "9972931d044cbc80face3c301afda08340daa5f375cbfc034e76a38b21e82908",
+      "bytes": 2875065,
+      "source_mtime_iso": "2026-07-20T21:20:21",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "4b2bf87b-e9f7-41ab-983f-b681f6879cd8.jsonl",
+      "sha256": "9fbb72734b4f19672b310cf8cff4c3d23d37f15dbc80580a197f215dad1e90e8",
+      "bytes": 10871,
+      "source_mtime_iso": "2026-07-20T21:23:28",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "deca6eb6-6292-494c-ab31-9bc8576e8d75.jsonl",
+      "sha256": "20f3cbef51a18cb87b25df11200299d74005da855462744446700cf718599068",
+      "bytes": 3186879,
+      "source_mtime_iso": "2026-07-21T22:26:57",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "86105106-174b-40ae-8684-cbeb8831d21c.jsonl",
+      "sha256": "5d02d103c42e21139fd33f96427a10a36a3ebc80d5e8bff9fd063f3ea03a9e67",
+      "bytes": 2308673,
+      "source_mtime_iso": "2026-07-23T17:23:59",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "11c72f23-b135-42b4-8868-41f736c7d971.jsonl",
+      "sha256": "630161dd8204fe1dcf9cca72b1788fa7f9a1acb684218548cc67b1b068507bb1",
+      "bytes": 10748,
+      "source_mtime_iso": "2026-07-23T17:25:23",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "d6f7ee32-e448-465c-967f-54c1d9f9c8a2.jsonl",
+      "sha256": "68b3a0a48019c72b0f3f4ac93e2c6c5eacfd89a1a615d431612e9bdab05d7edc",
+      "bytes": 3391706,
+      "source_mtime_iso": "2026-07-23T21:42:32",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "e2a6db77-92c3-4a75-9e29-5608cece99b9.jsonl",
+      "sha256": "dd4dfa9c3a90af320abc1e760c9bcbcd21d97114b5ab48d5299d591af92b2217",
+      "bytes": 2743249,
+      "source_mtime_iso": "2026-07-24T10:52:11",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "7b9e072c-82cb-45c4-ae17-c017422ddd20.jsonl",
+      "sha256": "8f9d2205a590fa2ca9b4db5093092a753927784a37a22ebdbe04818253a2fd15",
+      "bytes": 904480,
+      "source_mtime_iso": "2026-07-24T11:20:38",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "3d93ae4a-11b7-49ca-8de0-63fa296e9394.jsonl",
+      "sha256": "ae90ded5c264d161f799432750d9e7868e7b00e7fa9b5cb1ecdddb72c2509a21",
+      "bytes": 2212643,
+      "source_mtime_iso": "2026-07-24T13:10:41",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "226d8113-7cd8-492b-8adb-e15a429bbabe.jsonl",
+      "sha256": "7b087b36e0135e1226b121d62cb04e393b795d3339d72cf158f150135c05874b",
+      "bytes": 5579776,
+      "source_mtime_iso": "2026-07-24T14:51:28",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "c8dd62d7-df44-4d38-8e66-12bd2afe9a33.jsonl",
+      "sha256": "00dd72be89a52f4871fee227b1e9c561314c3f6b44c9ec238af6c2187cfa1174",
+      "bytes": 2471197,
+      "source_mtime_iso": "2026-07-24T17:00:43",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "0ed8c15a-fea2-49a8-a7f7-8753142a4b0c.jsonl",
+      "sha256": "556a9797ccae662655049f76f7b7b5776bf39e5d61a3f5e8dfca349a21de4a6b",
+      "bytes": 2597201,
+      "source_mtime_iso": "2026-07-24T19:51:29",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "58ba5886-9bb6-415f-9440-a4b87099ffa0.jsonl",
+      "sha256": "ab691e4fcec574e04e3e63b7e79451a00d7d46f3d466bdfc9dcf5414b582c2e3",
+      "bytes": 2513480,
+      "source_mtime_iso": "2026-07-25T10:10:00",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "954fee42-68ff-46b5-95e6-238f33e6ca80.jsonl",
+      "sha256": "6b5e5604ea53a3c348819e6a35b8ffdbaa98f41859597d30a7315a2c616bb9fe",
+      "bytes": 2300516,
+      "source_mtime_iso": "2026-07-27T19:39:52",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "e3816856-e2d8-4877-ba70-25e6bae612b6.jsonl",
+      "sha256": "a63bb48ed7cd382af948923bff671ff16340922e5508f94b2947c6cf9ef53837",
+      "bytes": 3202018,
+      "source_mtime_iso": "2026-07-27T22:17:49",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "1f2001a9-b44c-4490-9eb2-86c1639a1276.jsonl",
+      "sha256": "81766032e5f3a44dddb133c5e485c2e04f4f1fb374441ec56a00dca7bc271e18",
+      "bytes": 1597982,
+      "source_mtime_iso": "2026-07-28T09:46:51",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "53971d20-52b2-4707-80f2-f7f651d350d0.jsonl",
+      "sha256": "69d80c6829d4a35132d3a401b69fbbbe7ebc3bd59d2a5ac57212affd0379a545",
+      "bytes": 2076554,
+      "source_mtime_iso": "2026-07-28T11:41:18",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "850100b0-d230-4e94-a226-480d681bb037.jsonl",
+      "sha256": "926e8c0c10ad423ac261b956d69d65b905e386f40757bd76360648d62a6ed21b",
+      "bytes": 1752936,
+      "source_mtime_iso": "2026-07-28T13:44:33",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "cdbcfb19-8656-4415-be6c-d0868bbd8549.jsonl",
+      "sha256": "d696fdc09d58a4ee28b5986909dba79e7f7400102a08c6a74f2978535a99a9e0",
+      "bytes": 2001812,
+      "source_mtime_iso": "2026-07-29T18:10:36",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "1c3580c9-c9cf-4cef-a0c4-c470ca684fa3.jsonl",
+      "sha256": "20a6d9f20540a5ecab491ca710f16533af3b8d2d41ac8fbd80127e7981abb647",
+      "bytes": 2327115,
+      "source_mtime_iso": "2026-07-31T22:25:55",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "be51f191-8658-4b4c-ad1e-1f14c934f624.jsonl",
+      "sha256": "e010a708df4e3f0a47440c331119db13a50755499092edfdefe3f4cdebe8cff3",
+      "bytes": 8183357,
+      "source_mtime_iso": "2026-08-02T10:42:11",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "9256a5b3-c56b-4564-8ff2-8dc9d93ef97a.jsonl",
+      "sha256": "09ea9dd2565c78f301fd5d5a347319b74f37e67f0d5a634ec8c9242f6ea7bcba",
+      "bytes": 2664119,
+      "source_mtime_iso": "2026-08-02T12:31:19",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "8f13c64f-ecb1-4579-b09f-97d2fa1eec4c.jsonl",
+      "sha256": "2a51b1893ad81d214a19eab255a05c40e73b1f3031ca0aa5f4ba17efe9404772",
+      "bytes": 4729297,
+      "source_mtime_iso": "2026-08-02T16:34:41",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "f01230e1-d62d-4195-8e21-356429806fbd.jsonl",
+      "sha256": "5b4d0f99b922de122cb5a8abab7281a88003c8d0226d18336f3b0e734619c87f",
+      "bytes": 3176017,
+      "source_mtime_iso": "2026-08-03T09:36:54",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "79865b08-85e5-4969-bf88-6b535d965ea9.jsonl",
+      "sha256": "49d664fb9bc260e47fc2f240ba551ea50bfa932071628f842ac611dffed3e5e9",
+      "bytes": 3319256,
+      "source_mtime_iso": "2026-08-03T21:33:06",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "27422433-12f3-4983-a5cc-c4105158d59c.jsonl",
+      "sha256": "18cf4a252295e2e7dd82efabb2cb912c8e8e2c06b9fac2fb58a6e243943f3931",
+      "bytes": 2100827,
+      "source_mtime_iso": "2026-08-04T15:35:04",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "bd67d3b3-e698-439d-bb6f-ae2017320cdf.jsonl",
+      "sha256": "22d3f52193e172b186107db1a0b3373d6138ee314defb57272a2354bca9bd2d7",
+      "bytes": 1760466,
+      "source_mtime_iso": "2026-08-04T18:10:33",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "1e7e6ba6-ad15-4d95-b057-1e92659517a0.jsonl",
+      "sha256": "3a56b7971251d01d307a069642638ffa86c25e1b37a10aedb82ad12734553369",
+      "bytes": 9918,
+      "source_mtime_iso": "2026-08-04T19:43:39",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "ef462bef-fa3d-4ed4-82e0-9dde3d8c7ab9.jsonl",
+      "sha256": "4c4e3dadee9c3ff87bfb5af94e8c2cc67249538bdabef5f4f1f69f86354bbac9",
+      "bytes": 3283633,
+      "source_mtime_iso": "2026-08-05T22:20:04",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "ba76bc5d-193e-4b06-8c8a-e6e07a194d4b.jsonl",
+      "sha256": "b71309e06b35ee6872e62af7463a597f4e79fbf7c5daff42134d71b3ff8767e4",
+      "bytes": 8721987,
+      "source_mtime_iso": "2026-08-06T13:45:39",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "75d3a0a3-70eb-4286-92ab-0aa05d419f0c.jsonl",
+      "sha256": "f018ba9c1617894df938757aec057083e3bf0ce735697c927058ea2ad26411a2",
+      "bytes": 1627253,
+      "source_mtime_iso": "2026-08-06T17:01:14",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "f1b95970-e482-41f2-9b0b-d74edf74a24d.jsonl",
+      "sha256": "59e58f17b976f1fbd0a611740480c01cbc55b958041db0759a79bb134fec694d",
+      "bytes": 2374845,
+      "source_mtime_iso": "2026-08-06T22:29:35",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "67e2310d-0613-4454-9e99-38047d527706.jsonl",
+      "sha256": "77eba56bb094dcf93747d7d680c8357259fd0595336b855d7506b87eb58b23af",
+      "bytes": 13534,
+      "source_mtime_iso": "2026-08-06T22:30:38",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "033cfe63-c9d0-4fad-accf-c45de561f09a.jsonl",
+      "sha256": "abe84c13ded9c6b687ccf4826b1979b1e580dd72d5e6577cc498b9c7ae56b4f8",
+      "bytes": 3909514,
+      "source_mtime_iso": "2026-08-07T18:12:22",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "1963f1a4-1999-4800-92fc-43f041ef4bdc.jsonl",
+      "sha256": "94a2e87de53af78526e9bd36a052c1294cff213028c50d8022584e3170c66d7e",
+      "bytes": 1783796,
+      "source_mtime_iso": "2026-08-07T19:10:29",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "3209a980-ab74-434e-a2a6-895a54f02f82.jsonl",
+      "sha256": "afbc113f7cd74f6da4af511474cf85945d91896f2a08e6b0eb1f136b4180d1e7",
+      "bytes": 2619943,
+      "source_mtime_iso": "2026-08-07T22:32:31",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "7d08dad4-626a-484c-870b-8f1a9674db7a.jsonl",
+      "sha256": "026150372f9ee621040e22c2fdacef7dd179bece158271dcb3389ac381fe8cd9",
+      "bytes": 1746327,
+      "source_mtime_iso": "2026-08-08T13:09:52",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "932b538a-4624-4ce7-8826-ecbd6b8d079f.jsonl",
+      "sha256": "80a73a33b5ceeb1ba023d06afb31efa6a889f7a8d0e7a819d116a9c6f5d279b0",
+      "bytes": 1612323,
+      "source_mtime_iso": "2026-08-08T15:28:20",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "2a23dafd-63d8-4e62-b955-33775639fc1f.jsonl",
+      "sha256": "cfb523dbdd00426d2e8a543bc38e6a87d636094d656b013df85231cba70870d9",
+      "bytes": 4371696,
+      "source_mtime_iso": "2026-08-08T21:41:28",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "126c343a-c7a0-4760-984a-b599b31dfff1.jsonl",
+      "sha256": "9f4338b96f6af414224fe56e92182de3e6b97255a3b6d21b5b065e33643cefd8",
+      "bytes": 12387,
+      "source_mtime_iso": "2026-08-08T21:46:57",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "d5f5c224-f249-41a3-87ce-cb2d50c6e1f4.jsonl",
+      "sha256": "fbc28ae0bda9598d11979dd97939635238fa22c6a10caa88d913edeaf31372af",
+      "bytes": 2042845,
+      "source_mtime_iso": "2026-08-09T21:54:44",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "bc984a6d-e8ce-47f5-99da-062703403e7d.jsonl",
+      "sha256": "9ccc243b272d4f16366a35998e11fbc5b7a80b7bd7f5d8e5e6ed03262b30a23c",
+      "bytes": 2418589,
+      "source_mtime_iso": "2026-08-12T01:58:36",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "1524bae7-44b3-4ba9-8c36-24f53bc8acae.jsonl",
+      "sha256": "352468ea821a08d97c53bd719a49f92c203e61c991475095b6b64e7fc25cda46",
+      "bytes": 2304255,
+      "source_mtime_iso": "2026-08-13T21:36:13",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "d6aeab18-fdf4-4dbf-937c-9547764ba0c4.jsonl",
+      "sha256": "79c4806b2186ab8b2ee01dce4a582afe47b6c71c3b2f5735ba0f5a1b94d8edbc",
+      "bytes": 2458090,
+      "source_mtime_iso": "2026-08-17T14:32:43",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "81f817e9-4016-4867-ae16-a486f1e8fb46.jsonl",
+      "sha256": "3d5bdcda933e9e797afa98716e78e4e2cce542c7145bc035365d91eb3e3573f1",
+      "bytes": 2754178,
+      "source_mtime_iso": "2026-08-18T18:33:40",
+      "source_matched_at_copy": true
+    },
+    {
+      "file": "0883c73d-9091-4508-aa31-592ddff5240a.jsonl",
+      "sha256": "a74fd3d7cb09700185ec0a32f17437a761e75e438653898bec71d5c7171b94e6",
+      "bytes": 554530,
+      "source_mtime_iso": "2026-08-19T11:21:12",
+      "source_matched_at_copy": false
+    }
+  ]
+}

claude/transcript-archive/README.md

@@ -0,0 +1,37 @@
+# Preserved Claude Code transcripts
+
+**What this is.** A verified copy of every `*.jsonl` session transcript that existed in
+`~/.claude/projects/-Users-davidglidden/` on 2026-08-19, taken out of that directory because the
+harness prunes it on a 30-day retention policy.
+
+**Why it exists — PENDING-147 leg (i), steward-authorized 2026-08-19.** Two governance instruments
+were counting files in that pruned directory as if the count were cumulative:
+
+- `REVIEWED-95` (2026-08-07) pre-registered a 20-session falsifier for the verification-ladder
+  retrieval trial, graded automatically when the count reaches 84.
+- `REVIEWED-123` cond. 2 (2026-08-17) obliges an N-now report at every wake.
+
+The count is a **30-day rolling window**, not a cumulative count: it read 60 on 08-17, 61 on 08-18
+and **47 on 08-19**. So the trigger is very likely unsatisfiable at the observed ~1 session/day, and
+the trial's own evidence was being deleted on a rolling basis — only 13 post-intervention
+transcripts survived, the earliest cohort due for deletion on 2026-09-06. **This archive stops that
+clock for everything that existed on 2026-08-19.**
+
+**What was verified.** 47/47 files copied; **46 confirmed sha256-identical to source**. The 47th is
+the live session's own transcript, still being appended at copy time — recorded in `MANIFEST.json`
+as a snapshot rather than silently counted as verified.
+
+**Read `MANIFEST.json` for provenance, not the filesystem.** Each entry carries `sha256`, `bytes`
+and the source `mtime` **as recorded data**. This is deliberate: mtime is mutable, and on 2026-08-17
+a bulk frontmatter repair moved 20 records' mtimes and broke the wake by promoting an April session
+to `Last wrap`. A hash in a manifest survives what a timestamp does not.
+
+## ⚠ What this archive does NOT do
+
+**It covers only files that existed on 2026-08-19.** It is a snapshot, not a mechanism. Sessions run
+after that date still land in the pruned directory and will still be deleted at 30 days unless the
+copy is repeated. The recurring case is named in PENDING-147 and is **not** discharged by this
+archive.
+
+**It is one copy on one disk.** The deletion clock is stopped; disk-loss is a different risk and is
+not addressed here.

obsidian/pass1-compass-changelog.json

@@ -0,0 +1,74 @@
+[
+ {
+  "file": "00. Compass/00b. Constellations/Animal Rationis Capax/ARC \u2014 System Assessment & Path Forward.md",
+  "line": 16,
+  "before": "sources:",
+  "after": "source:"
+ },
+ {
+  "file": "00. Compass/00b. Constellations/Animal Rationis Capax/AldineXXI \u2014 Assessment & Technical Debt.md",
+  "line": 14,
+  "before": "sources:",
+  "after": "source:"
+ },
+ {
+  "file": "00. Compass/00b. Constellations/Animal Rationis Capax/99. Archives\u2014Previous Iterations/Combined Roadmap -- Glyphs \u2194 UCE-CIE.md",
+  "line": 5,
+  "before": "version: 2025-09-21",
+  "after": "version: \"2025-09-21\""
+ },
+ {
+  "file": "00. Compass/00b. Constellations/Animal Rationis Capax/Mid-longform articles/From_Mushi-Ken_to_Morra.md",
+  "line": 7,
+  "before": "linked_daily_note: [[2025-06-02]]",
+  "after": "linked_daily_note: \"[[2025-06-02]]\""
+ },
+ {
+  "file": "00. Compass/00b. Constellations/Animal Rationis Capax/Mid-longform articles/Vespers for the Living - Monteverdi with Jordi Savall.md",
+  "line": 6,
+  "before": "linked_daily_note: [[2025-06-08]]",
+  "after": "linked_daily_note: \"[[2025-06-08]]\""
+ },
+ {
+  "file": "00. Compass/00b. Constellations/Animal Rationis Capax/Stubs & ideas/On the Disappearance of Moral Attention.md",
+  "line": 8,
+  "before": "related: [[2025-07-15]]",
+  "after": "related: \"[[2025-07-15]]\""
+ },
+ {
+  "file": "00. Compass/00b. Constellations/Animal Rationis Capax/03. Glyphs (Sigils)/Sigil System Capability Report \u2014 September 2025.md",
+  "line": 4,
+  "before": "version: 2025.09",
+  "after": "version: \"2025.09\""
+ },
+ {
+  "file": "00. Compass/00b. Constellations/Animal Rationis Capax/10. Ready to publish/After the Reply/2. On Abdication and Fidelity.md",
+  "line": 13,
+  "before": "language: en",
+  "after": "languages: en"
+ },
+ {
+  "file": "00. Compass/00b. Constellations/Animal Rationis Capax/10. Ready to publish/After the Reply/3. Boredom, Novelty, and the Breaking of the Common World.md",
+  "line": 13,
+  "before": "language: en",
+  "after": "languages: en"
+ },
+ {
+  "file": "00. Compass/00b. Constellations/Animal Rationis Capax/10. Ready to publish/After the Reply/1. The Ethics of the Reply.md",
+  "line": 13,
+  "before": "language: en",
+  "after": "languages: en"
+ },
+ {
+  "file": "00. Compass/00b. Constellations/Animal Rationis Capax/99. Archives\u2014Previous Iterations/99. The Chamber/Chamber Previous versions/Version 1/Documentation/The Chamber-A Living Amphitheatre, V1.md",
+  "line": 16,
+  "before": "version: 1.1",
+  "after": "version: \"1.1\""
+ },
+ {
+  "file": "00. Compass/00b. Constellations/Animal Rationis Capax/99. Archives\u2014Previous Iterations/99. The Chamber/99. Archive/Documentation/Chamber Prompting Practices & Variations.md",
+  "line": 14,
+  "before": "version: 2.1",
+  "after": "version: \"2.1\""
+ }
+]

obsidian/templates.json

@@ -0,0 +1,314 @@
+{
+ "declared": {
+  "work": 1,
+  "tags": 15,
+  "date": 3,
+  "family": 2,
+  "skin_observations": 1,
+  "reflection": 1,
+  "type": 15,
+  "health": 1,
+  "week": 2,
+  "homeopathy": 1,
+  "month": 3,
+  "year": 3,
+  "last_reviewed": 4,
+  "title": 4,
+  "related": 1,
+  "created": 10,
+  "aliases": 1,
+  "full_name": 1,
+  "languages": 1,
+  "notes": 1,
+  "location": 1,
+  "occupation": 1,
+  "alias": 1,
+  "citizenship": 1,
+  "relationship": 1,
+  "dob": 1,
+  "change_log": 1,
+  "canonical": 1,
+  "version": 1,
+  "assurance": 1,
+  "status": 6,
+  "links": 1,
+  "next_review": 1,
+  "project": 1,
+  "owner": 1,
+  "review_cycle": 1,
+  "quarter": 5,
+  "themes": 1,
+  "seasonal_cycle": 4,
+  "bloom": 2,
+  "roaster": 2,
+  "pour_strategy": 2,
+  "brew_temp": 2,
+  "rating": 2,
+  "water_brand": 2,
+  "process": 2,
+  "grind_setting": 2,
+  "bloom_time": 2,
+  "roast_level": 2,
+  "water": 2,
+  "origin": 2,
+  "dose": 2,
+  "total_time": 2,
+  "coffee": 2,
+  "blend_components": 1,
+  "week_of": 1,
+  "start_date": 1,
+  "vault_section": 2,
+  "description": 2
+ },
+ "per_tpl": {
+  "Book_Note_Template.md": {
+   "keys": [],
+   "how": "no-frontmatter"
+  },
+  "Daily Note Template.md": {
+   "keys": [
+    "date",
+    "family",
+    "health",
+    "homeopathy",
+    "month",
+    "reflection",
+    "skin_observations",
+    "tags",
+    "type",
+    "week",
+    "work"
+   ],
+   "how": "parsed"
+  },
+  "Document (PDF) note template.md": {
+   "keys": [],
+   "how": "no-frontmatter"
+  },
+  "End of Day Checklist.md": {
+   "keys": [],
+   "how": "no-frontmatter"
+  },
+  "GPT_Model_Selector_Template.md": {
+   "keys": [],
+   "how": "no-frontmatter"
+  },
+  "Monthly Planning Template.md": {
+   "keys": [
+    "month",
+    "tags",
+    "type",
+    "year"
+   ],
+   "how": "parsed"
+  },
+  "Monthly Review Template.md": {
+   "keys": [
+    "last_reviewed",
+    "month",
+    "tags",
+    "type",
+    "year"
+   ],
+   "how": "parsed"
+  },
+  "PPP_Template.md": {
+   "keys": [
+    "aliases",
+    "created",
+    "related",
+    "tags",
+    "title"
+   ],
+   "how": "textual(templater-broken YAML)"
+  },
+  "People Template.md": {
+   "keys": [
+    "alias",
+    "citizenship",
+    "dob",
+    "family",
+    "full_name",
+    "languages",
+    "last_reviewed",
+    "location",
+    "notes",
+    "occupation",
+    "relationship",
+    "tags",
+    "type"
+   ],
+   "how": "parsed"
+  },
+  "Quarterly Review Checklist \u2014 Context Rot Guardrails.md": {
+   "keys": [
+    "assurance",
+    "canonical",
+    "change_log",
+    "created",
+    "last_reviewed",
+    "links",
+    "next_review",
+    "owner",
+    "project",
+    "status",
+    "tags",
+    "title",
+    "type",
+    "version"
+   ],
+   "how": "parsed"
+  },
+  "Quarterly Review Template.md": {
+   "keys": [
+    "created",
+    "quarter",
+    "review_cycle",
+    "status",
+    "tags",
+    "themes",
+    "type"
+   ],
+   "how": "parsed"
+  },
+  "Seasonal Compass \u2013 Autumn Equinox 2025.md": {
+   "keys": [
+    "created",
+    "quarter",
+    "seasonal_cycle",
+    "status",
+    "tags",
+    "type"
+   ],
+   "how": "parsed"
+  },
+  "Seasonal Compass \u2013 Spring Equinox 2025.md": {
+   "keys": [
+    "created",
+    "quarter",
+    "seasonal_cycle",
+    "status",
+    "tags",
+    "type"
+   ],
+   "how": "parsed"
+  },
+  "Seasonal Compass \u2013 Summer Solstice 2025.md": {
+   "keys": [
+    "created",
+    "quarter",
+    "seasonal_cycle",
+    "status",
+    "tags",
+    "type"
+   ],
+   "how": "parsed"
+  },
+  "Seasonal Compass \u2013 Winter Solstice 2025.md": {
+   "keys": [
+    "created",
+    "quarter",
+    "seasonal_cycle",
+    "status",
+    "tags",
+    "type"
+   ],
+   "how": "parsed"
+  },
+  "Tasting_Log_Template_Dataview.md": {
+   "keys": [
+    "bloom",
+    "bloom_time",
+    "brew_temp",
+    "coffee",
+    "date",
+    "dose",
+    "grind_setting",
+    "origin",
+    "pour_strategy",
+    "process",
+    "rating",
+    "roast_level",
+    "roaster",
+    "total_time",
+    "type",
+    "water",
+    "water_brand"
+   ],
+   "how": "textual(templater-broken YAML)"
+  },
+  "Tasting_Log_Template_With_Blend.md": {
+   "keys": [
+    "blend_components",
+    "bloom",
+    "bloom_time",
+    "brew_temp",
+    "coffee",
+    "date",
+    "dose",
+    "grind_setting",
+    "origin",
+    "pour_strategy",
+    "process",
+    "rating",
+    "roast_level",
+    "roaster",
+    "total_time",
+    "type",
+    "water",
+    "water_brand"
+   ],
+   "how": "textual(templater-broken YAML)"
+  },
+  "Weekly_Coffee_Journal_Template.md": {
+   "keys": [
+    "type",
+    "week_of"
+   ],
+   "how": "textual(templater-broken YAML)"
+  },
+  "Weekly_Review_Template.md": {
+   "keys": [
+    "last_reviewed",
+    "start_date",
+    "tags",
+    "type",
+    "week"
+   ],
+   "how": "parsed"
+  },
+  "Yearly Compass Template.md": {
+   "keys": [
+    "created",
+    "tags",
+    "type",
+    "year"
+   ],
+   "how": "parsed"
+  },
+  "Zibaldone Note Template.md": {
+   "keys": [],
+   "how": "no-frontmatter"
+  },
+  "concept_thread_template.md": {
+   "keys": [
+    "created",
+    "description",
+    "tags",
+    "title",
+    "vault_section"
+   ],
+   "how": "parsed"
+  },
+  "language_reflection_template.md": {
+   "keys": [
+    "created",
+    "description",
+    "tags",
+    "title",
+    "vault_section"
+   ],
+   "how": "parsed"
+  }
+ }
+}

obsidian/vault-frontmatter-inventory-2026-08-19.md

@@ -0,0 +1,365 @@
+---
+name: obsidian-vault-frontmatter-inventory-2026-08-19
+description: Read-only inventory of YAML frontmatter conventions in the "David, root-and-branch" Obsidian vault — key census, consumption cross-reference, folder correlation, template drift. No proposals.
+type: reference
+---
+
+# Obsidian frontmatter inventory — *David, root-and-branch*
+
+**Date:** 2026-08-19 · **Mode:** read-only audit, no edits · **Scope:** the root-and-branch vault only
+(`Ars Legendi` and `DFG Principles` exist and were **not** audited).
+
+**Method.** Every `*.md` outside `.obsidian/`, `.trash/`, `.git/`, `.smart-env/` was parsed — 2,519 files,
+no sampling. Frontmatter recognised only as a `---` block **beginning at byte 0**; a stray `---` mid-file
+is not frontmatter. The parser carries four controls, all passing: well-formed → detected; no
+frontmatter → none; stray mid-file `---` → none; unterminated → reported as its own outcome rather than
+folded into silence. Keys were harvested **twice** — once via `yaml.safe_load`, once textually — so a
+parse failure cannot silently shrink the census (410 textual key-lines vs 400 parsed keys; the gap is the
+21 unparseable notes in §6).
+
+---
+
+## 1. Coverage — the first number
+
+| | notes |
+|---|---|
+| markdown files | **2,519** |
+| **no frontmatter at all** | **1,713 (68%)** |
+| frontmatter present | 806 (32%) |
+| … parsed as a mapping | 784 |
+| … YAML error | 20 |
+| … not a mapping / empty | 2 |
+| unreadable | 0 |
+| unmaterialized iCloud placeholders | **0** — so this census is of the vault, not of what happened to be downloaded |
+
+**By folder** — coverage is not uniform; it tracks how recently and how deliberately a folder was built.
+
+| folder | notes | with frontmatter | % |
+|---|---:|---:|---:|
+| 99. Archive | 1,070 | 120 | **11%** |
+| 08. Notes | 596 | 230 | 38% |
+| 00. Compass | 400 | 193 | 48% |
+| 06. Projects | 246 | 105 | 42% |
+| 04. Life admin | 47 | 45 | **95%** |
+| 07. Learn | 29 | 19 | 65% |
+| 97. Tools and Systems | 28 | 26 | 92% |
+| 98. Templates | 23 | 18 | 78% |
+| 03. People | 21 | 14 | 66% |
+| 05. Work | 21 | 7 | 33% |
+| 02. Reviews & Planning | 13 | 7 | 53% |
+| 01. Daily | 11 | 10 | 90% |
+| 00a. _inbox | 11 | 11 | 100% |
+| 09. Atlas of Roots | 1 | 1 | 100% |
+| 10. Instrumentarium | 1 | 0 | 0% |
+| (vault root) | 1 | 0 | 0% |
+
+---
+
+## 2. The key census — 400 distinct keys, 5,867 instances
+
+**Distribution is extremely long-tailed.** 227 keys (57%) appear on one or two notes; **170 appear
+exactly once**. The top 10 keys carry 3,145 instances — 54% of all frontmatter in the vault.
+
+### Keys on ≥10 notes, with observed value shapes
+
+| key | notes | shapes observed |
+|---|---:|---|
+| `tags` | 698 | `list[str]`×689, `list[int\|str]`×6, empty×1, nested-list×1 |
+| `title` | 610 | `str`×605, null/empty×5 |
+| `type` | 416 | `str`×416 — **the only high-frequency key with a single shape** |
+| `created` | 359 | `date`×339, `str(date-like)`×12, `str`×7, nested-list×1 |
+| `status` | 305 | `str`×305 |
+| `version` | 164 | `str`×157, **`float`×6**, `date`×1 |
+| `date` | 163 | `date`×155, `str`×7, `str(wikilink)`×1 |
+| `canonical` | 161 | `str`×158, **`bool`×3** |
+| `owner` | 153 | `str`×153 |
+| `assurance` | 126 | `dict`×117, **`str`×8**, null×1 |
+| `last_reviewed` | 123 | `date`×115, `str`×5, null×1, nested-list×1 |
+| `related` | 120 | `list[str]`×90, nested-list×8, `list[wikilink]`×7, `list[list]`×6 |
+| `change_log` | 89 | `list[dict]`×51, **empty list×38** |
+| `source` | 86 | `str`×79, `list[str]`×3, `str(url)`×2, `dict`×1 |
+| `project` | 83 | `str`×81, `list[str]`×2 |
+| `next_review` | 80 | `date`×80 |
+| `links` | 77 | `dict`×76, null×1 |
+| `aliases` | 71 | `list[str]`×71 |
+| `location` | 67 | `str`×58, null×8, nested-list×1 |
+| `category` | 52 | `str`×43, `list[str]`×9 |
+| `week` | 51 | `str`×51 |
+| `author` | 49 | `str`×45, `list[str]`×3, `dict`×1 |
+| `last_updated` | 38 | `date`×38 |
+| `description` | 36 | `str`×36 |
+| `origin` | 34 | `str`×34 |
+| `layout` | 33 | `str`×33 |
+| `mood` | 30 | **null/empty×26**, `str`×4 |
+| `focus` | 24 | **null/empty×24 — never once filled in** |
+| `vault_section` / `month` / `marker` | 23 each | `str` |
+| `class` / `roaster` | 22 each | `str` |
+| `review_cycle` | 21 | `str` |
+| `water` | 21 | `int`×10, `float`×6, `str`×4, `list`×1 |
+| `coffee` | 21 | `str` |
+| `grind_setting` | 21 | `float`×16, `str`×3, `int`×2 |
+| `related_notes` | 20 | `list[str]`×13, `list[wikilink]`×4, nested×1, empty×1 |
+| `bloom` | 20 | `int`×11, `float`×8, `str`×1 |
+| `brew_temp` | 20 | `str`×16, `list[list[str]]`×4 |
+| `superseded_by` | 18 | `list[list[str]]`×18 |
+| `depends_on` | 17 | `list[wikilink]`×6, nested×5, `list[str]`×4, empty×2 |
+| `summary` | 17 | `str` |
+| `family` | 16 | empty×6, `dict`×6, null×4 |
+| `context` | 15 | `str`×8, null×6, `dict`×1 |
+| `retention` | 15 | `float`×9, `str`×4, `int`×2 |
+| `updated` | 14 | `date`×14 |
+| `languages` / `permalink` / `process` | 13 each | mixed / `str` / `str` |
+| `relationship`, `dob`, `latitude`, `longitude`, `source_type`, `attributed_to`, `date_claimed`, `first_cited`, `fictional_description`, `chambers_cited_in`, `excerpts`, `dose`, `weather`, `temperature`, `humidity`, `pressure` | 12 each | see JSON |
+| `citizenship`, `draft_created`, `emerged_from`, `related_real_sources`, `dateAdded`, `lastUpdated`, `method`, `roast_level`, `bloom_time`, `pour_strategy`, `total_time`, `rating` | 11 each | see JSON |
+| `alias`, `person`, `bill_number`, `moon_phase` | 10 each | see JSON |
+
+*Full per-key detail — every shape, four sample values, folder distribution, and the file list — is in
+`fm_inventory.json` alongside this report.*
+
+### 2a. Type instability, observed
+
+Nine keys carry more than one value type. Three matter because a query would silently mis-sort or drop rows:
+
+- `version` — `str`×157 but **`float`×6** (`1.0` unquoted becomes a number) and `date`×1.
+- `canonical` — `str`×158 but **`bool`×3** (`true` unquoted).
+- `assurance` — `dict`×117 but **`str`×8**: the same key is a structure on most notes and a bare string on eight.
+- Nested-list shapes (`list[list[...]]`) on `created`, `related`, `location`, `superseded_by`, `brew_temp`,
+  `linked_daily_note` are the signature of a wikilink or date written unquoted inside a YAML list —
+  `- [[Note]]` parses as a nested list, not a link.
+
+### 2b. Two keys that collide with Dataview's own namespace
+
+- **`file`** is used as a frontmatter key on 5 notes. `file` is Dataview's implicit page object
+  (`file.link`, `file.day`, `file.name`) and appears in 83 query blocks in that sense.
+- **`date`** on 163 notes coexists with Dataview's `file.day`, which is inferred from the filename.
+
+---
+
+## 3. Consumption — is anything reading these keys?
+
+Cross-referenced against every consumption surface in the vault: **357 code blocks** (264 `dataview`,
+72 `dataviewjs`, 21 `tasks`) across 98 notes; **23 templates** in `98. Templates`; all **39** `.obsidian`
+JSON configs; 14 CSS snippets.
+
+> **A method note, because the first pass of this was wrong.** I initially scored a key as
+> "written by a template" if its name appeared *anywhere* in a file containing Templater syntax. That
+> tests whether the word occurs in the prose, not whether a template writes the key — and it inflated
+> the bucket badly (`practice`, `work`, `note` all scored as template-written on prose matches alone).
+> The figures below come from parsing each template's **own frontmatter block**. Likewise, Dataview
+> matches are made after stripping string literals and `FROM` clauses, so a folder path like
+> `FROM "08. Notes"` no longer counts as consumption of a key named `notes`.
+
+| verdict | keys | key-instances |
+|---|---:|---:|
+| **CONSUMED** — appears in a Dataview query field position | 66 | **3,661 (62%)** |
+| **WRITTEN-NOT-READ** — a template writes it, no query reads it | 29 | 1,128 (19%) |
+| **ORPHAN** — no template declares it, no query reads it | **305** | 1,078 (18%) |
+| DECLARED-ONLY (`types.json`, unqueried) | 0 | 0 |
+
+**The shape of it: the *mass* is consumed, the *variety* is not.** 62% of all frontmatter instances sit
+on the 66 keys something actually reads. But 305 of 400 distinct keys — 76% — are read by nothing, and
+248 of those appear on four notes or fewer.
+
+### 3a. WRITTEN-NOT-READ — the governance block is the largest instance
+
+These are written faithfully by template onto hundreds of notes and queried by nothing in the vault:
+
+| key | notes | declared by |
+|---|---:|---|
+| `canonical` | 161 | 1 template |
+| `owner` | 153 | 1 |
+| `assurance` | 126 | 1 |
+| `related` | 120 | 1 |
+| `change_log` | 89 | 1 — and **38 of the 89 are an empty list** |
+| `links` | 77 | 1 |
+| `aliases` | 71 | 1 |
+| `location` | 67 | 1 |
+| `vault_section` | 23 | 2 |
+| `month` | 23 | 3 |
+| `review_cycle`, `water`, `bloom`, `brew_temp` | 20–21 | 1–2 |
+| `family`, `languages`, `process`, `relationship`, `dob`, `dose` | 12–16 | 1–2 |
+| `citizenship`, `bloom_time`, `pour_strategy`, `alias` | 10–11 | 1–2 |
+| `reflection`, `homeopathy`, `skin_observations`, `full_name`, `occupation` | 2–7 | 1 |
+
+`canonical`, `owner`, `assurance`, `change_log`, `links`, `related` are the Compass's own
+governance/provenance apparatus — the fields that would answer *is this authoritative, who holds it,
+when was it last checked, what does it depend on.* **Nothing queries them.**
+
+### 3b. ORPHAN keys on ≥5 notes — no template, no query
+
+`source`(86) · `last_updated`(38) · `layout`(33) · `focus`(24) · `marker`(23) · `related_notes`(20) ·
+`vault_path`(19) · `depends_on`(17) · `context`(15) · `permalink`(13) · `source_type`(12) ·
+`attributed_to`(12) · `date_claimed`(12) · `first_cited`(12) · `fictional_description`(12) ·
+`chambers_cited_in`(12) · `excerpts`(12) · `weather`(12) · `temperature`(12) · `humidity`(12) ·
+`pressure`(12) · `emerged_from`(11) · `related_real_sources`(11) · `dateAdded`(11) · `lastUpdated`(11) ·
+`method`(11) · `person`(10) · `bill_number`(10) · `created_by`(9) · `address`(9) · `billing_period`(9) ·
+`dose_in`(9) · `dose_out`(9) · `pour_durations`(9) · `chat_topics`(9) · `due_date`(8) ·
+`contract_number`(8) · `organ`(7) · `currency`(7) · `meter_number`(7) · `payment_method`(7) · `cups`(7) ·
+`moon_illumination`(7) · `steward`(7) · `period`(6) · `language`(6) · `brew_time`(6) ·
+`executor-action`(6) · `body`(6) · `sources`(5) · `spiral_stage`(5) · `symbol`(5) · `provenance`(5) ·
+`domain`(5) · `sequence`(5) · `published`(5) · `tone`(5)
+
+**plus 248 orphan keys on 1–4 notes (385 instances).**
+
+### 3c. Obsidian's own property registry is effectively unused
+
+`.obsidian/types.json` declares **26** properties. Twenty-two are `TQ_*` UI toggles belonging to the
+Tasks plugin. The genuine declarations are **four**: `aliases`, `cssclasses`, `tags`, `status`. Of the
+400 keys in use, 396 have no declared type.
+
+---
+
+## 4. Folder correlation — distinct shapes do exist
+
+Five folders show a consistent, recognisable shape; the rest are mixed.
+
+- **`00. Compass`** — 84 keys / 1,836 instances. The most consistent shape in the vault:
+  `title`(190) `tags`(163) `status`(137) `type`(135) `version`(115) `canonical`(107) `owner`(99)
+  `created`(80) `assurance`(78). This is a governed-document shape and it is applied evenly.
+- **`03. People`** — 29 keys / 100 instances, tightly matching the People template:
+  `relationship`(10) `languages`(9) `dob`(9) `citizenship`(9) `family`(8) `alias`(8).
+- **`01. Daily`** — 18 keys / 69 instances: `date` `week` `month` `health` `family` `work` `reflection`.
+  Only 11 notes remain in the folder; `week`(51) and `mood`(30) live mostly in `99. Archive`, so the
+  daily practice has been archived rather than discontinued.
+- **`04. Life admin`** — 95% coverage but **120 distinct keys** over 47 notes: `bill_number`
+  `billing_period` `meter_number` `contract_number` `tariff` `power_contracted_kw` `total_amount_eur`.
+  A per-document-type shape, invented per bill rather than shared.
+- **`08. Notes`** — **188 distinct keys**, the widest in the vault, because it holds unrelated
+  populations at once: coffee logs (17-key tasting shape), book notes, CapableMind architecture notes,
+  chamber material (`attributed_to` `first_cited` `chambers_cited_in` `fictional_description`).
+- **`99. Archive`** — 1,070 notes, 11% coverage, 51 keys. Mostly ChatGPT exports carrying
+  `tags`/`type`/`aliases`/`date`/`location`/`week`/`mood`.
+
+---
+
+## 5. Template drift
+
+**23 templates.** Five carry **no frontmatter at all** — `Book_Note_Template`,
+`Document (PDF) note template`, `End of Day Checklist`, `GPT_Model_Selector_Template`,
+`Zibaldone Note Template`. Notes made from them start with no properties.
+
+**Four emit frontmatter that does not parse as YAML** — `PPP_Template`,
+`Tasting_Log_Template_Dataview`, `Tasting_Log_Template_With_Blend`, `Weekly_Coffee_Journal_Template` —
+because Templater expressions sit unquoted in value positions. Their keys had to be harvested textually.
+This is upstream of §6: a template that emits invalid YAML propagates it to every note it creates.
+
+**No template declares a key that appears on zero notes** — every declared key is in real use somewhere.
+
+**Declared-vs-actual drift**, comparing each template against its target folder:
+
+| template → folder | declared but absent | present (≥3 notes) but undeclared |
+|---|---|---|
+| Daily Note → `01. Daily` | — | `title` |
+| People → `03. People` | — | `title` |
+| Weekly_Review → `02. Reviews` | — | — |
+| Quarterly Review → `02. Reviews` | — | `last_reviewed`, `start_date`, `week` |
+| Monthly Review → `02. Reviews` | `month`, `year` | `start_date`, `week` |
+| Yearly Compass → `02. Reviews` | `year` | `last_reviewed`, `start_date`, `week` |
+| concept_thread → `08. Notes` | `vault_section` | 73 keys |
+| Tasting_Log_Dataview → `08. Notes` | — | 60 keys |
+
+> ⚠ **What this comparison can and cannot show.** A note does not record which template made it, so
+> "target folder" is a **proxy**. It is a fair proxy for `01. Daily`, `03. People` and `02. Reviews`,
+> where the folder holds one note type. It is **not** meaningful for `08. Notes`, which holds many
+> unrelated populations — the "73 undeclared keys" there is an artefact of the proxy, not drift. Read
+> those two rows as *not established*, not as a finding.
+>
+> `title` is the one clean drift signal: two templates that do not declare it, on folders where notes
+> consistently carry it.
+
+---
+
+## 6. Notes whose frontmatter is invisible — 21
+
+These parse as neither properties nor Dataview fields. Whatever they claim, **nothing can read it**:
+
+`03. People/Kai Aureli Glidden Pujolràs.md` · `03. People/Lune Polymnie Marie Glidden.md` ·
+`04. Life admin/Life Admin — To-Do Master List.md` · `98. Templates/Weekly_Coffee_Journal_Template.md` ·
+`98. Templates/PPP_Template.md` · `98. Templates/Tasting_Log_Template_With_Blend.md` ·
+`98. Templates/Tasting_Log_Template_Dataview.md` · `00a. _inbox/2025-09-13-- wild gut.md` ·
+`00. Compass/…/Animal Rationis Capax/99. Archives—Previous…` ·
+`00. Compass/…/ARC/Stubs & ideas/Lang…` · `00. Compass/…/ARC/Stubs & ideas/Fire…` ·
+`05. Work/CV-bio/Site version of CV.md` · `04. Life admin/01. DFG/04. Health/Transition Ritual/…` ·
+`04. Life admin/01. DFG/06. Passeig de Sant Joan/Facturas/Electricidad/…` ·
+`08. Notes/Reflections/The Chamber as Threshold.md` · `08. Notes/Children/02. Kai/Kai – Vaccine Record.md` ·
+`08. Notes/CapableMind/thinking-mirror/architecture/cold-start-ingestion-…` ·
+`08. Notes/Claudia Grice/05 Taxes/…/Med…` (frontmatter is a string, not a mapping) ·
+`97. Tools and Systems/04. Philosophical Curricula/Zen_Mind_Beginners_Min…` ·
+`…/Ways_of_Seeing_Berger…` · `…/The_Timeless_Way_of_Bu…`
+
+Both children's People notes are in this list.
+
+---
+
+## 7. Variants and near-duplicates
+
+### 7a. Same key, different spelling
+
+| normalised | variants (notes, verdict) |
+|---|---|
+| tag | `tags`(698, consumed) · `tag`(3, consumed) |
+| source | `source`(86, orphan) · `sources`(5, orphan) |
+| last_updated | `last_updated`(38, orphan) · `last-updated`(3, orphan) |
+| related_note | `related_notes`(20, orphan) · **`related notes`**(1) — *with a space* |
+| language | `languages`(13, written-not-read) · `language`(6, orphan) |
+| note | `note`(19) · `notes`(7) |
+| domain | `domain`(5) · `domains`(2) |
+| period | `period`(6) · `periods`(1) |
+| theme | `themes`(6, consumed) · `theme`(1, orphan) |
+| nif | `nif`(2) · `NIF`(2) |
+| consumption_kwh | `consumption_kwh`(2) · `consumption_kWh`(1) |
+| linked_note | `linked_notes`(2) · `linked_note`(1) |
+| tool | `tools`(1) · `tool`(1) |
+
+### 7b. Same job, unrelated spelling
+
+**"When was this touched" — six keys, three read, three not:**
+`last_reviewed`(123, consumed) · `last_updated`(38, **orphan**) · `updated`(14, consumed) ·
+`lastUpdated`(11, **orphan**) · `modified`(4, orphan) · `last-updated`(3, orphan).
+
+**"When was this made" — six keys:** `created`(359, consumed) · `date`(163, consumed) ·
+`dateAdded`(11, orphan) · `draft_created`(11, consumed) · `created_by`(9, orphan) · `date-created`(3, orphan).
+
+**Relations — twelve keys, three read:** `related`(120, written-not-read) · `links`(77, written-not-read) ·
+`related_notes`(20, orphan) · `superseded_by`(18, **consumed**) · `depends_on`(17, orphan) ·
+`related_real_sources`(11) · `emerged_from`(11) · `related_threads`(9, **consumed**) · `parents`(4) ·
+`relations`(3) · `linked_to`(3) · `emerged_through`(3).
+
+**Classification — seven keys, three read:** `type`(416, consumed) · `category`(52, consumed) ·
+`layout`(33, orphan) · `marker`(23, orphan) · `class`(22, consumed) · `domain`(5) · `document-type`(3).
+
+**Provenance — eight keys, two read:** `source`(86, **orphan**) · `author`(49, consumed) ·
+`origin`(34, consumed) · `source_type`(12) · `attributed_to`(12) · `first_cited`(12) · `sources`(5) ·
+`provenance`(5).
+
+**Identity:** `title`(610, consumed) · `aliases`(71, written-not-read) · `alias`(10, written-not-read) ·
+`document-title`(3) · `full_name`(2).
+
+### 7c. Three naming conventions coexist
+
+`snake_case` (dominant) · `kebab-case` (`last-updated`, `date-created`, `document-type`,
+`project-phase`, `executor-action`, `obsidian-folder`) · `camelCase` (`dateAdded`, `lastUpdated`).
+
+---
+
+## 8. Fields that are always empty
+
+`focus` — 24 notes, **null on all 24**. `mood` — 30 notes, null on 26. `virtue`, `practice`, `meaning` —
+6 notes each, null on all. `change_log` — an empty list on 38 of 89. These are declared and carried but
+never filled.
+
+---
+
+## Instrument caveats
+
+1. **"Consumed" means read by a Dataview query, a template, or Obsidian config inside this vault.** A key
+   read by an external tool, by an MCP client, by Claude, or by the steward's eye is invisible to this
+   method and would be scored ORPHAN. Every orphan verdict is therefore an **upper** bound on disuse.
+2. **`08. Notes` and `06. Projects` template-drift rows are proxy artefacts**, marked in §5 as not
+   established.
+3. **21 notes could not be parsed.** Their keys are in the textual harvest but not the shape analysis, so
+   §2's shape counts are a floor.
+4. **This is a point-in-time census**, 2026-08-19, of the vault as it stands on disk.
+
+*Raw data: `fm_inventory.json` (per-key shapes, samples, folders, file lists), `final.json`
+(per-key consumption verdicts), `templates.json` (per-template declared keys).*

obsidian/vault-frontmatter-pass1-changelog-2026-08-19.json

@@ -0,0 +1,650 @@
+[
+ {
+  "section": "\u00a71",
+  "file": "03. People/Arthur Boyntin Glidden Jr..md",
+  "line": 10,
+  "before": "sources:",
+  "after": "source:",
+  "what": "sources \u2192 source"
+ },
+ {
+  "section": "\u00a72",
+  "file": "04. Life admin/01. DFG/01. Admin/Birth certificates/DFG American Birth Certificate.md",
+  "line": 6,
+  "before": "related: [[DFG]]",
+  "after": "related: \"[[DFG]]\"",
+  "what": "nested-list \u2192 quoted link (related)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "04. Life admin/01. DFG/01. Admin/Birth certificates/DFG French Birth Certificate.md",
+  "line": 8,
+  "before": "- - DFG",
+  "after": "- DFG",
+  "what": "stray double dash \u2192 single-level list"
+ },
+ {
+  "section": "\u00a72",
+  "file": "04. Life admin/01. DFG/01. Admin/Declaration de Nationalit\u00e9 fran\u00e7aise.md",
+  "line": 6,
+  "before": "related: [[DFG]]",
+  "after": "related: \"[[DFG]]\"",
+  "what": "nested-list \u2192 quoted link (related)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "04. Life admin/01. DFG/01. Admin/Spain documents/NIE.md",
+  "line": 6,
+  "before": "related: [[dfg]]",
+  "after": "related: \"[[dfg]]\"",
+  "what": "nested-list \u2192 quoted link (related)"
+ },
+ {
+  "section": "\u00a71",
+  "file": "04. Life admin/01. DFG/05. Emergency/En cas d\u2019emerg\u00e8ncia \u2014 Catal\u00e0.md",
+  "line": 7,
+  "before": "language: ca",
+  "after": "languages: ca",
+  "what": "language \u2192 languages"
+ },
+ {
+  "section": "\u00a71",
+  "file": "04. Life admin/01. DFG/05. Emergency/En cas d\u2019urgence \u2014 fran\u00e7ais.md",
+  "line": 6,
+  "before": "language: fr",
+  "after": "languages: fr",
+  "what": "language \u2192 languages"
+ },
+ {
+  "section": "\u00a71",
+  "file": "04. Life admin/01. DFG/05. Emergency/En caso de emergencia \u2014 Espa\u00f1ol.md",
+  "line": 6,
+  "before": "language: es",
+  "after": "languages: es",
+  "what": "language \u2192 languages"
+ },
+ {
+  "section": "\u00a71",
+  "file": "04. Life admin/01. DFG/06. Passeig de Sant Joan/Facturas/Electricidad/Factura FE2400829716.md",
+  "line": 9,
+  "before": "consumption_kWh:",
+  "after": "consumption_kwh:",
+  "what": "consumption_kWh \u2192 consumption_kwh"
+ },
+ {
+  "section": "\u00a71",
+  "file": "04. Life admin/01. DFG/06. Passeig de Sant Joan/Facturas/Electricidad/Factura FE2401308373.md",
+  "line": 11,
+  "before": "NIF: \"Y7592963X\"",
+  "after": "nif: \"Y7592963X\"",
+  "what": "NIF \u2192 nif"
+ },
+ {
+  "section": "\u00a71",
+  "file": "04. Life admin/01. DFG/06. Passeig de Sant Joan/Facturas/Electricidad/Factura FE2401424574.md",
+  "line": 11,
+  "before": "NIF: \"Y7592963X\"",
+  "after": "nif: \"Y7592963X\"",
+  "what": "NIF \u2192 nif"
+ },
+ {
+  "section": "\u00a72",
+  "file": "06. Projects/Divorce-transition/Divorce_Annex_and_Statement.md",
+  "line": 5,
+  "before": "location: [[2025-06-03]]",
+  "after": "location: \"[[2025-06-03]]\"",
+  "what": "nested-list \u2192 quoted link (location)"
+ },
+ {
+  "section": "\u00a71",
+  "file": "06. Projects/Pattern, Presence, Practice/02. Pattern Language/04. Research/Pattern Interactions in A Pattern Language.md",
+  "line": 6,
+  "before": "last-updated: 2025-05-09",
+  "after": "last_updated: 2025-05-09",
+  "what": "last-updated \u2192 last_updated"
+ },
+ {
+  "section": "\u00a71",
+  "file": "06. Projects/Pattern, Presence, Practice/02. Pattern Language/04. Research/Perplexity report, Applying Christopher Alexander\u2019s Pattern Language to Violin Pedagogy.md",
+  "line": 6,
+  "before": "last-updated: 2025-05-09",
+  "after": "last_updated: 2025-05-09",
+  "what": "last-updated \u2192 last_updated"
+ },
+ {
+  "section": "\u00a71",
+  "file": "06. Projects/Pattern, Presence, Practice/02. Pattern Language/04. Research/The Interconnectedness of Patterns in Christopher Alexander's A Pattern Language.md",
+  "line": 6,
+  "before": "last-updated: 2025-05-09",
+  "after": "last_updated: 2025-05-09",
+  "what": "last-updated \u2192 last_updated"
+ },
+ {
+  "section": "\u00a71",
+  "file": "08. Notes/CapableMind/thinking-mirror/agent-circles/humanities-agents-introduction.md",
+  "line": 4,
+  "before": "tag: [PROPOSAL]",
+  "after": "tags: [PROPOSAL]",
+  "what": "tag \u2192 tags"
+ },
+ {
+  "section": "\u00a71",
+  "file": "08. Notes/CapableMind/thinking-mirror/agent-circles/humanities-agents-taxonomy.md",
+  "line": 4,
+  "before": "tag: [PROPOSAL]",
+  "after": "tags: [PROPOSAL]",
+  "what": "tag \u2192 tags"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Children/02. Kai/Administrative/2025-08-04- INSS Resolution \u2014 Healthcare Coverage for Kai.md",
+  "line": 5,
+  "before": "related: [[Kai Aureli Glidden Pujolr\u00e0s]]",
+  "after": "related: \"[[Kai Aureli Glidden Pujolr\u00e0s]]\"",
+  "what": "nested-list \u2192 quoted link (related)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Children/02. Kai/Administrative/Empadronament \u2014 Kai Aureli Glidden Pujolr\u00e1s.md",
+  "line": 7,
+  "before": "related: [[Kai Aureli]]",
+  "after": "related: \"[[Kai Aureli]]\"",
+  "what": "nested-list \u2192 quoted link (related)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Children/02. Kai/Health/00. Discernment Framework for Engaging with Homeopathic Pediatrics.md",
+  "line": 5,
+  "before": "version: 1.0",
+  "after": "version: \"1.0\"",
+  "what": "version quoted to str"
+ },
+ {
+  "section": "\u00a71",
+  "file": "08. Notes/Children/02. Kai/Health/00. Discernment Framework for Engaging with Homeopathic Pediatrics.md",
+  "line": 9,
+  "before": "sources:",
+  "after": "source:",
+  "what": "sources \u2192 source"
+ },
+ {
+  "section": "\u00a71",
+  "file": "08. Notes/Children/02. Kai/Health/Vaccine info and studies/Kai \u2014 Vaccination - Big Four + Rotavirus (Catalonia 2025).md",
+  "line": 12,
+  "before": "sources:",
+  "after": "source:",
+  "what": "sources \u2192 source"
+ },
+ {
+  "section": "\u00a71",
+  "file": "08. Notes/Claudia Grice/00 Dashboard.md",
+  "line": 8,
+  "before": "related notes:",
+  "after": "related_notes:",
+  "what": "related notes \u2192 related_notes"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Coffee/coffee_logs/2025-06-04_Coffee_Log.md",
+  "line": 12,
+  "before": "brew_temp: [[94\u201396\u00b0C]]",
+  "after": "brew_temp: \"[[94\u201396\u00b0C]]\"",
+  "what": "nested-list \u2192 quoted link (brew_temp)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Coffee/coffee_logs/2025-06-05_Coffee_Log.md",
+  "line": 12,
+  "before": "brew_temp: [[94\u201396\u00b0C]]",
+  "after": "brew_temp: \"[[94\u201396\u00b0C]]\"",
+  "what": "nested-list \u2192 quoted link (brew_temp)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Coffee/coffee_logs/2025-06-11_Coffee_Log.md",
+  "line": 12,
+  "before": "brew_temp: [[94\u201396\u00b0C]]",
+  "after": "brew_temp: \"[[94\u201396\u00b0C]]\"",
+  "what": "nested-list \u2192 quoted link (brew_temp)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Coffee/coffee_logs/2025-06-12_Coffee_Log.md",
+  "line": 27,
+  "before": "brew_temp: [[94\u201396\u00b0C]]",
+  "after": "brew_temp: \"[[94\u201396\u00b0C]]\"",
+  "what": "nested-list \u2192 quoted link (brew_temp)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Coffee/coffee_recipes/Moccamaster Protocol \u2013 Daily Brew.md",
+  "line": 5,
+  "before": "created: [[2025-07-08]]",
+  "after": "created: \"[[2025-07-08]]\"",
+  "what": "nested-list \u2192 quoted link (created)"
+ },
+ {
+  "section": "\u00a71",
+  "file": "08. Notes/Listening notes/Grief & Disintegration \u2013 Listening Pathway.md",
+  "line": 4,
+  "before": "theme: [grief, emotional processing, ambient]",
+  "after": "themes: [grief, emotional processing, ambient]",
+  "what": "theme \u2192 themes"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Reflections/Carl Jung \u2013 The Red Book.md",
+  "line": 7,
+  "before": "- [[Reflection on Parmenides Opening Fragment]]",
+  "after": "- \"[[Reflection on Parmenides Opening Fragment]]\"",
+  "what": "nested-list \u2192 quoted link (list item)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Reflections/Carl Jung \u2013 The Red Book.md",
+  "line": 8,
+  "before": "- [[Gaston Bachelard \u2013 Thresholds and Spaces]]",
+  "after": "- \"[[Gaston Bachelard \u2013 Thresholds and Spaces]]\"",
+  "what": "nested-list \u2192 quoted link (list item)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Reflections/Carl Jung \u2013 The Red Book.md",
+  "line": 9,
+  "before": "- [[Rilke \u2013 Duino Elegies]]",
+  "after": "- \"[[Rilke \u2013 Duino Elegies]]\"",
+  "what": "nested-list \u2192 quoted link (list item)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Reflections/Dante \u2013 Inferno I.md",
+  "line": 7,
+  "before": "- [[Reflection on Parmenides Opening Fragment]]",
+  "after": "- \"[[Reflection on Parmenides Opening Fragment]]\"",
+  "what": "nested-list \u2192 quoted link (list item)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Reflections/Dante \u2013 Inferno I.md",
+  "line": 8,
+  "before": "- [[Plato \u2013 Phaedrus]]",
+  "after": "- \"[[Plato \u2013 Phaedrus]]\"",
+  "what": "nested-list \u2192 quoted link (list item)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Reflections/Dante \u2013 Inferno I.md",
+  "line": 9,
+  "before": "- [[William Blake \u2013 Marriage of Heaven and Hell]]",
+  "after": "- \"[[William Blake \u2013 Marriage of Heaven and Hell]]\"",
+  "what": "nested-list \u2192 quoted link (list item)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Reflections/Gaston Bachelard \u2013 Thresholds and Spaces.md",
+  "line": 7,
+  "before": "- [[Reflection on Parmenides Opening Fragment]]",
+  "after": "- \"[[Reflection on Parmenides Opening Fragment]]\"",
+  "what": "nested-list \u2192 quoted link (list item)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Reflections/Gaston Bachelard \u2013 Thresholds and Spaces.md",
+  "line": 8,
+  "before": "- [[Carl Jung \u2013 The Red Book]]",
+  "after": "- \"[[Carl Jung \u2013 The Red Book]]\"",
+  "what": "nested-list \u2192 quoted link (list item)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Reflections/Parmenides Opening Fragment.md",
+  "line": 15,
+  "before": "- [[Path of Knowing]]",
+  "after": "- \"[[Path of Knowing]]\"",
+  "what": "nested-list \u2192 quoted link (list item)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Reflections/Parmenides Opening Fragment.md",
+  "line": 16,
+  "before": "- [[Philosophical Poetics]]",
+  "after": "- \"[[Philosophical Poetics]]\"",
+  "what": "nested-list \u2192 quoted link (list item)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Reflections/Parmenides Opening Fragment.md",
+  "line": 17,
+  "before": "- [[Fragments as Form]]",
+  "after": "- \"[[Fragments as Form]]\"",
+  "what": "nested-list \u2192 quoted link (list item)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Reflections/Parmenides Opening Fragment.md",
+  "line": 18,
+  "before": "- [[Plato \u2013 Phaedrus]]",
+  "after": "- \"[[Plato \u2013 Phaedrus]]\"",
+  "what": "nested-list \u2192 quoted link (list item)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Reflections/Parmenides Opening Fragment.md",
+  "line": 19,
+  "before": "- [[Upanishads \u2013 Katha]]",
+  "after": "- \"[[Upanishads \u2013 Katha]]\"",
+  "what": "nested-list \u2192 quoted link (list item)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Reflections/Parmenides Opening Fragment.md",
+  "line": 20,
+  "before": "- [[Dante \u2013 Inferno I]]",
+  "after": "- \"[[Dante \u2013 Inferno I]]\"",
+  "what": "nested-list \u2192 quoted link (list item)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Reflections/Parmenides Opening Fragment.md",
+  "line": 21,
+  "before": "- [[William Blake \u2013 Marriage of Heaven and Hell]]",
+  "after": "- \"[[William Blake \u2013 Marriage of Heaven and Hell]]\"",
+  "what": "nested-list \u2192 quoted link (list item)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Reflections/Parmenides Opening Fragment.md",
+  "line": 22,
+  "before": "- [[Gaston Bachelard \u2013 Thresholds and Spaces]]",
+  "after": "- \"[[Gaston Bachelard \u2013 Thresholds and Spaces]]\"",
+  "what": "nested-list \u2192 quoted link (list item)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Reflections/Parmenides Opening Fragment.md",
+  "line": 23,
+  "before": "- [[Carl Jung \u2013 The Red Book]]",
+  "after": "- \"[[Carl Jung \u2013 The Red Book]]\"",
+  "what": "nested-list \u2192 quoted link (list item)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Reflections/Parmenides Opening Fragment.md",
+  "line": 24,
+  "before": "- [[Rilke \u2013 Duino Elegies]]",
+  "after": "- \"[[Rilke \u2013 Duino Elegies]]\"",
+  "what": "nested-list \u2192 quoted link (list item)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Reflections/Plato \u2013 Phaedrus.md",
+  "line": 7,
+  "before": "- [[Reflection on Parmenides Opening Fragment]]",
+  "after": "- \"[[Reflection on Parmenides Opening Fragment]]\"",
+  "what": "nested-list \u2192 quoted link (list item)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Reflections/Plato \u2013 Phaedrus.md",
+  "line": 8,
+  "before": "- [[Upanishads \u2013 Katha]]",
+  "after": "- \"[[Upanishads \u2013 Katha]]\"",
+  "what": "nested-list \u2192 quoted link (list item)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Reflections/Plato \u2013 Phaedrus.md",
+  "line": 9,
+  "before": "- [[Dante \u2013 Inferno I]]",
+  "after": "- \"[[Dante \u2013 Inferno I]]\"",
+  "what": "nested-list \u2192 quoted link (list item)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Reflections/Rilke \u2013 Duino Elegies.md",
+  "line": 7,
+  "before": "- [[Reflection on Parmenides Opening Fragment]]",
+  "after": "- \"[[Reflection on Parmenides Opening Fragment]]\"",
+  "what": "nested-list \u2192 quoted link (list item)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Reflections/Rilke \u2013 Duino Elegies.md",
+  "line": 8,
+  "before": "- [[Carl Jung \u2013 The Red Book]]",
+  "after": "- \"[[Carl Jung \u2013 The Red Book]]\"",
+  "what": "nested-list \u2192 quoted link (list item)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Reflections/Upanishads \u2013 Katha.md",
+  "line": 7,
+  "before": "- [[Reflection on Parmenides Opening Fragment]]",
+  "after": "- \"[[Reflection on Parmenides Opening Fragment]]\"",
+  "what": "nested-list \u2192 quoted link (list item)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Reflections/Upanishads \u2013 Katha.md",
+  "line": 8,
+  "before": "- [[Plato \u2013 Phaedrus]]",
+  "after": "- \"[[Plato \u2013 Phaedrus]]\"",
+  "what": "nested-list \u2192 quoted link (list item)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Reflections/William Blake \u2013 Marriage of Heaven and Hell.md",
+  "line": 7,
+  "before": "- [[Reflection on Parmenides Opening Fragment]]",
+  "after": "- \"[[Reflection on Parmenides Opening Fragment]]\"",
+  "what": "nested-list \u2192 quoted link (list item)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Reflections/William Blake \u2013 Marriage of Heaven and Hell.md",
+  "line": 8,
+  "before": "- [[Dante \u2013 Inferno I]]",
+  "after": "- \"[[Dante \u2013 Inferno I]]\"",
+  "what": "nested-list \u2192 quoted link (list item)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "08. Notes/Tools & Workflow/Travel_Power_Kit_Evergoods_1L.md",
+  "line": 8,
+  "before": "version: 1.2",
+  "after": "version: \"1.2\"",
+  "what": "version quoted to str"
+ },
+ {
+  "section": "\u00a72",
+  "file": "97. Tools and Systems/02. Workflows & Promptcraft/GPT_Promptcraft_Framework.md",
+  "line": 4,
+  "before": "version: 1.0",
+  "after": "version: \"1.0\"",
+  "what": "version quoted to str"
+ },
+ {
+  "section": "\u00a73",
+  "file": "98. Templates/PPP_Template.md",
+  "line": 3,
+  "before": "created: {{date:YYYY-MM-DD}}",
+  "after": "created: \"{{date:YYYY-MM-DD}}\"",
+  "what": "template YAML validity"
+ },
+ {
+  "section": "\u00a73",
+  "file": "98. Templates/PPP_Template.md",
+  "line": 6,
+  "before": "related: [[P3 Pattern Index]], [[Pattern, Presence, Practice base document]]",
+  "after": "related: [\"[[P3 Pattern Index]]\", \"[[Pattern, Presence, Practice base document]]\"]",
+  "what": "template YAML validity"
+ },
+ {
+  "section": "\u00a73",
+  "file": "98. Templates/Tasting_Log_Template_Dataview.md",
+  "line": 2,
+  "before": "date: {{date}}",
+  "after": "date: \"{{date}}\"",
+  "what": "template YAML validity"
+ },
+ {
+  "section": "\u00a73",
+  "file": "98. Templates/Tasting_Log_Template_With_Blend.md",
+  "line": 2,
+  "before": "date: {{date}}",
+  "after": "date: \"{{date}}\"",
+  "what": "template YAML validity"
+ },
+ {
+  "section": "\u00a73",
+  "file": "98. Templates/Weekly_Coffee_Journal_Template.md",
+  "line": 2,
+  "before": "week_of: {{date:YYYY-MM-DD}}",
+  "after": "week_of: \"{{date:YYYY-MM-DD}}\"",
+  "what": "template YAML validity"
+ },
+ {
+  "section": "\u00a72",
+  "file": "99. Archive/07. Reading/Currently reading/A Philosophy of Walking.md",
+  "line": 7,
+  "before": "superseded_by: [[Master_Reading_Index]]",
+  "after": "superseded_by: \"[[Master_Reading_Index]]\"",
+  "what": "nested-list \u2192 quoted link (superseded_by)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "99. Archive/07. Reading/Currently reading/Angelmaker.md",
+  "line": 7,
+  "before": "superseded_by: [[Master_Reading_Index]]",
+  "after": "superseded_by: \"[[Master_Reading_Index]]\"",
+  "what": "nested-list \u2192 quoted link (superseded_by)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "99. Archive/07. Reading/Currently reading/Essayism.md",
+  "line": 7,
+  "before": "superseded_by: [[Master_Reading_Index]]",
+  "after": "superseded_by: \"[[Master_Reading_Index]]\"",
+  "what": "nested-list \u2192 quoted link (superseded_by)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "99. Archive/07. Reading/Currently reading/Insomniac Dreams Experiments With Time.md",
+  "line": 5,
+  "before": "superseded_by: [[Master_Reading_Index]]",
+  "after": "superseded_by: \"[[Master_Reading_Index]]\"",
+  "what": "nested-list \u2192 quoted link (superseded_by)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "99. Archive/07. Reading/Currently reading/M\u00e9moires d'Hadrien Marguerite Yourcenar.md",
+  "line": 5,
+  "before": "superseded_by: [[Master_Reading_Index]]",
+  "after": "superseded_by: \"[[Master_Reading_Index]]\"",
+  "what": "nested-list \u2192 quoted link (superseded_by)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "99. Archive/07. Reading/Currently reading/Sol\u00e9no\u00efde.md",
+  "line": 5,
+  "before": "superseded_by: [[Master_Reading_Index]]",
+  "after": "superseded_by: \"[[Master_Reading_Index]]\"",
+  "what": "nested-list \u2192 quoted link (superseded_by)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "99. Archive/07. Reading/Currently reading/The Canterbury Tales A Retelling.md",
+  "line": 5,
+  "before": "superseded_by: [[Master_Reading_Index]]",
+  "after": "superseded_by: \"[[Master_Reading_Index]]\"",
+  "what": "nested-list \u2192 quoted link (superseded_by)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "99. Archive/07. Reading/Currently reading/The Gone-Away World.md",
+  "line": 5,
+  "before": "superseded_by: [[Master_Reading_Index]]",
+  "after": "superseded_by: \"[[Master_Reading_Index]]\"",
+  "what": "nested-list \u2192 quoted link (superseded_by)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "99. Archive/07. Reading/Reading lists/2025-08-24 Fiction Suggestions after Angelmaker & Piranesi.md",
+  "line": 7,
+  "before": "superseded_by: [[Master_Reading_Index]]",
+  "after": "superseded_by: \"[[Master_Reading_Index]]\"",
+  "what": "nested-list \u2192 quoted link (superseded_by)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "99. Archive/07. Reading/Reading lists/2025-08-24 Master reading list.md",
+  "line": 7,
+  "before": "superseded_by: [[Master_Reading_Index]]",
+  "after": "superseded_by: \"[[Master_Reading_Index]]\"",
+  "what": "nested-list \u2192 quoted link (superseded_by)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "99. Archive/07. Reading/Reading lists/2025-08-24 Missing Pillars Reading List.md",
+  "line": 6,
+  "before": "superseded_by: [[Master_Reading_Index]]",
+  "after": "superseded_by: \"[[Master_Reading_Index]]\"",
+  "what": "nested-list \u2192 quoted link (superseded_by)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "99. Archive/07. Reading/Reading lists/Christopher Alexander's Published Works.md",
+  "line": 6,
+  "before": "superseded_by: [[Master_Reading_Index]]",
+  "after": "superseded_by: \"[[Master_Reading_Index]]\"",
+  "what": "nested-list \u2192 quoted link (superseded_by)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "99. Archive/07. Reading/Reading lists/Chuck Wendig reading list.md",
+  "line": 6,
+  "before": "superseded_by: [[Master_Reading_Index]]",
+  "after": "superseded_by: \"[[Master_Reading_Index]]\"",
+  "what": "nested-list \u2192 quoted link (superseded_by)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "99. Archive/07. Reading/Reading lists/Comprehensive Science Reading List - From Cosmos to Consciousness.md",
+  "line": 3,
+  "before": "superseded_by: [[Master_Reading_Index]]",
+  "after": "superseded_by: \"[[Master_Reading_Index]]\"",
+  "what": "nested-list \u2192 quoted link (superseded_by)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "99. Archive/07. Reading/Reading lists/Foundational thinkers.md",
+  "line": 8,
+  "before": "superseded_by: [[Master_Reading_Index]]",
+  "after": "superseded_by: \"[[Master_Reading_Index]]\"",
+  "what": "nested-list \u2192 quoted link (superseded_by)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "99. Archive/07. Reading/Reading lists/Reading List \u2014 L\u00e1szl\u00f3 Krasznahorkai.md",
+  "line": 7,
+  "before": "superseded_by: [[Master_Reading_Index]]",
+  "after": "superseded_by: \"[[Master_Reading_Index]]\"",
+  "what": "nested-list \u2192 quoted link (superseded_by)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "99. Archive/07. Reading/Reading lists/To find and add to library.md",
+  "line": 3,
+  "before": "superseded_by: [[Master_Reading_Index]]",
+  "after": "superseded_by: \"[[Master_Reading_Index]]\"",
+  "what": "nested-list \u2192 quoted link (superseded_by)"
+ },
+ {
+  "section": "\u00a72",
+  "file": "99. Archive/07. Reading/Reading lists/Virginia_Woolf_Reading_List.md",
+  "line": 8,
+  "before": "superseded_by: [[Master_Reading_Index]]",
+  "after": "superseded_by: \"[[Master_Reading_Index]]\"",
+  "what": "nested-list \u2192 quoted link (superseded_by)"
+ }
+]

obsidian/vault-frontmatter-pass1-followups-2026-08-19.md

@@ -0,0 +1,93 @@
+---
+name: obsidian-vault-frontmatter-pass1-followups-2026-08-19
+description: Read-only surfacing of the four items held back from frontmatter pass 1 — the 8 assurance strings, the prose tag, the three shape-disagreeing pairs, and the canonical path/flag split. Nothing decided, nothing changed.
+type: reference
+---
+
+# Pass 1 follow-ups — surfaced, not decided
+
+2026-08-19, at the jurist's request. **Read-only. No vault file was changed by this pass.**
+
+## 1 · The 8 `assurance` strings
+
+| value | note |
+|---|---|
+| `medium` | 08. Notes/Reflections/Parmenides Opening Fragment |
+| `high` | 08. Notes/Tools & Workflow/Travel_Power_Kit_Evergoods_1L |
+| `high` | 07. Learn/Reading/00. Master_Reading_Index |
+| `high` | 07. Learn/Reading/01. Polestars/Berger — Ways of Seeing |
+| `high` | 07. Learn/Reading/01. Polestars/Bachelard — The Poetics of Space |
+| `high` | 07. Learn/Reading/01. Polestars/Alexander — The Timeless Way |
+| `high` | 07. Learn/Reading/01. Polestars/Tolkien — The Long Road and the Ring |
+| `high` | 99. Archive/07. Reading/Reading lists/Reading List — László Krasznahorkai |
+
+Seven `high`, one `medium`. Five of eight are the Reading polestars — one cluster, one habit, not
+eight independent decisions. The dict form's `evidence_level` takes a *kind* vocabulary
+(experiential · design · practice · strong · mixed · cohort · narrative), so `high`/`medium` is a
+**confidence scale that the dict has no slot for**.
+
+## 2 · The prose `tag`
+
+- **Note:** `08. Notes/CapableMind/thinking-mirror/agent-circles/agent-circle-ARC-survey-2026-04-23.md`
+- **Value:** `tag: survey / scoping material; no spec commitments`
+- **Other keys:** `created`, `status`, `origin`, `related`, `steward`, `executor-action`
+- **Has no `tags` key at all.**
+
+It is a scope disclaimer written into the key named `tag`. Nothing about it is a tag.
+
+## 3 · The three pairs — same question as `note`/`notes`
+
+**`domains` / `domain` — ONE thing, inconsistently typed.** Both classify the same way; the plural
+is used where there are several values and the singular where there is one.
+- `domain` (5): `personal_care` ×3, `language-ecology`, `beverage-ecology`
+- `domains` (2): `[historically_informed_performance, violin_and_viola_technique, …]`, `[music, pedagogy, philosophy]`
+
+**`periods` / `period` — TWO things.**
+- `period` (6) is a **date range as prose**: `1912–1922` · `c. 800–400 BCE` · `2024-01-04 to 2024-02-05`
+- `periods` (1) is a **structured schedule**: `[{name: Late Autumn 2025, months: [...], ...}]`
+
+**`linked_note` / `linked_notes` — two things, and the singular belongs to a third key.**
+- `linked_notes` (2) is a list of note names: `[00_Historical_Disease_Profiles_Index, Vaccination Conversations Index]`
+- `linked_note` (1) is `[[2025-06-12]]` on a coffee log — **a daily-note link**, which is what
+  `linked_daily_note` (2 notes) already means. Its nearest neighbour is not the key it was proposed
+  to merge into.
+
+## 4 · `canonical` — what it actually is, across 161 notes
+
+| form | count |
+|---|---|
+| path-like string | **157** |
+| real YAML boolean (`true`) | 3 |
+| `'INDEX.yml'` (points at a non-markdown file) | 1 |
+
+**The semantic split — the jurist's question.** Read by whether the value names the note's own file:
+
+| reading | count |
+|---|---|
+| **self-descriptive** — names its own basename: *"I am canonical, and I live here"* | **91** |
+| **pointer** — names a *different* note: *"the canonical version is over there"* | **66** |
+| **pure flag** — bare `true`, no address | 3 |
+
+So the key carries at least three jobs, and the two large ones are not variants of each other: one
+is a self-assertion of authority, the other is a redirect away from it. A query filtering
+`WHERE canonical` would treat all three as true.
+
+**Pointer integrity, tested at four strictnesses:**
+
+| | count |
+|---|---|
+| exact path match — correct as written | **6** |
+| case-insensitive match only | 0 |
+| **basename exists, path is wrong** (note moved) | **88** |
+| **unresolvable — no note of that name anywhere** | **63** |
+
+⚠ **A correction to what the executor reported earlier today.** The first pass at this used an
+exact-path matcher and reported *"151 do not resolve"*. That number is right about the **paths** and
+wrong about the **notes**: 88 of the 151 name a note that still exists at a different location. The
+honest statement is **151 of 157 paths are stale as written, and 63 name nothing at all** — the
+field is *stale*, not *dead*, and those are different problems with different remedies. The error
+was a resolver too strict for the claim it was being cited for; caught by testing the resolver
+before quoting its output.
+
+**Not proposed, not decided.** Recorded so the governance-block conversation starts from the
+substrate rather than from the census.

obsidian/vault-governance-block-round2-2026-08-19.md

@@ -0,0 +1,211 @@
+---
+name: obsidian-vault-governance-block-round2-2026-08-19
+description: Read-only round-2 investigation of owner, related, change_log and links, plus a faithful account of AldineXXI's frontmatter specification. Findings only; nothing proposed, nothing decided, nothing changed.
+type: reference
+---
+
+# Governance block, round 2 — `owner` · `related` · `change_log` · `links`
+
+2026-08-19. **Read-only. No vault file was changed.** Same method as the `canonical`/`assurance`
+follow-up. Findings only.
+
+---
+
+## 1 · `owner` (153) — one job, three spellings, zero discrimination
+
+| value | notes |
+|---|---:|
+| `David Glidden` | 136 |
+| `David` | 12 |
+| `David F. Glidden` | 5 |
+
+**Three distinct values across 153 notes, all naming the same person.** The key does one job
+consistently — and the job is constant. A field whose value never varies partitions nothing; a
+`GROUP BY owner` returns three groups that are one person spelled three ways.
+
+Unlike `canonical`, there is no second meaning hiding here. The finding is the opposite shape: not
+*more* than its count suggested, but *less*.
+
+## 2 · `change_log` (89) — real content, four incompatible schemas
+
+| | count |
+|---|---:|
+| empty list / null | **38** |
+| carrying content | **51** |
+
+The 51 are real and substantive (`{date: 2025-09-28, change: 'Created alias stub pointing to
+canonical Learning & Mind organ', by: 'David'}`). But they use **four different entry shapes**:
+
+| entry keys | count |
+|---|---:|
+| `(by, change, date)` | 26 |
+| `(change, date)` | 11 |
+| `(date, note)` | 11 |
+| `(date, summary, version)` | 2 |
+| ⚠ `(datetime.date(2025,10,12),)` — the **date became the key** | 1 |
+
+So the answer to *"template nobody filled in, or real content worth keeping?"* is **both, unevenly**:
+43% empty, 57% real, and the real half is four conventions rather than one. `change` / `note` /
+`summary` are three names for the same slot; `by` is present on half of one schema and absent
+everywhere else, recording an author who — per §1 — is invariant.
+
+## 3 · `related` (121 instances, 442 link targets)
+
+**Pointer integrity**, case-insensitive, tested at four strictnesses:
+
+| | count | |
+|---|---:|---:|
+| note name resolves | 215 | 48% |
+| matches an alias or title | 17 | 3% |
+| **unresolvable** | **210** | **47%** |
+
+**Two link conventions, and the minority one is the working one.** 57 targets are wikilink-wrapped
+(`'[[P3 Pattern Index]]'`); **385 are bare strings** (`'White Abstraction – Moy Glidden'`). A bare
+string in frontmatter is not a link in Obsidian — so **87% of `related` entries do not produce a
+clickable relation**, whatever they resolve to.
+
+**A third job, as with `canonical`.** Some targets are **people, not notes** — `Divorce.md` carries
+`related: [Lune, Marie, Briac Prud'homme]`. These are unresolvable not because the link is stale but
+because the referent was never a document. Relating-to-a-person and relating-to-a-note are different
+operations sharing one field.
+
+## 4 · `links` (77 instances, 286 link targets)
+
+**Six dict schemas:**
+
+| keys | count |
+|---|---:|
+| `(children, parents, peers)` | 31 |
+| `(parents, peers)` | 23 |
+| `(related,)` | 6 |
+| `(children, parents)` | 5 |
+| `(canonical,)` | 4 |
+| `(parents,)` | 4 |
+
+⚠ **`links` contains sub-keys that duplicate two other top-level governance fields.** Four notes
+carry `links: {canonical: [[...]]}` while `canonical` also exists as a top-level key on 161 notes;
+six carry `links: {related: ...}` against a top-level `related` on 121. The same relation can be
+expressed in two places, and nothing reconciles them.
+
+**Pointer integrity:**
+
+| | count | |
+|---|---:|---:|
+| full path resolves | 1 | 0% |
+| note name resolves | 122 | 42% |
+| matches an alias or title | 72 | 25% |
+| **unresolvable** | **91** | **31%** |
+
+⚠ **The alias/title tier is load-bearing and was nearly missed.** A first pass without it reported
+163 unresolvable (57%); adding alias and title matching moved that to 91 (31%). The stricter figure
+would have overstated decay by nearly two to one. Same resolver-too-strict error as the `canonical`
+"151 dead" number this morning, caught this time before it was quoted.
+
+**Some targets address a vault structure that does not exist here** — `places/pine-street`,
+`people/moy-glidden`, `people/abg`, `GLOSSARY.md`, all from `00. Atlas of Roots — Index.md`. That is
+not a stale path; it is a path shaped for a different repository layout.
+
+---
+
+# The AldineXXI Frontmatter specification — faithful account
+
+`~/_Dev/animal-davidglidden-eu/docs/AldineXXI-Codex/frontmatter-specification.md` · 310 lines /
+3,268 words · **Status: OPERATIVE 2026-05-22**, drafted 2026-04-17.
+
+**Scope:** every markdown document under `content/`. Stated as *"the contract between the author (at
+writing time), the versioning system (at revision time), and Hakyll (at build time). Publishing a new
+piece or revising an existing one should not require re-deciding frontmatter shape."* The document
+declares itself the canonical record, expects to evolve, and rules that pre-convention pieces may be
+backfilled or carry less metadata — *"graceful degradation rather than demanded completeness."*
+
+### §1 Design principles (five, verbatim in substance)
+
+1. **Minimal required surface.** A new essay needs only `title`, `date`, `class`. Everything else is
+   opt-in, driven by what the piece needs.
+2. **Dates, not versions.** YYYY-MM-DD throughout. No semver, no `v1.0.0`.
+3. **Public-facing naming.** Field names appear in templates and occasionally in prose; they should
+   be legible to a reader who sees them. No internal jargon.
+4. **Flat where possible, nested when justified.** Nesting only where the structure is load-bearing.
+5. **Private editorial notes stay private.** Author's stance, intent or mode live in separate notes
+   files, not published frontmatter — *"What's in the frontmatter is what the publication stands
+   behind."*
+
+### §2 Field reference
+
+- **§2.1 Identity (always present):** `title` (req), `date` (req, ISO — the **origin date**, stable
+  through all revisions, drives archive location), `class` (req, one of 14 content types),
+  `location` (opt, city-level), `slug` (opt, routing override).
+- **§2.2 Sequence membership:** `sequence`, `sequence_short`, `sequence_order`, `sequence_slug`,
+  `sequence_order_roman`, `preceded_by`, `followed_by`. Carries a **known latent defect** — the
+  sequence marker's total is hardcoded `"of V"` and is ruled to become build-derived.
+- **§2.3 Versioning:** `revisions` (chronological list of `{date, location?, summary?}`),
+  `edition_label`, `recants`, `recanted_by`. Two are explicitly **forward fields** kept without
+  carriers.
+- **§2.4 Content metadata:** `description` is the operative field the build reads; `summary` is
+  retained as drafted but **not read** by the head template. `description` is required for Essay and
+  Observation, soft-required elsewhere.
+- **§2.6 Language [2026-05-14]:** `lang` (ISO 639-1, defaults `en`), `lang_secondary` (list). Three
+  contexts: French-primary, English-primary-with-passages, genuinely bilingual.
+- **§2.7 Medium [2026-05-20]:** `medium`, orthogonal to `class`; `verse` the first non-default value,
+  which *"surfaces because the corpus produced an instance"* rather than by anticipation.
+- **§2.8 Translated renderings [2026-06-05]:** `work` (slug of the work this piece renders),
+  `translator` (absent = the author's own rendering; **absence is the signal**). The work file carries
+  no `work:` field — it *is* the work.
+
+### §2.4's prune — the precedent most directly on point
+
+**Four documented-but-unread fields removed (W1.12, 2026-06-07)**, on the stated ground that *"the
+audit found zero readers in the build for each"*: `comments`, `epigraph`, `philosophical_lineage`,
+`related_texts`. The disposition rule: *"Legacy carriers degrade gracefully (unread fields are inert);
+strip them on touch. Re-entry of any of these is a new convention decision, not a revival."*
+
+### §3 — the iA Writer → ARC translation table
+
+⚠ **Surfaced without comment, because it names this investigation's fields directly.** The table
+rules on each Obsidian-side field it encounters:
+
+| Obsidian field | ARC disposition, as written |
+|---|---|
+| `change_log` (list of `{date, change}`) | → `revisions:` list, one entry per item; `change` → `summary` |
+| `last_updated` / `last_modified` / `last_reviewed` | → a single `revisions:` entry with that date |
+| `canonical: "03. Writings/..."` | **Drop.** *"Obsidian path — private authoring metadata."* |
+| `assurance: {evidence_level, risk_flags, scope}` | **Drop.** *"Private editorial metadata."* |
+| `status: canonical` | **Drop.** *"Publication IS canonicalization."* |
+| `author` | **Drop.** *"Every piece is by the same author."* |
+| `version` (semver) | **Drop.** *"Per ADR-005: dates, not versions."* |
+| `type: essay` | **Drop.** *"Use `class:` instead."* |
+| `project` | **Drop.** *"Redundant — every piece in this repo is ARC."* |
+| `tags` | **Drop.** Retired 2026-05-20; *"topical organization is carried by `class:` and the corpus enfilade, not by tag indexes."* |
+| `related_texts` (Obsidian `[[...]]` links) | **Drop.** Pruned; the anticipated rendering was never built |
+| `relations: preceded_by` / `followed_by` | Flatten to top level; **use slug not title** |
+| `review_cycle` | **Drop.** *"Private editorial metadata."* |
+| `notes: {intent, stance, mode}` | **Drop from public frontmatter.** *"Preserve in separate private notes file if wanted."* |
+| `subproject` | **Drop.** *"`sequence:` carries the same information publicly."* |
+| `external_references` | **Drop.** *"External citations belong in the text, not in frontmatter."* |
+| `language` | → `lang:` (ISO 639-1) |
+| `languages` | decompose per §2.8 into one work + N renderings |
+
+### §4–§6 Recipes
+
+Publish (decide `class` → create `content/{class-folder}/YYYY-MM-DD-slug.md` → required frontmatter →
+optional fields → write → `make build` → commit). Revise (`make revise` → edit → **append** a
+`revisions:` entry → build → commit new current + dated snapshot together). Recant (write the
+retractation-piece with `recants:`, add `recanted_by:` to the original, commit both together).
+
+### §7 What is deliberately NOT in the frontmatter
+
+Word count / reading time (derivable) · **last-modified auto-timestamps** (*"Misleading (git tracks
+this; the frontmatter should reflect publication events, not filesystem touches)"*) · author name ·
+license · copyright year · OG/Twitter card metadata.
+
+### §8 Open questions
+
+Three of four are struck through as resolved (slug canonicalization; translated pieces; epigraph
+rendering). One remains live: **sequence wrapper pages** — the running page uses
+`class: sequence-index`, a working convention outside the 14-type enumeration, *"not yet ratified"*.
+The section closes: *"These do not block publishing under the current convention."*
+
+---
+
+**Nothing above is proposed or decided.** The reading of the spec against the vault findings is the
+jurist's, not the executor's.

obsidian/vault-round3-archive-and-relations-2026-08-19.md

@@ -0,0 +1,178 @@
+---
+name: obsidian-vault-round3-archive-and-relations-2026-08-19
+description: Read-only round 3 — related's person-targets, Atlas of Roots context, what already distinguishes 99. Archive, and the search for the Chamber library-curation pattern-language document. Findings only.
+type: reference
+---
+
+# Round 3 — relations, Atlas of Roots, and what Archive already is
+
+2026-08-19. **Read-only. Nothing in the vault was changed.** Findings only.
+
+---
+
+## 1 · `related`'s person-targets — narrower than I implied
+
+Every one of the 442 `related` targets was matched mechanically against a **People index** built from
+all 21 People notes and every identity string they answer to (filename stem, `title`, `full_name`,
+`alias`, `aliases` — 32 identity strings in total). No judgement about which "look like" people.
+
+| | count |
+|---|---:|
+| resolves to a note, and matches a People note | 5 |
+| resolves to a note, no People match | 210 |
+| resolves to nothing, no People match | 227 |
+
+**⚠ This corrects the impression I left in round 2.** I reported that `related` carries "a third job —
+relating to a person rather than a document," generalising from `Divorce.md`'s three targets. Run
+across the full set, **the person-targets are those three and essentially nothing else.** A
+person-name-shaped filter over the unresolvable targets returns 79 distinct strings, but almost all
+are **title-case document names**, not people: `Presence Before Performance` ×14, `Pattern` ×12,
+`Practice` ×12, `Look Again`, `Limits Are Sacred`, `The Chamber Standard Protocol`. The third job is
+real but rare — one note, not a pattern.
+
+**The three, individually:**
+
+| target | status |
+|---|---|
+| `Lune` | ⚠ **A People note exists** — `03. People/Lune Polymnie Marie Glidden.md` — but its `alias:` is `[Lulu]`. The short name actually used in `related` is not among its registered identities, so the link fails on a note that is present. |
+| `Marie` | No People note. She *is* declared elsewhere: Lune's own note carries `family: [[Marie]], [[DFG]], [[Kai…\|Kai]]` — so Marie is a linked family member with no note behind the link. |
+| `Briac Prud'homme` | No note, no reference anywhere else in the vault. |
+
+The source is `06. Projects/Divorce-transition/Divorce.md`, whose `related:` is `[Lune, Marie, Briac
+Prud'homme]` — three bare strings, no wikilinks.
+
+## 2 · Atlas of Roots — context only
+
+**`09. Atlas of Roots/00. Atlas of Roots — Index.md`** — created 2025-09-29, mtime **Sep 28 2025**,
+and it appears in the mirror's history exactly **once**: first and last commit are the same sync.
+**Untouched for ~11 months.**
+
+**The section contains exactly one note — this index.** Nothing was ever filed under it.
+
+**What it says about itself** (verbatim):
+
+> *A codex of places, people, and meanings that formed my roots.
+> This work is both a vessel for grief and a durable inheritance for Kai and Lune.*
+>
+> **Purpose** — To **codify grief into form**: no longer carried loosely, but tended as lineage. To
+> **preserve roots** in words, images, and rituals. To **offer inheritance**: not nostalgia, but
+> *living soil* for Kai, Lune, and future descendants.
+
+Its frontmatter carries `status: living`, `version: 0.1.0`, and **`next_review: 2026-01-15` — a
+review date seven months past.**
+
+⚠ **Its own `assurance.risk_flags` name what happened to it:** `nostalgic distortion` · **`isolation
+from Compass`** · `unreviewed grief`. And its stated assumptions include *"Placement at top-level
+ensures visibility and prevents siloing."* The note predicted its own failure mode in the same
+frontmatter block that has now sat unread for eleven months.
+
+**Its declared children:**
+
+| declared | exists? |
+|---|---|
+| `places/pine-street` | no note anywhere |
+| `places/salmon-lake` | no note anywhere |
+| `people/moy-glidden` | **exists elsewhere** — `03. People/Moy Glidden.md` |
+| `people/abg` | no note under that name (`03. People/Arthur Boyntin Glidden Jr..md` exists) |
+| `GLOSSARY.md` (peer) | **exists elsewhere** — `…/Animal Rationis Capax/docs/context/GLOSSARY.md.md` |
+
+Its own `canonical: 09. Atlas of Roots/index.md` points at a filename that does not exist; the note
+is `00. Atlas of Roots — Index.md`.
+
+**Inbound:** exactly **two** non-Atlas notes mention "Atlas of Roots", and **both are in
+`99. Archive/99. chatgpt-conversations/`** — one of them dated 2025-09-28, the conversation from
+which it was conceived. **No live note in the working vault links to it.**
+
+## 3 · What already distinguishes `99. Archive` (1,070 notes, 42% of the vault)
+
+### 3a · Frontmatter presence
+
+| | with frontmatter | |
+|---|---|---:|
+| Archive | 120 / 1,070 | **11%** |
+| non-Archive | 668 / 1,449 | **46%** |
+
+### 3b · ⚠ `canonical`'s pointer form is NOT concentrated in Archive — the hypothesis tests negative
+
+| | self-descriptive | pointer-elsewhere | bool flag | total |
+|---|---:|---:|---:|---:|
+| **Archive** | 8 | **2** | 0 | 10 |
+| **non-Archive** | 83 | **65** | 3 | 151 |
+
+**65 of the 67 pointer-form instances are outside Archive.** If "the current version lives elsewhere"
+were already functioning as an archival marker, the pointers would cluster in Archive. They do the
+opposite.
+
+The finding this *does* support is narrower and, if anything, more useful: **65 notes sitting in the
+live vault declare that their live version is somewhere else, and none of them was moved.** The
+declaration exists; it has never been *acted on*. Whether that makes it a latent archival signal or
+merely an unmaintained field is not something this check can settle — but it is not currently doing
+archival work, because the population it marks is precisely the population that was left in place.
+
+### 3c · `status`
+
+| Archive (32 of 1,070 carry `status` — **3%**) | | non-Archive (273 carry it) | |
+|---|---:|---|---:|
+| `archived` | 25 | `active` | 97 |
+| `Active` | 5 | `living` | 71 |
+| `active` | 2 | `canonical` | 20 |
+| | | `draft` | 13 |
+| | | `in_progress` / `stable` / `private` / `exploratory — pre-proposal` / `pointer` / `complete` | 4–6 each |
+
+**`status: archived` exists and is used on 25 notes — 2.3% of the Archive.** No note outside Archive
+carries it. Seven notes *inside* Archive still declare themselves `Active`/`active`, in two
+capitalisations.
+
+### 3d · Inbound links — do archived notes go quiet?
+
+Counting wikilinks from non-Archive notes into Archive notes:
+
+- **97 of 1,449** live notes contain at least one link into Archive.
+- **105 of 1,070** Archive notes (**9%**) receive such a link.
+- **965 Archive notes (90%) receive no wikilink from any live note.**
+
+The 9% that stay linked are concentrated: `06. Projects/…/03. GPT-Archeologist` alone accounts for 39
+links, then `07. Learn/Reading/00. Master_Reading_Index` (10), `Lune — Updates Log` (7),
+`03. People/DFG` (5), and the two vault indexes (5 each).
+
+### 3e · An existing archival policy note
+
+**None found.** No note in the vault states an archival rule, criterion, or policy. Searched by
+filename and by content across the whole vault.
+
+## 4 · ⚠ The Chamber library-curation pattern-language document does not exist
+
+Searched `~/_Dev/chamber-library`, `~/_Dev/studium-engine`, `~/_Dev/animal-davidglidden-eu`,
+`~/_Dev/CapableMind-AI` and the whole vault, by filename and by content, including a search for
+Alexander's pattern *form* (a `**Therefore**` invariant clause) applied to curation. The two hits for
+that form are ordinary prose.
+
+**Three real things exist that the name could be resolving to, and they are different from each
+other:**
+
+1. **Christopher Alexander's books are chamber library SOURCES** —
+   `canonical_texts/traditions/contemporary_voices/environmental/a-pattern-language-christopher-alexander.md`
+   and `…/The_Timeless_Way_of_Building/the-timeless-way-of-building.md`, catalogued as
+   *title: A Pattern Language · author: Christopher Alexander*. **PENDING-146's "Pattern 26's bold
+   invariant slot" refers to this** — Alexander's book as a text under citation, not to a framework
+   for curating the library.
+2. **`Pattern, Presence, Practice` (P3)** — **177 notes** in `06. Projects/`, the steward's own
+   pattern language, explicitly *"inspired by Christopher Alexander's The Timeless Way of Building"*
+   and Zehetmair's *Systematische Violintechnik*. Its subject is **violin pedagogy** — *"a way to
+   think, feel, and teach music through pattern languages, dimensional awareness, and symbolic
+   gesture."* It is Alexander-modelled and it is a real framework; it is not a Chamber document and
+   not about curation.
+3. **ARC chamber-generated essays about Alexander** — e.g.
+   `content/chamber/canon/chamber-generated/alexander-pattern-languages-minds.md`. These are
+   **outputs of** the Chamber, not frameworks **for** it.
+
+The Chamber's own governing documents are of a different kind entirely: Vision & Charters (Hermetic,
+Editorial, Epistemic; *The Chamber — Complete Living Amphitheatre V2.1*) and Schemas & Protocols
+(first-light / standard / shadow). None is a pattern language.
+
+**Nothing was substituted.** Naming the closest candidates is not the same as relaying the requested
+document, and the request was specific enough that the difference matters.
+
+---
+
+**Findings only. Nothing proposed, nothing decided, nothing changed.**

scripts/governance-drift-check.py

@@ -350,7 +350,24 @@ _scan_targets = [(r, "*/docs/**/*.md") for r in SCAN_ROOTS] + EXTRA_SCAN_GLOBS
 # READING task, and it is reported as owed rather than silently skipped.
 _scan_targets += [(HOME / "dotfiles", "PENDING.md"), (HOME / "dotfiles", "PENDING-archive.md")]
 PROSE_DEFERRAL_RE = re.compile(r"defer(?:red|ral)", re.I)
+# The size guard bounds the unbounded `**/*.md` globs. It must NOT apply to the two
+# governance files, which were added to the scan on purpose and are the whole reason
+# the scan reaches outside docs/ at all.
+#
+# 2026-08-17 [FIX]: it did apply, and PENDING.md had grown to 546,944 bytes — so every
+# structured DEFERRED-DECISION block in the governance register was skipped, silently,
+# by the checker built to stop deferrals from being silently missed. Worse than silent:
+# the prose-deferral loop below has no size guard, so PENDING.md's prose count appeared
+# in the report and made the file look examined. Found by placing a block under
+# REVIEWED-123 cond. 2 and noticing the tracked count did not move.
+#
+# Both halves are fixed here: the named governance files are never size-skipped, and a
+# skip is now REPORTED rather than swallowed — the third outcome of REVIEWED-104's
+# doctrine, on the instrument whose whole subject is conditions nobody is watching.
+GOVERNANCE_FILES = {HOME / "dotfiles" / "PENDING.md",
+                    HOME / "dotfiles" / "PENDING-archive.md"}
 _seen_files: set = set()
+skipped_too_large: list = []
 for root, pattern in _scan_targets:
     if not root.is_dir():
         continue
@@ -359,7 +376,8 @@ for root, pattern in _scan_targets:
             continue
         _seen_files.add(f)
         try:
-            if f.stat().st_size > 400_000:
+            if f.stat().st_size > 400_000 and f not in GOVERNANCE_FILES:
+                skipped_too_large.append(f)
                 continue
             body = f.read_text(errors="replace")
         except OSError:
@@ -389,6 +407,20 @@ control("transcripts trigger silent on an unreached threshold",
 control("governance dir is inside the deferral scan",
         any("claude/governance" in str(p) for p in _seen_files)
         or not (HOME / "dotfiles/claude/governance").is_dir())
+# 2026-08-17: PENDING.md passed 400 KB and every structured block in it went unscanned,
+# silently, while its prose count still appeared in the report. These controls are derived
+# from the PROPERTY (is the register's block actually parsed?), not from the guard's own
+# vocabulary — a control asking "does the guard work" would have passed throughout.
+control("the governance register is actually scanned for blocks, whatever its size",
+        (HOME / "dotfiles/PENDING.md") in _seen_files
+        and (HOME / "dotfiles/PENDING.md") not in skipped_too_large)
+control("a real block IN the register is parsed  [the live instance, not a fixture]",
+        any(d["file"].name == "PENDING.md" for d in deferrals)
+        or "DEFERRED-DECISION:" not in (HOME / "dotfiles/PENDING.md").read_text(errors="replace"))
+control("the size guard still applies to non-governance files  [negative control — "
+        "the exemption must not become 'scan everything']",
+        (HOME / "dotfiles/PENDING.md") in GOVERNANCE_FILES
+        and (HOME / "dotfiles/CLAUDE.md") not in GOVERNANCE_FILES)
 control("trigger evaluator FIRES on a met condition",
         _p_ok and trigger_fired(_p_ok[0]) is True)
 control("trigger evaluator does NOT fire on an unmet condition  "
@@ -564,5 +596,13 @@ if deferrals:
               f"({', '.join(f'{k} {v}' for k, v in prose_counts.items())}) — these carry no")
         print("    DEFERRED-DECISION block, so NO trigger is machine-checkable for any of them.")
         print("    Counted, not classified. Whether any condition has fired is unestablished.")
+    if skipped_too_large:
+        print(f"  ⚠ and {len(skipped_too_large)} file(s) were NOT SCANNED for structured blocks "
+              f"(over the 400 KB guard):")
+        for _s in skipped_too_large:
+            print(f"      {_s.relative_to(HOME) if HOME in _s.parents else _s} "
+                  f"({_s.stat().st_size:,} bytes)")
+        print("    Any DEFERRED-DECISION block in these is INERT. This is 'could not assess',")
+        print("    not 'nothing there' — the distinction REVIEWED-104 rules may not be collapsed.")
 
 sys.exit(0)

scripts/governance-mcp.py

@@ -47,6 +47,7 @@ import time
 HOME = os.path.expanduser("~")
 D = os.path.join(HOME, "dotfiles")
 SCRIPTS = os.path.join(D, "scripts")
+ENGINE = os.path.join(HOME, "_Dev", "studium-engine")
 NAME, VERSION = "governance", "1.0.0"
 
 # Newest protocol we speak; we echo the client's version when it sends a known one.
@@ -85,6 +86,49 @@ FILES = {
     "graduation-spec":  (os.path.join(HOME, "_Dev", "chamber-library", "_curation",
                                       "graduation-spec.yaml"),
                          "the constitution's machine-readable convention-data + gate-list"),
+    # PENDING-86 class, FOURTH instance — steward-requested 2026-08-10. Same shape
+    # as the two above and the same remedy: the jurist design-gates a V0-lane
+    # matter (§7.4(i) governs what Tier-1 must REFUSE) whose governing text it
+    # could not open, and said so at the top of its own ruling — "every quotation
+    # in Part I is your testimony, not something I can reach. That is exactly the
+    # material two of today's three reversals turned on." Read-only, keyed, no
+    # path argument; the enum design is unchanged.
+    "v2-harness-design": (os.path.join(ENGINE, "docs",
+                                       "v2-validation-harness-design-2026-07-09.md"),
+                          "the V2 validation-harness design — the ratified text behind the "
+                          "nested-voice arc. §5 = failure-mode table (F1–F10, each with a "
+                          "Direction and an 'Exercised by' column); §6.2 = the PRE-REGISTERED "
+                          "difficulty strata; §7.4 = whole-for-part attribution, sub-type (i) "
+                          "nested-voice. ⚠ Long (~65 KB); page to the § you need rather than "
+                          "reading from the top"),
+    # ⚠ DESCRIPTIONS REFRESHED 2026-08-13. They are what the jurist reads to decide
+    # which key to open, and both went stale the same day the dispositions landed —
+    # a description standing in for the thing, which is the class this whole arc is
+    # about. Refreshed BEFORE the client restart that first serves these keys, so
+    # the jurist's first read is not of a stale index.
+    "v2-stratum-tags":  (os.path.join(ENGINE, "corpus", "v2-stratum-tags.yaml"),
+                         "P7 — the stratum tagging of the INHERITED gold (fr Mauss; en March "
+                         "chavruta). ⚠ Its `en` block is `taggable: false`. ⚠ The fr ratio is "
+                         "now VOID, not 1:9 — re-derived ONCE after PENDING-134 lands and all "
+                         "dispositions are recorded (REVIEWED-116 pt 5). Cell as of 2026-08-13: "
+                         "11 listed spans / 8 grounded (1 A + 7 B) / 2 reclassified out "
+                         "(Havámál L856 at P7; instance 8 L1551, PENDING-135) / 1 retracted "
+                         "(L926, REVIEWED-118) / 10 grounded bound instances. Count fields now "
+                         "carry their populations — bare `distinct_spans` was retired "
+                         "(PENDING-136)"),
+    "mauss-fixture-spans": (os.path.join(ENGINE, "corpus", "mauss-phase2-spans.yaml"),
+                            "the fr fixture — 15 BOUND instances / 11 distinct spans, with "
+                            "per-instance Tier-1 verdicts. Locations and verdicts only. ⚠ "
+                            "BINDING ≠ ADMISSIBILITY: all 15 still bind and the counts here do "
+                            "not move for a disposition, but 3 instances (6/12/16) are "
+                            "retracted and 1 (8) reclassified — see the "
+                            "`retracted_from_grounded_gold` and `reclassified_from_grounded_gold` "
+                            "keys in the file, and `v2-stratum-tags` for the grounded set"),
+    "mauss-fixture-citations": (os.path.join(ENGINE, "corpus",
+                                             "mauss-phase2-reanchored.yaml"),
+                                "the fr fixture's CITATION TEXTS — the quoted strings "
+                                "themselves. This is the file that answers 'whose "
+                                "proposition does the claim assert?'"),
 }
 REPOS = wd.REPOS
 
@@ -480,6 +524,25 @@ def selftest():
     chk("governance_read ACCEPTS a listed key  [positive control for the refusal above]",
         t_read({"file": "pending"}).startswith("[pending —"))
 
+    print("\nPENDING-86 4th instance — the V0-lane texts behind the nested-voice arc:")
+    chk("v2-harness-design key reads",
+        t_read({"file": "v2-harness-design"}).startswith("[v2-harness-design —"))
+    chk("...and carries §6.2's PRE-REGISTERED strata  [the clause the ruling turns on]",
+        "Difficulty strata (pre-registered" in t_read({"file": "v2-harness-design"}))
+    chk("...and carries §7.4's nested-voice sub-type",
+        "nested-voice" in t_read({"file": "v2-harness-design"}))
+    chk("...and carries §5's F4 row, whose omission from §6.2 is the counter-argument",
+        "Irony / persona distance / unasserted content" in t_read({"file": "v2-harness-design"}))
+    chk("v2-stratum-tags (P7) key reads, and its en cell is the untaggable one",
+        "taggable: false" in t_read({"file": "v2-stratum-tags"}))
+    chk("mauss-fixture-spans key reads",
+        t_read({"file": "mauss-fixture-spans"}).startswith("[mauss-fixture-spans —"))
+    chk("mauss-fixture-citations carries the CITATION TEXT, not just the locations"
+        "  [the file that answers whose-proposition]",
+        "Le charpentier dit à Arthur" in t_read({"file": "mauss-fixture-citations"}))
+    chk("...and the L926 testimony the whole arc turns on",
+        "Le hau n'est pas le vent qui souffle" in t_read({"file": "mauss-fixture-citations"}))
+
     print("\nPENDING-86 (a) — the documents the jurist design-gates are now reachable:")
     chk("chamber-spec key reads",
         t_read({"file": "chamber-spec"}).startswith("[chamber-spec —"))

scripts/wake-digest.py

@@ -16,7 +16,7 @@ if it cannot be computed it says so rather than emitting nothing.
 Provenance: 2026-07-28, steward-authorized alongside the PENDING split and the
 CLAUDE.md doctrine annotation. Sibling of governance-drift-check.py.
 """
-import os, re, subprocess, sys, time
+import calendar, os, re, subprocess, sys, time
 
 HOME = os.path.expanduser("~")
 D = os.path.join(HOME, "dotfiles")
@@ -125,8 +125,20 @@ def sec_pause():
     if not files:
         warn.append("no session memory files found")
         return None, None
-    newest = max(files, key=lambda f: os.path.getmtime(os.path.join(MEM, f)))
-    age = time.time() - os.path.getmtime(os.path.join(MEM, newest))
+    # By git add-time, NOT mtime. Editing an old wrap record — a CODA, a
+    # correction, a mechanical repair — moves its mtime to today and makes it
+    # look like the newest wrap. That is not hypothetical: on 2026-08-17 a
+    # frontmatter repair touched 20 April–May records at once and this line
+    # promoted a session from April to "last wrap", losing the thread and the
+    # question in the same stroke. Add-time cannot be moved by an edit.
+    # Residual, stated: add-time is when the wrap was COMMITTED, which lags when
+    # it was written (08-14's record was committed 08-15 09:16, ~14 h later). So
+    # `Last wrap` is an upper bound on elapsed time, never exact — but it is wrong
+    # by hours, where mtime was wrong by months.
+    when = {os.path.basename(p): e for p, e, _s in wrap_events()}
+    stamp = lambda f: when.get(f, os.path.getmtime(os.path.join(MEM, f)))
+    newest = max(files, key=stamp)
+    age = time.time() - stamp(newest)
     h = age / 3600
     span = f"{age/60:.0f} min" if h < 1 else (f"{h:.1f} h" if h < 48 else f"{h/24:.1f} days")
     return newest, span
@@ -138,6 +150,41 @@ def wrap_records():
             if f.startswith("session-") and not f.startswith("session-ledger-")]
 
 
+def parse_iso(s):
+    """ISO-8601 -> true epoch, honouring the zone suffix.
+
+    THE 2026-08-17 BUG, and it is the whole reason the alarm below misfired.
+    Transcript timestamps are UTC (`2026-08-14T07:29:36.852Z`). The previous
+    implementation dropped the `Z` and called `time.mktime`, which reads a
+    struct_time as LOCAL — putting the span in a different time base from
+    `os.path.getmtime()`, which returns a true epoch. Measured that day: a
+    +2 h (CEST) skew against a 15 min tolerance. Since the skew exceeds the
+    tolerance, a wrap written at the end of a session could NEVER land inside
+    the window — so `PREVIOUS SESSION DID NOT WRAP` was systematic, not
+    occasional. It had been overridden by hand at two consecutive wakes.
+
+    Naive strings (no zone) are still read as local: that is what they mean.
+    """
+    m = re.match(r"(\d{4}-\d{2}-\d{2})[T ](\d{2}:\d{2}:\d{2})", s or "")
+    if not m:
+        return None
+    try:
+        st = time.strptime(f"{m.group(1)}T{m.group(2)}", "%Y-%m-%dT%H:%M:%S")
+    except (ValueError, OverflowError):
+        return None
+    z = re.match(r"(?:\.\d+)?(Z|[+-]\d{2}:?\d{2})", s[m.end():])
+    if not z:
+        try:
+            return time.mktime(st)
+        except (ValueError, OverflowError):
+            return None
+    tag = z.group(1)
+    if tag == "Z":
+        return calendar.timegm(st)
+    sign = 1 if tag[0] == "+" else -1
+    return calendar.timegm(st) - sign * (int(tag[1:3]) * 3600 + int(tag[-2:]) * 60)
+
+
 def transcript_span(path):
     """
     A session's true span, from the timestamps INSIDE the transcript — never mtime.
@@ -148,28 +195,115 @@ def transcript_span(path):
     try:
         with open(path, errors="ignore") as f:
             for line in f:
-                m = re.search(r'"timestamp"\s*:\s*"([0-9T:\-]{19})', line)
+                m = re.search(r'"timestamp"\s*:\s*"([^"]{19,40})"', line)
                 if m:
+                    e = parse_iso(m.group(1))
+                    if e is None:
+                        continue
                     if first is None:
-                        first = m.group(1)
-                    last = m.group(1)
+                        first = e
+                    last = e
     except OSError:
         return None, None
-
-    def epoch(s):
-        try:
-            return time.mktime(time.strptime(s, "%Y-%m-%dT%H:%M:%S"))
-        except (ValueError, OverflowError):
-            return None
-    return epoch(first), epoch(last)
+    return first, last
 
 
-def wrap_inside(span, wrap_mtimes, lead=300, lag=900):
-    """Did a wrap record get written inside this session's span?"""
+def wrap_events():
+    """-> [(path, epoch, source)] — when each wrap record CAME INTO EXISTENCE.
+
+    Not mtime. A wrap record edited later — a CODA appended, a correction made —
+    carries the edit's mtime, so an ordinary and correct act destroys the evidence
+    that the wrap happened inside its own session. Measured 2026-08-17: the 08-14
+    record's mtime read 08-17 for exactly that reason. Git's add-time cannot move
+    once committed; mtime is the fallback for a not-yet-committed record and is
+    labelled so the caller can tell the two apart.
+    """
+    added, at = {}, None
+    out = sh(["git", "-C", D, "log", "--diff-filter=A", "--format=%at",
+              "--name-only", "--", os.path.relpath(os.path.realpath(MEM), D)])
+    for line in (out or "").split("\n"):
+        line = line.strip()
+        if re.fullmatch(r"\d{9,11}", line):
+            at = int(line)
+        elif line and at is not None:
+            base = line.rsplit("/", 1)[-1]
+            if base not in added or at < added[base]:
+                added[base] = at            # earliest add wins
+    ev = []
+    for p in wrap_records():
+        base = os.path.basename(p)
+        if base in added:
+            ev.append((p, added[base], "git"))
+        else:
+            try:
+                ev.append((p, os.path.getmtime(p), "mtime"))
+            except OSError:
+                pass
+    return ev
+
+
+def previous_transcript(now, spans):
+    """The session before this one, selected by SPAN — never by 'quiet for >60 s'.
+
+    The old rule excluded any transcript touched within 60 s as 'the current
+    session'. That is wrong at precisely the moment it matters: on 2026-08-17 the
+    previous session had ended 12 s before the wake, was excluded as too recent,
+    and the digest reported the session from four days earlier instead — 'ended
+    ~Aug 13 21:36'. The defect is time-dependent and disappears ~60 s later, which
+    is why re-running the digest afterwards showed nothing wrong.
+
+    THIS session's transcript is the one most recently STARTED that is still being
+    appended. Keying on start alone breaks once the current session has run a
+    while; keying on end alone cannot tell a live session from one that ended
+    seconds ago. Both together identify it, and at most one is ever excluded — so
+    a just-ended prior session can no longer be skipped.
+
+    Residual, stated rather than hidden: if the current session's transcript holds
+    no parseable timestamp yet, the newest START is the previous session, and if it
+    also ended moments ago it is excluded and the one before it is reported. That
+    is the old failure in a much smaller window, and it is why the caller treats a
+    'no wrap' result as advisory rather than as proof.
+    """
+    dated = [r for r in spans if r[1] is not None and r[2] is not None]
+    if not dated:
+        return None
+    live = max(dated, key=lambda r: r[1])          # newest start …
+    rest = [r for r in dated if r is not live] if live[2] >= now - 120 else dated
+    return max(rest, key=lambda r: r[2]) if rest else None    # … and still growing
+
+
+def wrap_verdict(span, events, lead=300, lag=10800):
+    """-> (state, detail). FOUR outcomes, because 'I could not tell' is two things.
+
+    REVIEWED-104: a check whose subject can be absent may not be two-valued, and
+    the third outcome is itself two kinds — subject absent (environment, must not
+    block) versus check broken (defect). The previous version folded both into
+    silence via `verdict is None`, so 'I could not look' read as 'it wrapped'.
+    """
     a, b = span
     if a is None or b is None:
-        return None                      # unreadable — not the same as 'no wrap'
-    return any(a - lead <= m <= b + lag for m in wrap_mtimes)
+        return "unassessable-subject", ("the previous session's transcript carries "
+                                        "no readable timestamps")
+    if not events:
+        return "unassessable-check", "no wrap records could be enumerated"
+    if any(a - lead <= e <= b + lag for _p, e, _s in events):
+        return "wrapped", ""
+    # No event in the window. Before alarming, ask whether some wrap record NAMES a
+    # day inside this span: commit lag can push real evidence past the window, and
+    # an alarm that cannot be substantiated is worse than an honest non-answer.
+    days, t, guard = set(), int(a), 0
+    while t <= int(b) + 86400 and guard < 60:
+        days.add(time.strftime("%Y-%m-%d", time.localtime(t)))
+        t += 86400
+        guard += 1
+    named = [os.path.basename(p) for p, _e, _s in events
+             if any(d in os.path.basename(p) for d in days)]
+    if named:
+        return ("unassessable-check",
+                f"no wrap event inside the span, but {named[0]} names a day within "
+                f"it — a real wrap with lagged evidence cannot be told apart from "
+                f"another session's record")
+    return "unwrapped", ""
 
 
 def sec_unwrapped():
@@ -182,30 +316,44 @@ def sec_unwrapped():
     detected this via a MemPalace Stop hook; that hook is retired, but the
     failure it named is live. The transcripts are the only witness that a
     session ran at all.
+
+    Rebuilt 2026-08-17, after the alarm fired falsely at three consecutive wakes
+    and was overridden by hand at two of them. FOUR defects were found, and only
+    one was the one the work had been scoped to:
+      1. a UTC/local time-base mismatch (see `parse_iso`) — THE CAUSE, and large
+         enough that an end-of-session wrap could never be seen;
+      2. a selection rule that skipped a session which had just ended;
+      3. wrap evidence read from mutable mtimes;
+      4. a two-valued verdict over an assessment that can fail.
+    Fixing only (4), as scoped, would have left the false alarms firing.
     """
     proj = os.path.dirname(os.path.join(HOME, ".claude", "projects",
                                         "-Users-davidglidden", "memory"))
     try:
         tx = [os.path.join(proj, f) for f in os.listdir(proj) if f.endswith(".jsonl")]
     except OSError:
+        warn.append("session transcripts unreadable — wrap check did not run")
         return None
-    now = time.time()
-    # The current session's transcript is being appended right now; the previous
-    # session's is the newest one that has gone quiet.
-    prior = [p for p in tx if now - os.path.getmtime(p) > 60]
-    if not prior:
+    if not tx:
         return None
-    last = max(prior, key=os.path.getmtime)
-    verdict = wrap_inside(transcript_span(last),
-                          [os.path.getmtime(w) for w in wrap_records()])
-    if verdict is None or verdict:
+    prev = previous_transcript(time.time(), [(p,) + transcript_span(p) for p in tx])
+    if prev is None:
         return None
-    ended = time.strftime("%b %d %H:%M", time.localtime(os.path.getmtime(last)))
-    return (f"⚠ PREVIOUS SESSION DID NOT WRAP (ended ~{ended}). The thread and "
-            f"question below are inherited from an OLDER session — treat them as "
-            f"possibly stale, and expect no record of what that session did.\n"
-            f"  Not established: whether that session did work worth keeping. The "
-            f"transcript is on disk and can be read if the gap matters.")
+    _path, a, b = prev
+    state, detail = wrap_verdict((a, b), wrap_events())
+    if state == "wrapped":
+        return None
+    ended = time.strftime("%b %d %H:%M", time.localtime(b))
+    if state == "unwrapped":
+        return (f"⚠ PREVIOUS SESSION DID NOT WRAP (ended ~{ended}). The thread and "
+                f"question below are inherited from an OLDER session — treat them as "
+                f"possibly stale, and expect no record of what that session did.\n"
+                f"  Not established: whether that session did work worth keeping. The "
+                f"transcript is on disk and can be read if the gap matters.")
+    return (f"◌ WRAP STATUS UNDETERMINED for the previous session (ended ~{ended}) — "
+            f"{detail}.\n"
+            f"  This is neither an alarm nor a clean pass: the check could establish "
+            f"neither. Open the newest session record to see what it actually holds.")
 
 
 def ruled_pendings(reviewed_text):
@@ -219,18 +367,39 @@ def ruled_pendings(reviewed_text):
     closing that item later produced no visible change because it had never been
     counted. Measured at the time: 9 suppressed, 8 correctly, 1 falsely.
 
-    A ruling whose header names no PENDING (REVIEWED-78, -81, -82 …) suppresses
-    nothing.
+    A ruling whose header names no PENDING suppresses nothing — which is the rule's
+    correct behaviour in general and its FALSE-OPEN class in particular. See below.
 
     The correction runs in BOTH directions, and an earlier draft of this docstring
     claimed otherwise — that it could only ever surface more, never fewer. That was
     an overclaim, caught by the change proof rather than by reading. Measured against
-    the live files at the time of the fix: 3 items surfaced that had been falsely
-    hidden (PENDING-78, -81, -82 — like-numbered rulings exist, concerning other
-    matters), and 2 stopped being shown that were genuinely ruled (PENDING-87 by
-    REVIEWED-84, PENDING-88 by REVIEWED-85 — no REVIEWED-87 or -88 exists, so the
-    number-match had never suppressed them). Net 18 → 19 visible. Number-matching
-    was wrong in both directions; only subject-matching is right in either.
+    the live files at the time of the fix: 3 items surfaced (PENDING-78, -81, -82),
+    and 2 stopped being shown that were genuinely ruled (PENDING-87 by REVIEWED-84,
+    PENDING-88 by REVIEWED-85 — no REVIEWED-87 or -88 exists, so the number-match had
+    never suppressed them). Net 18 → 19 visible.
+
+    ⚠ CORRECTED 2026-08-17 (PENDING-142; jurist-ruled to correct independently of the
+    mechanism). This docstring previously described those 3 as *"falsely hidden"* by
+    "like-numbered rulings … concerning other matters." **Both halves are false, and
+    the substrate says so in its own words.** REVIEWED-78/-81/-82 are the AUTHORIZED
+    rulings ON PENDING-78/-81/-82 — same date (2026-07-28), same titles verbatim, and
+    REVIEWED-81 names "PENDING-81" twice in its body. They are like-numbered ON
+    PURPOSE: REVIEWED-78's own Notes state it was filed as a separate entry
+    *"for a mechanical reason: the closure rule in `wake-digest.py` matches a PENDING
+    item to `REVIEWED-<same number>`, so a cross-numbered closure stated only in prose
+    would leave PENDING-78 listed as open at every wake."*
+
+    So the number→subject fix broke the three entries that had been deliberately
+    authored to satisfy the rule it replaced, and then recorded their compliance as
+    coincidence. Surfacing them was a REGRESSION, not a repair; they have read open
+    since 2026-07-28. The change proof could not see it because it measured a COUNT
+    (18 → 19) while the claim was about each item's disposition — and the counts stay
+    equal: removing 3 false-opens and restoring 3 false-closeds both leave 29.
+
+    Number-matching was wrong in both directions. Subject-matching is right in
+    neither until it matches on the SUBJECT — the title or the decision — rather than
+    on the presence of an id token in a header. Remedy is PENDING-142, unbuilt; this
+    note exists so the code does not keep asserting the opposite while it waits.
     """
     return set(re.findall(r"^## REVIEWED-\S+\s*—\s*PENDING-(\S+?)\s*—", reviewed_text, re.M))
 
@@ -429,10 +598,52 @@ def brief_age_days():
 # memory files' own prose (17 uses). Absolute still VALIDATES here — it is not
 # wrong, only unportable — but it is counted and reported so it cannot re-enter
 # silently.
+#
+# 2026-08-10 — three completions, all earned before this code existed.
+#
+# (1) CODE SPANS. The matcher read `](file.md)` inside backticks as a pointer,
+#     so on 2026-08-09 it reported exactly one DEAD pointer: the link pattern
+#     written inside MEMORY.md's own SPECIFICATION OF THIS CANARY. An
+#     instrument that flags its own documentation flags it every wake, forever,
+#     and the real signal drowns in a permanent known-false line — the same
+#     "known canary bug" dismissal the block above was written to end, arriving
+#     by a second route. Code spans and fenced blocks are blanked before
+#     matching, offsets preserved so every reported line number stays true.
+#     Inline spans may not cross a newline: a stray unmatched backtick must
+#     bound its damage to one line rather than blanking the rest of the file
+#     and HIDING dead pointers. An unterminated fence simply does not match,
+#     so the failure direction is over-reporting, never silence.
+#
+# (2) WIKILINKS. `reference-verification-ladder.md` has specified the canary as
+#     covering "every `](file.md)` and `[[wikilink]]`" since 2026-07-06; only
+#     the first half was ever built. Reported as UNWRITTEN, not DEAD, because
+#     ~/CLAUDE.md rules a wikilink with no file yet to be legitimate — it marks
+#     something worth writing. A permitted forward-reference and a broken index
+#     pointer are different findings and must not share a word.
+#
+# (3) PRE-EXISTING vs NEWLY BROKEN. The 2026-08-09 spec asked for it. Derived
+#     from git, NOT from a stored prior run: a state file would make this the
+#     one cached section in a digest whose governing property is that it is
+#     computed. Where git cannot answer — a target outside this repo — it says
+#     so rather than guessing.
 NONPORTABLE_RE = re.compile(r"^/(Users|home)/")
 
 MEM_INDEXES = ["MEMORY.md", "MEMORY-reference.md"]
 POINTER_RE = re.compile(r"\]\(([^)\s]+\.md)\)")
+WIKILINK_RE = re.compile(r"\[\[([^\[\]|#\n]+?)(?:#[^\[\]|\n]*)?(?:\|[^\[\]\n]*)?\]\]")
+FENCE_RE = re.compile(r"^(?P<f>`{3,}|~{3,})[^\n]*\n.*?^(?P=f)[^\n]*$", re.M | re.S)
+INLINE_CODE_RE = re.compile(r"`+[^`\n]*`+")
+
+
+def blank_code(text):
+    """Blank code-span and fenced-block CONTENT, preserving offsets and newlines.
+
+    Preserving offsets is the point: every line number this module reports is
+    computed from the blanked text, so it must still address the real line.
+    """
+    def blank(m):
+        return "".join("\n" if c == "\n" else " " for c in m.group(0))
+    return INLINE_CODE_RE.sub(blank, FENCE_RE.sub(blank, text))
 
 
 def find_basename(name):
@@ -458,6 +669,7 @@ def resolve(raw, base):
 def classify_pointers(text, base):
     """(n_checked, mis_authored, dead, nonportable) — outcomes, never one word."""
     n, mis, dead, nonport = 0, [], [], []
+    text = blank_code(text)
     for m in POINTER_RE.finditer(text):
         raw = m.group(1)
         if raw.startswith(("http://", "https://", "mailto:")):
@@ -479,8 +691,93 @@ def classify_pointers(text, base):
     return n, mis, dead, nonport
 
 
+def near_slugs(slug, memdir):
+    """Memory files this wikilink was plainly REACHING FOR. Prefix-family only.
+
+    `[[trust-prior-pass-frame]]` wants `feedback-trust-prior-pass-frame.md`; the
+    slug is the tail of the real stem after a hyphen. Matching on that boundary
+    (never on a bare substring) keeps `[[arc]]` from claiming every file with
+    "arc" inside a word.
+    """
+    out = []
+    try:
+        stems = [f[:-3] for f in os.listdir(memdir) if f.endswith(".md")]
+    except OSError:
+        return out
+    for stem in stems:
+        if stem.endswith("-" + slug) or slug.endswith("-" + stem):
+            out.append(stem)
+    return sorted(out)
+
+
+def classify_wikilinks(text, memdir):
+    """(n_checked, mis_authored, unwritten) — three outcomes, never one word.
+
+    The same discipline as the path pointers above, and for the same reason: the
+    first build of this function reported only UNWRITTEN, and its two live hits
+    were both `[[trust-prior-pass-frame]]`, whose file EXISTS as
+    `feedback-trust-prior-pass-frame.md`. One word would have sent a fixable
+    typo to the wake every morning wearing the label "nothing to do here".
+
+    UNWRITTEN, never DEAD, for the genuine misses: ~/CLAUDE.md rules that a
+    `[[name]]` matching no file yet "is fine — it marks something worth writing
+    later, not an error." A permitted forward-reference is not a defect.
+    """
+    n, mis, unwritten = 0, [], []
+    text = blank_code(text)
+    for m in WIKILINK_RE.finditer(text):
+        slug = m.group(1).strip()
+        if not slug:
+            continue
+        n += 1
+        stem = slug[:-3] if slug.endswith(".md") else slug
+        if os.path.exists(os.path.join(memdir, stem + ".md")):
+            continue
+        line = text.count("\n", 0, m.start()) + 1
+        near = near_slugs(stem, memdir)
+        if near:
+            mis.append((line, slug, " | ".join(near)))
+        else:
+            unwritten.append((line, slug))
+    return n, mis, unwritten
+
+
+# Breakage age is DERIVED from git, never from a stored prior run — a cache is
+# the one thing this digest's governing property forbids. Two questions, both
+# answerable at HEAD: was the pointer already written, and did its target
+# already exist? Their four combinations are the four honest verdicts.
+def breakage(raw, head_text, target_at_head):
+    """PRE-EXISTING vs NEWLY BROKEN. `None` inputs mean 'git cannot say'."""
+    if head_text is None:
+        return "age unknown — no committed version of this index to compare"
+    if raw not in head_text:
+        return "NEW — this pointer was added since HEAD"
+    if target_at_head is True:
+        return "NEWLY BROKEN — target existed at HEAD and is gone now"
+    if target_at_head is False:
+        return "pre-existing — already broken at HEAD"
+    return "pre-existing at HEAD — target lives outside this repo, break date unknown"
+
+
+def head_text_of(relpath):
+    """The index as committed. None => never committed, or git unavailable."""
+    return sh(["git", "-C", D, "show", f"HEAD:{relpath}"])
+
+
+def target_at_head(raw, memrel):
+    """Did the pointer's target exist at HEAD? None where git cannot know."""
+    base = os.path.basename(raw)
+    if os.path.normpath(resolve(raw, os.path.realpath(MEM))) != os.path.normpath(
+            os.path.join(os.path.realpath(MEM), base)):
+        return None                      # leaves the memory dir — outside git's reach here
+    return sh(["git", "-C", D, "cat-file", "-e", f"HEAD:{memrel}/{base}"]) is not None
+
+
 def sec_pointers():
     total, mis, dead, nonport = 0, [], [], []
+    wtotal, wmis, unwritten = 0, [], []
+    memdir = os.path.realpath(MEM)
+    memrel = os.path.relpath(memdir, D)
     for name in MEM_INDEXES:
         path = os.path.realpath(os.path.join(MEM, name))
         text = read(path)
@@ -489,10 +786,16 @@ def sec_pointers():
             continue
         n, m_, d_, np_ = classify_pointers(text, os.path.dirname(path))
         total += n
+        head = head_text_of(f"{memrel}/{name}")
         mis += [(name,) + t for t in m_]
-        dead += [(name,) + t for t in d_]
+        dead += [(name, ln, raw, breakage(raw, head, target_at_head(raw, memrel)))
+                 for ln, raw, _ in d_]
         nonport += [(name,) + t for t in np_]
-    return total, mis, dead, nonport
+        wn, wm, wu = classify_wikilinks(text, memdir)
+        wtotal += wn
+        wmis += [(name,) + t for t in wm]
+        unwritten += [(name,) + t for t in wu]
+    return total, mis, dead, nonport, wtotal, wmis, unwritten
 
 
 # ---------- stray maps ----------
@@ -559,6 +862,16 @@ def selftest():
         ruled_pendings("## REVIEWED-84 — PENDING-87 — Order attestation") == {"87"})
     chk("ruled_pendings does NOT suppress the like-numbered item  [the 2026-08-01 bug]",
         "84" not in ruled_pendings("## REVIEWED-84 — PENDING-87 — Order attestation"))
+    # ⚠ RELIANCE ON THE DISCARDED READING — reported under REVIEWED-122 cond. 6,
+    # NOT repaired here (the repair is inside the gated mechanism; see PENDING-142
+    # ADDENDUM 1). The assertion is mechanically TRUE and will stay true. What is
+    # wrong is the fixture and what the name implies: `REVIEWED-82` is not a
+    # ruling-about-something-else, it is the AUTHORIZED ruling on PENDING-82, and
+    # this line therefore presents the false-open class as intended behaviour.
+    # Whoever builds PENDING-142 will see this check fail, or be tempted to keep it
+    # passing. Failing is the fix working. Re-derive the fixture from the property
+    # ("does this ruling dispose of that item?") using two genuinely unrelated
+    # documents, per REVIEWED-122 cond. 2.
     chk("ruled_pendings ignores a ruling that names no PENDING",
         ruled_pendings("## REVIEWED-82 — Read-only MCP server: eyes on the substrate") == set())
     chk("ruled_pendings handles non-numeric families",
@@ -609,6 +922,61 @@ def selftest():
         classify_pointers("[x](https://a.md)", MEMDIR) == (0, [], [], []))
     chk("classify_pointers returns clean on empty input",
         classify_pointers("", MEMDIR) == (0, [], [], []))
+    NOWHERE = "no-such-file-anywhere-xyzzy-9931.md"
+    print("\ncode spans  [2026-08-09: the canary flagged its own specification]:")
+    chk("a pointer INSIDE a code span is not a pointer",
+        classify_pointers(f"`[y]({NOWHERE})`", MEMDIR) == (0, [], [], []))
+    chk("...and the SAME pointer outside one still fires  [direction control —"
+        " blanking must not swallow everything]",
+        classify_pointers(f"[y]({NOWHERE})", MEMDIR)[0] == 1)
+    chk("MEMORY.md's own canary spec is silent  [the exact 2026-08-09 false positive]",
+        (lambda t: classify_pointers(t, MEMDIR) == (0, [], [], [])
+         and classify_wikilinks(t, MEMDIR) == (0, [], []))(
+            "→ `~/dotfiles/scripts/`, invoked not described; `](file.md)` +"
+            " `[[wikilink]]` over both memory indexes"))
+    chk("blanking preserves LINE NUMBERS  [offsets kept, not deleted]",
+        classify_pointers(f"`](x.md)`\n[y]({NOWHERE})\n", MEMDIR)[2][0][0] == 2)
+    chk("a fenced block is blanked",
+        classify_pointers(f"```\n[y]({NOWHERE})\n```\n", MEMDIR) == (0, [], [], []))
+    chk("a STRAY unmatched backtick blanks nothing  [damage bounded to one line;"
+        " a greedy matcher would HIDE dead pointers]",
+        classify_pointers(f"a ` b\n[y]({NOWHERE})\n", MEMDIR)[0] == 1)
+    chk("an UNTERMINATED fence blanks nothing  [fails toward reporting, not silence]",
+        classify_pointers(f"```\n[y]({NOWHERE})\n", MEMDIR)[0] == 1)
+    print("\nwikilinks  [the ladder specified them 2026-07-06; never built until now]:")
+    chk("a wikilink whose file exists resolves",
+        classify_wikilinks("see [[MEMORY]]", MEMDIR) == (1, [], []))
+    chk("a wikilink with no file is UNWRITTEN, not dead  [~/CLAUDE.md rules it legitimate]",
+        (lambda r: r[0] == 1 and not r[1] and len(r[2]) == 1)(
+            classify_wikilinks("see [[no-such-memory-xyzzy-9931]]", MEMDIR)))
+    chk("a NEAR-MISS slug is MIS-AUTHORED with the real file handed back"
+        "  [live: the two hits the one-word version mislabelled]",
+        (lambda r: len(r[1]) == 1 and not r[2]
+         and r[1][0][2] == "feedback-trust-prior-pass-frame")(
+            classify_wikilinks("[[trust-prior-pass-frame]]", MEMDIR)))
+    chk("...and a genuine miss does NOT collapse into mis-authored  [direction control]",
+        not classify_wikilinks("[[no-such-memory-xyzzy-9931]]", MEMDIR)[1])
+    chk("near_slugs matches on the HYPHEN boundary, not bare substring"
+        "  [else [[arc]] would claim every file with 'arc' in a word]",
+        all(s.endswith("-arc") or "arc".endswith("-" + s) for s in near_slugs("arc", MEMDIR)))
+    chk("an alias and a heading are stripped down to the slug",
+        classify_wikilinks("[[MEMORY#Index|the index]]", MEMDIR) == (1, [], []))
+    chk("a wikilink inside a code span is not a wikilink",
+        classify_wikilinks("`[[no-such-memory-xyzzy-9931]]`", MEMDIR) == (0, [], []))
+    chk("classify_wikilinks returns clean on empty input  [positive control]",
+        classify_wikilinks("", MEMDIR) == (0, [], []))
+    print("\nbreakage age  [derived from git — this digest may not cache]:")
+    chk("a pointer absent at HEAD is NEW",
+        breakage("x.md", "nothing here", False).startswith("NEW"))
+    chk("a pointer present at HEAD whose target was there too is NEWLY BROKEN",
+        breakage("x.md", "[a](x.md)", True).startswith("NEWLY BROKEN"))
+    chk("a pointer present at HEAD whose target was already gone is pre-existing",
+        breakage("x.md", "[a](x.md)", False).startswith("pre-existing"))
+    chk("an out-of-repo target says the break date is unknown  [honest degradation]",
+        "unknown" in breakage("x.md", "[a](x.md)", None))
+    chk("no committed index reads as UNKNOWN, never as pre-existing"
+        "  [negative control — absence of evidence]",
+        breakage("x.md", None, None).startswith("age unknown"))
     chk("is_homed TRUE for a Desktop map symlinked into maps/  [live substrate]",
         is_homed(os.path.join(DESKTOP, "corpus-index-2026-07-26.md"), MAPS_DIR))
     chk("is_homed FALSE for a regular file  [negative control — must not pass everything]",
@@ -616,26 +984,91 @@ def selftest():
     chk("is_homed FALSE for a symlink pointing OUTSIDE maps/",
         not is_homed(os.path.join(HOME, ".claude"), MAPS_DIR))
     print("\nunwrapped-session detector  [PENDING-S2's obligation, our substrate]:")
-    chk("wrap_inside TRUE when a wrap falls inside the span",
-        wrap_inside((1000.0, 2000.0), [1500.0]))
-    chk("wrap_inside TRUE for a wrap just after the last write  [wraps land near the end]",
-        wrap_inside((1000.0, 2000.0), [2400.0]))
-    chk("wrap_inside FALSE when every wrap is outside  [negative control]",
-        not wrap_inside((1000.0, 2000.0), [500.0, 5000.0]))
-    chk("wrap_inside returns None on an unreadable span  [must NOT read as 'no wrap']",
-        wrap_inside((None, None), [1500.0]) is None)
-    # Discrimination on REAL sessions: the detector must return BOTH verdicts over
-    # the actual transcript history. One verdict everywhere = it discriminates nothing.
+    # --- time base. The 2026-08-17 cause, and the control that was missing. ----
+    _utc = calendar.timegm(time.strptime("2026-08-14T07:29:36", "%Y-%m-%dT%H:%M:%S"))
+    chk("parse_iso reads a 'Z' timestamp as UTC  [the 2026-08-17 cause]",
+        parse_iso("2026-08-14T07:29:36.852Z") == _utc)
+    _agrees = (parse_iso("2026-08-14T07:29:36.852Z")
+               == time.mktime(time.strptime("2026-08-14T07:29:36", "%Y-%m-%dT%H:%M:%S")))
+    _utc_box = (time.altzone if time.daylight else time.timezone) == 0
+    chk("parse_iso differs from the old mktime reading unless the box is on UTC"
+        "  [negative control — proves the line above can fail]", _agrees == _utc_box)
+    chk("parse_iso honours an explicit offset",
+        parse_iso("2026-08-14T09:29:36+02:00") == parse_iso("2026-08-14T07:29:36Z"))
+    chk("parse_iso returns None on junk  [must not invent a span]",
+        parse_iso("not a timestamp") is None and parse_iso("") is None)
+    # THE END-TO-END FORM, derived from the property rather than from the check:
+    # a transcript's last inner timestamp and its file mtime are two readings of
+    # one moment. If they disagree by more than minutes, the detector is comparing
+    # two different clocks — which is exactly what it was doing (~7200 s skew).
     _proj = os.path.dirname(MEM)
     _tx = sorted((os.path.join(_proj, f) for f in os.listdir(_proj)
-                  if f.endswith(".jsonl")), key=os.path.getmtime)[-14:-1]
-    _wm = [os.path.getmtime(w) for w in wrap_records()]
-    _v = [wrap_inside(transcript_span(p), _wm) for p in _tx]
-    chk(f"real sessions read as WRAPPED  [{sum(1 for x in _v if x is True)} of {len(_v)}]",
-        any(x is True for x in _v))
-    chk(f"real sessions read as UNWRAPPED  [{sum(1 for x in _v if x is False)} of {len(_v)}]"
-        "  — the negative instance; without one the detector is unproven",
-        any(x is False for x in _v))
+                  if f.endswith(".jsonl")), key=os.path.getmtime)
+    # MEDIAN, not max, and the reason is itself a finding: a clock mismatch is
+    # SYSTEMATIC — it shifts every transcript by the same amount, so it moves the
+    # median. A lone large skew is a different phenomenon: 2026-08-10's transcript
+    # was touched 31 h after its last line. That is the very mutable-mtime problem
+    # `wrap_events` routes around, measured here on the transcript side. Max is
+    # printed so the outlier stays visible instead of being averaged away.
+    _skew = sorted(abs(os.path.getmtime(p) - transcript_span(p)[1])
+                   for p in _tx[-8:] if transcript_span(p)[1] is not None)
+    _med = _skew[len(_skew) // 2] if _skew else -1
+    chk(f"transcript span END agrees with file mtime"
+        f"  [median {_med:.0f}s, max {max(_skew) if _skew else -1:.0f}s;"
+        f" median was ~7200s before the fix]",
+        bool(_skew) and _med < 900)
+    # --- the four outcomes -----------------------------------------------------
+    _E = [("/w/session-2026-01-02-x.md", 1500.0, "git")]
+    chk("wrap_verdict WRAPPED when an event lands inside the span",
+        wrap_verdict((1000.0, 2000.0), _E)[0] == "wrapped")
+    chk("wrap_verdict WRAPPED for an event just after the last write  [wraps land near the end]",
+        wrap_verdict((1000.0, 2000.0), [("/w/session-2026-01-02-x.md", 2400.0, "git")])[0]
+        == "wrapped")
+    chk("wrap_verdict UNWRAPPED when every event is outside  [negative control]",
+        wrap_verdict((1000.0, 2000.0), [("/w/session-1999-01-01-a.md", 500.0, "git"),
+                                        ("/w/session-1999-01-01-b.md", 5.0e8, "git")])[0]
+        == "unwrapped")
+    chk("wrap_verdict UNASSESSABLE-SUBJECT on an unreadable span  [must NOT read as 'no wrap']",
+        wrap_verdict((None, None), _E)[0] == "unassessable-subject")
+    chk("wrap_verdict UNASSESSABLE-CHECK when no wrap record can be enumerated",
+        wrap_verdict((1000.0, 2000.0), [])[0] == "unassessable-check")
+    _t0 = time.time()
+    chk("wrap_verdict declines to alarm when a record NAMES a day inside the span"
+        "  [commit lag must not become a false alarm]",
+        wrap_verdict((_t0, _t0 + 3600),
+                     [(f"/w/session-{time.strftime('%Y-%m-%d', time.localtime(_t0))}-x.md",
+                       _t0 + 10 * 86400, "git")])[0] == "unassessable-check")
+    # --- selection -------------------------------------------------------------
+    _now = 1_000_000.0
+    _spans = [("cur.jsonl", _now - 5, _now),
+              ("prev.jsonl", _now - 86400, _now - 12),
+              ("old.jsonl", _now - 400000, _now - 350000)]
+    chk("previous_transcript picks the session that ended 12 s ago  [the 2026-08-17 miss]",
+        previous_transcript(_now, _spans)[0] == "prev.jsonl")
+    _mid = [("cur.jsonl", _now - 1380, _now),          # running 23 min — a manual run
+            ("prev.jsonl", _now - 86400, _now - 1400),
+            ("old.jsonl", _now - 400000, _now - 350000)]
+    chk("previous_transcript excludes a LONG-running current session  [manual mid-session run;"
+        " keying on start alone regressed here]",
+        previous_transcript(_now, _mid)[0] == "prev.jsonl")
+    chk("previous_transcript keeps a quiet newest-start transcript  [negative control —"
+        " exclusion needs BOTH signals, not just newest start]",
+        previous_transcript(_now, _mid[1:])[0] == "prev.jsonl")
+    # --- real substrate --------------------------------------------------------
+    _ev = wrap_events()
+    _git = sum(1 for _p, _e, _s in _ev if _s == "git")
+    chk(f"wrap evidence is taken from git add-time, not mutable mtimes"
+        f"  [{_git} of {len(_ev)} from git]", len(_ev) > 0 and _git > len(_ev) // 2)
+    _v = [wrap_verdict(transcript_span(p), _ev)[0] for p in _tx[-14:-1]]
+    chk(f"a real session reads as WRAPPED end-to-end  [{_v.count('wrapped')} of {len(_v)}]",
+        "wrapped" in _v)
+    # ⚠ The old gate here demanded a real UNWRAPPED instance too, and PASSED on
+    # 2026-08-17 while the detector was systematically broken — it established that
+    # both verdicts OCCUR, never that either was CORRECT. Its subject was the
+    # spread of outcomes; the claim was their truth. Reported, not asserted.
+    print(f"  [note] real-session outcome spread: "
+          + ", ".join(f"{s}={_v.count(s)}" for s in sorted(set(_v)))
+          + "  — a spread is not a proof of correctness; the controls above are.")
 
     print("\nlive substrate:")
     chk("PENDING.md readable", read(PENDING) is not None)
@@ -676,16 +1109,23 @@ def main():
     o.append(f"\nGOVERNANCE DRIFT — ~/CLAUDE.md: {drift} substrate-contradicted claim(s)"
              " (detection only; correction needs [ESCALATE])")
 
-    ptot, pmis, pdead, pnp = sec_pointers()
+    ptot, pmis, pdead, pnp, wtot, wmis, wun = sec_pointers()
     o.append(f"\nMEMORY POINTERS — {ptot} checked · {len(pmis)} mis-authored · {len(pdead)} dead"
-             + (f" · {len(pnp)} non-portable" if pnp else ""))
+             + (f" · {len(pnp)} non-portable" if pnp else "")
+             + f"  |  {wtot} wikilinks · {len(wmis)} mis-authored · {len(wun)} unwritten")
     for f, ln, raw, fix in pmis:
         o.append(f"  MIS-AUTHORED {f}:{ln}  {raw}")
         o.append(f"    → target exists; replace with: {fix}")
-    for f, ln, raw, _ in pdead:
+    for f, ln, raw, age in pdead:
         o.append(f"  DEAD {f}:{ln}  {raw}  (no file of that name in ~/_Dev or the memory dir)")
+        o.append(f"    → {age}")
     for f, ln, raw in pnp:
         o.append(f"  NON-PORTABLE {f}:{ln}  {raw}  (resolves, but hardcodes this machine)")
+    for f, ln, slug, near in wmis:
+        o.append(f"  MIS-AUTHORED {f}:{ln}  [[{slug}]]")
+        o.append(f"    → the file exists; replace with: [[{near}]]")
+    for f, ln, slug in wun:
+        o.append(f"  UNWRITTEN {f}:{ln}  [[{slug}]]  (permitted forward-reference, not an error)")
 
     strays = stray_maps()
     if strays: