diff --git a/claude/memory/MEMORY-reference.md b/claude/memory/MEMORY-reference.md
index ae33f1e..b6cd821 100644
--- a/claude/memory/MEMORY-reference.md
+++ b/claude/memory/MEMORY-reference.md
@@ -34,6 +34,9 @@ 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 (2026-08-04 — the replay had never resumed; demoted on promote at the 2026-08-04 evening wrap)
+- [Session 2026-08-04 — the replay had never resumed](session-2026-08-04-the-replay-had-never-resumed.md) — **four mechanism hypotheses proposed and refuted in one day** (sleep · entity timeout · drain gating · Ollama saturation); the steward's *"how can this be so persistently elusive?"* stopped a fifth being born. **The answer came from killing the replay and reading what it left at rest, not from profiling.** `minCursor = Math.min(...)` over **all 11** modules; `structured`+`training` have **never processed an event** (0 deferrals, 0 errors) ⇒ floor pinned at 0 ⇒ every start a full rebuild. **13/13 restarts, 6/6 rebuild, 0 catch-up — the resume branch has never executed.** Explains #65's *"fails differently each time"* and why every real rate fix (ANALYZE 6.4×, B1.1, N6) changed nothing: completion is gated by **uninterrupted run length**, not rate. **Recall never worked either — `retrieval_count = 0` across 19,915 nodes / 813,178 chains** (writer + call site verified live first); ingestion-never-completes and recall-never-worked are **one fact from two ends**. Replay **killed** (steward-authorized, premise re-verified, 2 verified backups); **BMF down and staying down**. PENDING-92/93/94 filed; note pushed to Seb (`CapableMind-AI@ad285df`). **L1 now blocked on Seb.** **PULLING THREAD: census 01 against the chamber/engine tooling** — sharpened question: *has this instrument ever produced a positive result at all?*
+
 ## Archived (2026-07-28 mid-afternoon — Harrison broke the constitution, not the book; demoted on promote at the 2026-07-29 wrap)
 - [Session 2026-07-29 — coverage never attests order](session-2026-07-29-coverage-never-attests-order.md) — **The REVIEWED-83 Q3 precondition could not be satisfied by anyone**, and the jurist **WITHDREW it as its own error**: it demanded a coverage guard *FLAG* a reordering coverage is structurally blind to — already demonstrated on a real book (**Eichmann §7**, 07-19) and already ruled (**REVIEWED-74**, 07-24), **neither supplied to the jurist**. Measured against the repo's own `classify`: a **block-reversed candidate scores 100% match / 0 added / 0 interior lost / PASS** vs a *correct* reference — **independence cannot fix an operator that discards position**. Four extractors, zero shared PDF libraries, but **only docling recovers order**; the other four match poppler's documented `-raw`. My prediction that real two-column books would false-flag was **refuted by measurement**; only **0 of 17** born-digital *sources of record* are two-column. **Spec v2.9.0 LANDED** (`86311d6`, REVIEWED-84) — *coverage never attests order*; mechanism **deliberately NOT ratified**, eyeball-after-gate taken under condition (a)'s own second branch. A containment checker caught **six defects in my own package**, one meaning-changing. **PULLING THREAD — RESET BY THE STEWARD AT WRAP: close PENDING-85, diagnose PENDING-84, FIRST** — before any further instrument work. Measured basis: the last 3 days opened **12 governance items and closed none**; 11 more dormant since March–May; **27 open**. The work has been climbing away from the corpus (classifier → tier taxonomy → verification method → order instrument, all *instruments about instruments*) while **PENDING-84 is actual corpus damage** — 9 canonicals whose text cannot be derived from their source of record by any tier's method. Today built forward architecture for a hazard with **zero measured instances** (0 of 17) while those 9 sat a third day. **Executor framing failure:** the pacing question was put as *build now or bank*, never *build the instrument OR close the corpus defects*. `order_attestation:` is **demoted to second**, intact and unblocked (precondition MET; ⚠ do NOT carry the 0.995 floor — measured against order-*incapable* extractors). Detail in the session file.
 - [Session 2026-07-28 mid-afternoon — Harrison broke the constitution, not the book](session-2026-07-28-mid-afternoon-harrison-broke-the-constitution-not-the-book.md) — **The re-gate pilot broke the mechanism BEFORE converting a byte, and the break was CONSTITUTIONAL, not code.** `tier_of()` faithfully implements the ratified evidence-tier table, which enumerates tiers **by format** (*"V-SCAN (scanned pdf)"*) — so **16 born-digital-PDF canonicals with real ground truth get a false ABSTAIN** (*"as much a lie as a false PASS"*), Harrison among them. Census by mechanism: **60 canonicals resolve to a PDF · 35 scanned-with-OCR · 9 bare-scan · 16 born-digital**; `dominion` and `forests` are the SAME AUTHOR IN THE SAME FOLDER with opposite tiers. **Jurist design-gate PASSED, REVIEWED-83 AUTHORIZED + placed**, with two corrections: independence into the **constitutional text** — ⚠ **NOT by analogy with V-TEXT, which ruled the OTHER way** (shared pandoc reader accepted there because *reader-loss cancels a priori*; PDF recovery is inference over page geometry, so nothing cancels) — and the demonstration is of **TWO instruments**, the verification method having **no control at all**. **PULLING THREAD: the Q3 demonstration** — establish a genuinely independent extractor pair (poppler · pdfium · MuPDF: test lineage, don't assume), then construct the **column-order corruption** case and confirm the guard FLAGS it; that is what releases Harrison's stamp, and if no independent pair exists the honest verdict is **HELD**. Six steward corrections, one instrument catch (a fabricated quote in my own Grounding section — different media + mechanical + positive control). Maps got a durable home. Governance 15 → 19 open. Detail in the session file.
diff --git a/claude/memory/MEMORY.md b/claude/memory/MEMORY.md
index 2c80d55..03c9aa8 100644
--- a/claude/memory/MEMORY.md
+++ b/claude/memory/MEMORY.md
@@ -61,12 +61,13 @@ permalink: claude-memory/memory
 - [Source library — link + dedupe](project-source-library-link-and-dedupe.md) — steward's master ebook library = `~/Documents/___The Library [ePub_AWZ3]/` (2190 ebooks, messy nested). GOAL: link chamber↔sources (provenance index) + dedupe; real link needs EPUB/PDF internal metadata + edition-identity, not filenames. Detail + seed in file.
 - [Character-as-image hazard](feedback-character-as-image-hazard.md) — EPUBs rendering diacritics as inline images are SILENTLY MUTILATED by image-drop. Mechanism built (`apply_char_glyphs.py`, REVIEWED-70/v2.5.0), wired as a born-digital precondition; per-source glyph-maps still owed. VIEW the glyph; map to SOURCE form.
 - [Sidecar typology — protocol-dependent reading-indexes](project-sidecar-typology-protocol-dependent.md) — TWO layers: `.meta.json` structural sidecar = PROTOCOL-NEUTRAL (the graduated bar); reading-indexes (rich YAML) = PROTOCOL-DEPENDENT, probably PLURAL — **don't design the schema yet**; settle corpus to gold, let protocols declare themselves. Steward 2026-06-29.
-- Studium Engine — *no tracker file yet*; moves in per-session memories + the **[architectural charter](reference-studium-engine-architectural-charter.md)**. Steps 0–7 built; corpus CLEAN; **V1 `verify-quote` + `fidelity_equivalence@2` GOVERNING** (Greek/Latin census owed → @3). Stage-1 rebuild plan: V1 done → V2→V4 / N1→N3.
+- Studium Engine — *no tracker file yet*; moves in per-session memories + the **[architectural charter](reference-studium-engine-architectural-charter.md)** + **`docs/tool-evolution-log.md`** (built 2026-08-04 — organ reviews; **read its §0**: the discipline is attached to the human, so an automatically-invoked organ leaves no entry). Steps 0–7 built; corpus CLEAN; **V1 `verify-quote` + `fidelity_equivalence@2` GOVERNING** (Greek/Latin census owed → @3). ⚠ **The consuming end was first exercised 2026-08-04 and does not answer**: bare FTS tokens are conjunctive, no semantic layer, no test on `retrieve.py` at all (**PENDING-97**; silence now discloses its blindness, **PENDING-96** landed-but-open). Stage-1 rebuild plan: V1 done → V2→V4 / N1→N3.
+- [Instrument censuses — have our gates ever fired?](../governance/fool/census-02-have-they-ever-fired-RESULT.md) — `~/dotfiles/claude/governance/fool/`: **census 01** (does each gate have a real negative instance? → decay, not construction, is the failure mode) + **census 02** (has it ever fired at all? → the record divides by whether a human invokes it). Both pre-registered before the look; both had prediction 5 invert. Read before trusting any gate's silence.
 - [L1 reliability](project-L1-reliability.md) — canonical L1 tracker. **BLOCKED ON SEB (PENDING-94) — nothing moves until he rules; BMF is down and staying down.** The replay **has never resumed, only restarted**: `minCursor` is a minimum over all 11 modules and two never participate ⇒ every start rebuilds from seq 0 (13/13, 0 catch-up). Completion is gated by **uninterrupted run length, not rate** — which is why ANALYZE/B1.1/N6 were all real and all changed nothing. **Recall never worked either** (`retrieval_count = 0` across the whole April–June graph). Yesterday's "ingest mystery solved" was **corrected 2026-08-04**. **Read the tracker before ANY L1 work** — walked past once on 2026-08-03.
 - [Be (laundromat)](project-be-laundromat.md) — canonical Be tracker (est. 2026-06-08). Be = Skemantix startup (Seb+David) funding CapableMind's ladder; **bridge, not venture**. Decisions LOCKED (entity/pricing/infra in file); a11y gate MERGED. **Pre-revenue WTP gate = renovate Pat → charge her; discipline: no new spec until it clears → nothing for executor on be.** Repo @ `f43a0fd`.
 
 ## Active Session
-- [Session 2026-08-04 — the replay had never resumed](session-2026-08-04-the-replay-had-never-resumed.md) — **four mechanism hypotheses proposed and refuted in one day** (sleep · entity timeout · drain gating · Ollama saturation); the steward's *"how can this be so persistently elusive?"* stopped a fifth being born. **The answer came from killing the replay and reading what it left at rest, not from profiling.** `minCursor = Math.min(...)` over **all 11** modules; `structured`+`training` have **never processed an event** (0 deferrals, 0 errors) ⇒ floor pinned at 0 ⇒ every start a full rebuild. **13/13 restarts, 6/6 rebuild, 0 catch-up — the resume branch has never executed.** Explains #65's *"fails differently each time"* and why every real rate fix (ANALYZE 6.4×, B1.1, N6) changed nothing: completion is gated by **uninterrupted run length**, not rate. **Recall never worked either — `retrieval_count = 0` across 19,915 nodes / 813,178 chains** (writer + call site verified live first); ingestion-never-completes and recall-never-worked are **one fact from two ends**. Replay **killed** (steward-authorized, premise re-verified, 2 verified backups); **BMF down and staying down**. PENDING-92/93/94 filed; note pushed to Seb (`CapableMind-AI@ad285df`). **L1 now blocked on Seb.** **PULLING THREAD: census 01 against the chamber/engine tooling** — sharpened question: *has this instrument ever produced a positive result at all?*
+- [Session 2026-08-04 evening — the instruments that never fired](session-2026-08-04-evening-the-instruments-that-never-fired.md) — **Census 02 run entire on the seven instruments census 01 left uncensused. The firing record divides by whether a HUMAN is in the invocation path** — not by age, quality or importance. `audit_cruft`/`verify_conversion`/`apply_char_glyphs` exemplary (a curator invokes them); `resolve_archived_source` healthy 349/349 with **zero** log entries (nobody invokes it); `verify-before-compose` fired **exactly twice** (07-17, 07-18) recoverable only from harness transcripts; studium `verify-quote` + `fidelity_equivalence@2` have **no production caller at all**. **The hook cannot fire on the constitution it protects** — the existing file's own `GROUNDED-IN:` disarms it, 31 of 59 guarded files. **The engine was asked a question for the first time** and certified *"genuine silence, not a gap"* on `grey zone` over **ten `gray zone` matches in Levi** (corpus American-spelled, steward Canadian); mechanism is wider — bare FTS tokens are **conjunctive**, so recall dies as a question lengthens. Falsifier held (`the quality without a name` is *correctly* silent). **PENDING-95..98 filed together; 96 AUTHORIZED + LANDED on the jurist's sharper wording** (mine reproduced the overclaim one size down) and **stays OPEN** — `retrieve.py` has **no test at all**. Built: the **engine tool-evolution log**, seeded, **§0 declaring what it cannot see**. Two of my own findings died to their controls. **PULLING THREAD: name Chamber V1's purpose and settle the thirteen as its voice-set** — my "just go use it" was punctured by the steward's cycle (*engine missing x → source not golden → no bounded scope*); the break was already in his own tracker unread since 07-28 (*purpose choice and corpus scope are ONE decision*). Verified at wrap: **13/13 engine shas match disk** — the thirteen are NOT the 1,297, and the criterion is **stability, not quality**. One named defect inside them (Musil's stale voice-purity sidecar, off by 6).
 
 ## 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; the MemPalace `handoffs` glance was retired 2026-07-07 with the wind-down).
diff --git a/claude/memory/knowledge-graph.jsonl b/claude/memory/knowledge-graph.jsonl
index d2f42e7..9cc77f6 100644
--- a/claude/memory/knowledge-graph.jsonl
+++ b/claude/memory/knowledge-graph.jsonl
@@ -546,3 +546,12 @@
 {"subject": "the 2026-08-03 coherence_evaluated=0 lesson (verify a counter has a writer before trusting its zero)", "predicate": "prevention", "object": "Stopped a false claim about a DIFFERENT counter one day later. Investigating why recall never worked, retrieval_count/last_retrieved/recall_count/last_recalled all read 0 across 19,915 nodes. Rather than cite all four, checked each for a writer: retrieval_count has one (retrieval-tracker.ts:77) with live callers, so its zero is evidence; recall_count and last_recalled have NO writer anywhere in src/ (schema only), so their zeros mean nothing and would have been cited wrongly. A lesson banked from the coherence evaluator transferred to the retrieval counters \u2014 different subsystem, different session, same class.", "valid_from": "2026-08-04", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-04-the-replay-had-never-resumed.md", "extracted_at": "2026-08-04"}
 {"subject": "L1 / mindfabric-00 replay", "predicate": "never-completes-because", "object": "minCursor is Math.min across all 11 modules (replay-coordinator.ts:300); structured and training have never processed an event (0 deferrals, 0 errors) so the floor is pinned at 0 permanently; :340 classifies every start as rebuild and :368 skips nothing. 13/13 restarts at min cursor 0, 6/6 rebuild, 0 catch-up \u2014 the resume branch has never executed. Completion is gated by uninterrupted run length (38h at the documented-healthy 17 events/min), not by rate. PENDING-94 [ESCALATE]; Seb's surface.", "valid_from": "2026-08-04", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-04-the-replay-had-never-resumed.md", "extracted_at": "2026-08-04"}
 {"subject": "L1 / mindfabric-00 recall", "predicate": "has-never-returned-anything", "object": "retrieval_count = 0, last_retrieved on zero rows, across 19,915 nodes and 813,178 chains spanning April-June. Verified as a measured absence, not a blind one: writer at retrieval-tracker.ts:77, live callers in temporal/entity/vector/preference, temporal call site on the query return path guarded only by ids.length>0. The Recall canary logged FAILED 8 times vs PASSED 4. Same fact as never-completing ingestion, seen from the other end: no completed derived state to retrieve from.", "valid_from": "2026-08-04", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-04-the-replay-had-never-resumed.md", "extracted_at": "2026-08-04"}
+{"subject": "claude-code", "predicate": "drift-pattern", "object": "PROBED-AN-INSTRUMENT-IN-THE-WRONG-KEY-SPACE-AND-NEARLY-CALLED-IT-INERT — queried resolve_archived_source with the ENGINE's source_id (levi-drowned-and-saved) against the CHAMBER's canonical_slug key space (the-drowned-and-the-saved-primo-levi); got None three times INCLUDING the nonsense control, which should have been the tell, and was one sentence from reporting the resolver dead. It is healthy at 349/349. Twice in one session: also read character_as_image at the YAML top level and nearly reported zero glyph maps declared (it is at promotion.character_as_image, 2 sources, 63-item census). A null from an instrument you have not positive-controlled is a fact about your instrument.", "valid_from": "2026-08-04", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-04-evening-the-instruments-that-never-fired.md", "extracted_at": "2026-08-04"}
+{"subject": "claude-code", "predicate": "drift-pattern", "object": "THE-FIX-FOR-AN-OVERCLAIM-IS-AN-OVERCLAIM-CANDIDATE — replacing the engine's 'genuine silence, not a gap' with 'the index is complete and current' reproduced the same defect one size down: 'complete' is true of DOCUMENT COVERAGE and unverified of QUERY-MATCHING, and a reader without that distinction collapses the two exactly as the engine did. The repair inherits the frame that produced the original. Caught by the jurist, not by me. Re-reading a replacement as a stranger is a SEPARATE ACT from writing it.", "valid_from": "2026-08-04", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-04-evening-the-instruments-that-never-fired.md", "extracted_at": "2026-08-04"}
+{"subject": "the tool-evolution-log discipline (review after every use)", "predicate": "prevention", "object": "Its ABSENCE explained a whole class. Census 02 found the firing record divides by whether a human is in the invocation path: audit_cruft/verify_conversion/apply_char_glyphs are exemplary because a curator invokes them; resolve_archived_source runs on EVERY graduation, is healthy at 349/349, and has zero entries because nobody invokes it; verify-before-compose fired twice with evidence surviving only in harness transcripts. The recording is attached to the HUMAN, not the instrument — so a record vanishes exactly when a tool is automated, which is when it starts running often enough to matter.", "valid_from": "2026-08-04", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-04-evening-the-instruments-that-never-fired.md", "extracted_at": "2026-08-04"}
+{"subject": "the census pre-registration method (predict, then look)", "predicate": "prevention", "object": "Second census, second inverted prediction, and the discipline caught the reversal both times. Census 01 predicted weakness in the newest instruments and found it in the oldest (decay, not construction). Census 02 predicted FIRED-UNRECORDED dominant and was wrong about WHY — the skew is by human-in-the-loop, not by age or quality. Grading predictions written BEFORE the look is what converted two comfortable misses into the actual findings.", "valid_from": "2026-08-04", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-04-evening-the-instruments-that-never-fired.md", "extracted_at": "2026-08-04"}
+{"subject": "studium-engine retrieval", "predicate": "has-property", "object": "Conjunctive bare-token FTS5 with no semantic layer: gray 51 hits, gray zone 10, 'levi the gray zone' 0, 'what does levi mean by the gray zone' 0. Recall collapses as a question lengthens, so natural-language questions return certified silence by default. No vector table; embed/rerank stayed spikes. PENDING-97.", "valid_from": "2026-08-04", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-04-evening-the-instruments-that-never-fired.md", "extracted_at": "2026-08-04"}
+{"subject": "the studium engine's consuming end", "predicate": "was-first-exercised-on", "object": "2026-08-04 — the corpus was indexed 2026-07-19 (5,685 drawers, 13 sources) and no question was asked of it until this session. It ran, and certified that Levi has nothing to say about the grey zone over ten gray zone matches. Ingestion-elaborate / consumption-never-exercised is the same shape as L1's retrieval_count = 0.", "valid_from": "2026-08-04", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-04-evening-the-instruments-that-never-fired.md", "extracted_at": "2026-08-04"}
+{"subject": "the chamber-versioned-releases frame", "predicate": "prevention", "object": "Broke a deadlock the executor had walked straight into. I recommended 'stop building, go use the library'; the steward punctured it — 'the sources are not golden... it's a cycle of engine-missing-x / source-not-golden / no-bounded-scope'. The break was already written in his own tracker, unread since 2026-07-28: you never re-gate 1,297 files for a version, you re-gate the bounded voice-set the chosen purpose needs, which makes the corpus job and the purpose choice ONE decision, not sequential ones. A banked reframe dissolved a paralysis that neither party could argue their way out of in the moment.", "valid_from": "2026-08-04", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-04-evening-the-instruments-that-never-fired.md", "extracted_at": "2026-08-04"}
+{"subject": "claude-code", "predicate": "drift-pattern", "object": "RECOMMENDED-USE-WITHOUT-CHECKING-WHETHER-THE-SUBSTRATE-COULD-BEAR-IT — proposed a session of asking the corpus real questions without first checking whether the corpus was trustworthy enough for the answers to mean anything. The steward supplied the objection (sources not golden) and the check I should have run first: 13/13 engine shas match disk (so the thirteen ARE usable) and musil carries a stale voice-purity sidecar off by 6 (so one is named-defective). Both facts were one command away and would have shaped the recommendation instead of rescuing it afterwards.", "valid_from": "2026-08-04", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-04-evening-the-instruments-that-never-fired.md", "extracted_at": "2026-08-04"}
+{"subject": "studium-engine corpus (the thirteen)", "predicate": "has-property", "object": "A de-facto bounded voice-set: Levi, Arendt, Weil x2, Musil, Mauss, Alexander, Harrison + the steward's own five after-the-reply essays. All 13 manifest shas verified matching the canonical files on disk 2026-08-04. NOT the 1,297-file corpus (of which only 11 pass current graduation) — that number does not bound V1. One named defect inside the set: musil-the-man-without-qualities has a stale chamber-side voice-purity sidecar (boundaries derived at 5,032 lines, canonical now 5,038; the whose-words layer, not the citation layer), HELD not migrated.", "valid_from": "2026-08-04", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-04-evening-the-instruments-that-never-fired.md", "extracted_at": "2026-08-04"}
diff --git a/claude/memory/session-2026-08-04-evening-the-instruments-that-never-fired.md b/claude/memory/session-2026-08-04-evening-the-instruments-that-never-fired.md
new file mode 100644
index 0000000..bd2fbc8
--- /dev/null
+++ b/claude/memory/session-2026-08-04-evening-the-instruments-that-never-fired.md
@@ -0,0 +1,94 @@
+---
+name: session-2026-08-04-evening-the-instruments-that-never-fired
+description: "Census 02 run entire against the seven instruments census 01 left uncensused: every instrument a human runs by hand has a rich firing record, every instrument that runs by itself has none, and the two guarding the engine's output have no consumer at all. verify-before-compose fired exactly twice and cannot fire on the constitution it protects (31 of 59 guarded files disarmed). The engine was asked a question for the first time and certified that Levi has nothing to say about the grey zone, over ten gray zone matches. PENDING-95..98 filed together; 96 landed same session on the jurist's sharper wording and stays OPEN. The engine tool-evolution log built, seeded, with its own blind spot declared. PULLING THREAD: stop building and ask the library a real question — derive PENDING-97 from the consumer, not from my six invented probes."
+metadata:
+  node_type: memory
+  type: project
+---
+
+# Session 2026-08-04 (evening) — the instruments that never fired
+
+The day the chamber was finally asked something, and answered that it had nothing to say about the grey zone.
+
+## PAST — what moved, and why
+
+**Census 02, pre-registered before any source was read, run entire against the seven instruments census 01 declared out of scope.** Different question from 01: not *does this have a real negative instance* (capability) but *has it ever engaged in real life*. Those come apart exactly at the drift-checker's shape. Two axes recorded separately — engagement (can its trigger still match?) and firing record (does any durable record exist?) — because conflating them is the error.
+
+**The verdict: the record divides by whether a human is in the invocation path.** Not by age, not by quality, not by importance.
+
+- `audit_cruft` · `verify_conversion` · `apply_char_glyphs` → **FIRED-RECORDED**, exemplary. The chamber's `tool-evolution-log.md` is the strongest instrument record anywhere in the system — dated, artifact-named, PASS-BUT-FALSELY as the priority signal (160 corpus files found that the old gate was blind to; 948/952 with 4 genuine fails; Levi 527 docs 0 unclassified).
+- `verify-before-compose` → **FIRED-UNRECORDED**. Exactly twice: 2026-07-17 09:44:34 (Write), 2026-07-18 11:55:44 (Edit), recoverable only from Claude Code session transcripts — a harness artifact with unknown retention.
+- `resolve_archived_source` → **FIRED, UNLOGGED.** Healthy at 349/349, runs on every graduation, **zero** log entries — because no human invokes it.
+- studium `verify-quote` + `fidelity_equivalence@2` → **NO RECORD CAN TELL.** 42/42 tests, and no production call site anywhere.
+
+**The structural finding on the hook: it cannot fire on the constitution it exists to protect.** Lines 40–41 fold the *existing file's* contents into the search for the attestation, so any artifact already carrying `GROUNDED-IN:` is permanently un-gateable — **31 of 59** guarded files, including `chamber-library-specification.md`, all of v2.1.0–v2.9.0, and `graduation-spec.yaml`. Documented as designed ("or the existing file"; "a speed-bump… not a guarantee"); the *consequence* documented nowhere. Countervailing evidence recorded because it cuts the other way: all 28 un-markered files are dated ≤ 07-17, and every artifact created after the hook landed carries one.
+
+**The engine was asked a question for the first time, and that is the session's real finding.** The steward said mid-turn *"the engine has never run."* Taken as a claim to check rather than agreed with. It *runs* — `retrieve.py` returns citations, line numbers, a warrant, exit 0. But asked `grey zone` it replies **`SILENCE — ✓ warranted … genuine silence, not a gap`** while the corpus holds **ten** `gray zone` matches, all ten in `levi-drowned-and-saved`. The corpus is American-spelled; the steward is Canadian-spelled.
+
+Mechanism is wider than spelling: `retrieve.py:103` passes the normalized string straight to `drawers_fts MATCH`, where bare terms are **conjunctive**. `gray` 51 → `gray zone` 10 → `levi the gray zone` **0** → `what does levi mean by the gray zone` **0**. Natural-language questions — precisely what *"enter into discourse with my library"* means — return certified silence by default. No vector table; the embed/rerank spikes stayed spikes.
+
+**Discrimination held, and it is what keeps the finding honest:** the probe `the quality without a name` returns the same certified silence and is **correct** — *The Timeless Way of Building* is not among the 13 sources. One real defect and one real correct silence side by side.
+
+**Filed together at the steward's instruction** (*"something tells me there will be more"* — right): **PENDING-95** `[HARDENING]` the hook can't fire on the constitution · **PENDING-96** `[HARDENING]` the warrant certifies the index and claims the answer · **PENDING-97** `[PROPOSAL]` conjunctive tokens, no semantic layer · **PENDING-98** `[HARDENING]` firing history exists only where a human invokes.
+
+**PENDING-96 authorized and landed same session — with the jurist's wording, not mine.** My replacement (*"the index is complete and current"*) was **a smaller version of the same overclaim**: "complete" is true of coverage and unverified of matching, and a reader without that distinction collapses them exactly as the engine did. Shipped instead: *"Every document … was scanned … The query as submitted matched no indexed tokens."* Same logic extended one step further than asked, to the mark itself — `✓ warranted` beside a silence reads as *this silence is correct* → **`✓ coverage-warranted`**. Plus (b) `RETRIEVAL_BLINDNESS` as a fixed constant on *every* silence, its content verified against `chunker.normalize` and the FTS5 path rather than asserted; plus the (c) `silence_tier: "single-method"` tag as cheap insurance against a third string migration. A `⚠` at the constant binds it to PENDING-97 **in code, not in memory**.
+
+**PENDING-96 stays OPEN** on the jurist's process point — shipping a better string is itself a small "feeling of done." Three conditions remain, one of which the follow-up surfaced: **`retrieve.py` has no test at all.** Nothing in `tests/` references it. The organ whose output the steward reads directly is unguarded.
+
+**Built: the engine tool-evolution log** (`studium-engine/docs/tool-evolution-log.md`), steward-authorized. Deliberately **not** a copy of the chamber's — a straight copy would have reproduced census 02's blind spot inside the artifact built to answer it. It opens with **§0 declaring what it cannot see**: automatic invocation leaves no entry; absence of an entry is not absence of use. Seeded, not empty (an empty log is a governor that never engages) — two entries first-hand, two marked BACK-FILLED from the repo record. The back-fill surfaced something nothing was recording: the rebuild plan designates `pattern_finder`'s known-bad pass-1 output as **V4's first adversarial fixture** — it must not be deleted or regenerated.
+
+**Also landed:** `[FIX]` the `verify_quote` header, which asserted `@1` *and* a "word-aligned match" the organ does not perform — contradicting its own `_stage2` docstring on the exact distinction the `@2` ruling turned on.
+
+**Commits:** `studium-engine@782481b` (FIX), `@1085d09` (log), `@49a8851` (silence). `dotfiles@3a1790d` (census + PENDING-95..98), `@dca2d5d` (96 addendum). Two hats kept separate.
+
+## PRESENT — how it stood
+
+**Two of my own candidate findings died to their own controls, and that is the session's best evidence that the discipline works.** I probed `resolve_archived_source` with *engine* `source_id`s against the *chamber's* `canonical_slug` key space, got `None` three times including the nonsense control, and was one sentence from reporting "the resolver is inert" — the positive control (real slugs drawn from the manifest) showed it healthy at 349/349. Then I read `character_as_image` at the wrong YAML nesting and nearly reported "zero glyph maps declared"; it sits at `promotion.character_as_image` with 2 sources and a 63-item census. Same failure class as yesterday. Both caught before the claim left the workspace.
+
+**The transferable lesson, and it is new: when you fix an overclaim, the replacement is an overclaim candidate.** The repair inherits the frame that produced the original. Re-reading it as a stranger is a separate act from writing it, and I skipped that act — the jurist did it for me.
+
+**Also carried: the aliased `ls` and BSD `stat` bit twice more** (empty directory listing while `find` read the same tree; `stat -f` format flags failing). Yesterday's KG entry named this exact class. Knowing the name still confers no immunity — but this time I noticed inside one command rather than shipping the number.
+
+**The steward's closing image is the session's most accurate diagnosis** — *adrift, or Hyperion on the shore reaching for his abandoned lute*. The lute is not lost. It is set down, and lying right there. Rubbed against the touchstone's Q1, months of work have been making sure the voices *could* be genuinely theirs, and we have never once let them be. The corpus holds Levi, Arendt, Weil ×2, Musil, Mauss, Alexander, Harrison — **and the steward's own five `after-the-reply` essays**, which is why one probe returned `[glidden]` beside `[levi]`. His voice has been in the chamber with theirs since July, unasked.
+
+## FUTURE — what pulls
+
+**PULLING THREAD: name Chamber V1's purpose and settle the thirteen as its voice-set — the one decision that bounds all three arms of the cycle.**
+
+⚠ **My first answer to this was wrong and the steward punctured it at the wrap.** I proposed "stop building, go ask the library a question." He named the actual trap: *"the sources are not golden… it's a cycle of 'the engine is missing x, the source is not golden, we have no bounded scope'."* Use alone does not survive that objection — answers from a corpus you cannot trust teach nothing and may mislead.
+
+**The break was already written down, ten days unread.** `project-chamber-versioned-releases`, 2026-07-28 addendum: *"you never re-gate 1,297 files for a version. You re-gate the bounded voice-set the chosen purpose needs — which makes the corpus job and the purpose choice **the same decision, not sequential ones**. A version's corpus work is therefore finite by construction."* And: *"the enormity was the paralysis — 'the corpus must be trustworthy before I can use it' collapsed into 'wait for everything.'"* The open decision — **which purpose anchors V1** — has been open since 2026-07-25.
+
+**What the wrap-time check established (verified, not inherited):** **all 13 engine manifest shas match the canonical files on disk, 13/13.** The engine's binding is intact and its citations land where they claim. The corpus-wide *11 of 1,297 pass graduation* number is **not V1's problem** — the thirteen are not the 1,297. They accreted rather than being chosen, but they are bounded and bound.
+
+The tracker's selection criterion is **stability, not quality** ("re-conversion breaks engine work, not imperfection"), with properties **proven-or-named**. Against that bar the thirteen largely hold. The one named defect inside them: `musil-the-man-without-qualities` carries a **stale chamber-side voice-purity sidecar** — boundaries derived at 5,032 lines, canonical now 5,038, so section boundaries are off by six. That is the *whose-words* layer, not the citation layer; a passage near a boundary could be apparatus served as Musil. It was **HELD, not migrated** — named, which is what the frame permits. It is V1-blocking only if V1's purpose leans on Musil.
+
+And what accreted is not random: Levi · Arendt · Weil ×2 · Musil · Mauss · Alexander · Harrison · the steward's own five `after-the-reply` essays — a coherent chamber on moral witness under coercion, attention, dwelling, and making.
+
+**ACTIONABLE RESUMPTION POINT (as of wrap — re-judge against what changed):**
+```
+1. Read project-chamber-versioned-releases.md ENTIRE (not the MEMORY.md one-liner).
+   The open decision is its final paragraph + the 2026-07-28 addendum.
+2. Name V1's purpose. The candidates are already listed there:
+   the Making Sequence · the violin/music-in-the-XXI-c treatise · ARC.
+3. Test the thirteen AGAINST that purpose by asking them real questions —
+   use as the INSTRUMENT of the scoping decision, not a substitute for it:
+     cd ~/_Dev/studium-engine && python3 engine/retrieve.py "<real question>"
+   Works now: single terms + short phrases. Fails: conjunctive/long queries.
+   Record: question · served? · what it reached · what it missed and why.
+4. That record settles THREE things at once: whether the thirteen are V1's
+   voice-set, what capability envelope V1 needs (= PENDING-97's input, derived
+   from the consumer rather than my six invented probes), and which open
+   library questions are V1-blocking vs V2-deferrable.
+```
+
+**LITERAL QUESTION for next-Claude:** *Do the thirteen that accreted turn out to be the voice-set a named purpose would have chosen — and if not, which are missing?* Checkable: name the purpose first, then ask the corpus its questions and see what it cannot answer for lack of a voice rather than for lack of retrieval. The distinction between those two failures is the whole scoping decision.
+
+**Other horizons, ranked.**
+- **Open, awaiting steward:** PENDING-95 (hook re-grounding rule; self-contained, doesn't touch the engine) · PENDING-97 (the retrieval decision, carries a curatorial call that is the steward's: whose orthography is canonical when corpus and reader differ) · PENDING-98 (firing-count line in the wake digest).
+- **PENDING-96 open by design** until 97 is ruled → blindness text re-verified → the six probes bound in a test.
+- **Blocked on Seb:** PENDING-92/93/94. BMF down and staying down.
+- **Flagged, not acted on:** BetterMemories.io carries 38 MB / 4,091 files of untracked `dist.rollback-*` + `data.archive-*` that `.gitignore`'s `dist/` and `data/` patterns do not reach — one `git add -A` commits them into L1. CapableMind-AI carries 6 governance docs from 2026-07-27, untracked and named nowhere in `thinking/README.md`.
+- **Named, uncensused:** does any other module header assert a version or a method it no longer performs? The `verify_quote` case was found by accident.
+
+**PAUSE STATEMENT:** I am putting this down with the instruments finally audited and the thing they serve barely touched. Nothing is half-written: four items filed, one landed and honestly left open, three repos committed. What I want to find still pulling is **the use session** — because everything else on the list is more scaffolding, and the steward named the cost of that himself. The failure mode to guard against on return is the one that produced the adrift feeling: reaching for the next instrument because instruments are what we know how to build.
diff --git a/claude/memory/skill-harvest-register.md b/claude/memory/skill-harvest-register.md
index 41f6609..76bf66c 100644
--- a/claude/memory/skill-harvest-register.md
+++ b/claude/memory/skill-harvest-register.md
@@ -236,3 +236,14 @@ The single place proposed skills live so they don't evaporate between sessions.
 **Applied at this wrap under the §1.6 FIX lane** (mechanical repo-CLAUDE.md freshness; classification test: changes neither executor latitude nor a governed artifact's assertion — it removes a claim the substrate contradicts; hard floor not engaged, no open item's visibility reduced): ARC `CLAUDE.md` asset-structure listed `js/ # JavaScript (theme toggle)`; the directory **does not exist** and the toggle was retired with the JS pipeline at Stage M (2026-06-01). Replaced with a note recording the retirement. Indexed in `skill-harvest-fix-lane-index.md`.
 
 **Noticed, not fixed (needs steward/jurist — vignette Phase 4 scope):** `vignette-specification.md` Part II Phase 4 prescribes moving `assets/js/glyphs/` to `assets/js/glyphs-archived/`; that tree no longer exists, so part of the quarantine phase is already moot. And `AldineXXI-specification.md` §IX still says genomes are *"Generated by a local model via Ollama"*, which the companion superseded (Part II, *Engine evolution*). Both recorded in the under-determination census; §IX is sealed-spec.
+
+---
+
+## New proposals (2026-08-04 evening wrap — census 02 + the engine's first questions)
+
+| Element | Kind | One-line | Where it lands | Status |
+|---|---|---|---|---|
+| **`/census` — the pre-registered instrument census** | **create** | **Strongly earned: two runs, ten days apart, both productive, and in BOTH the pre-registration caught a reversal the run would otherwise have banked comfortably.** Method: pre-register question + unit of census + the test applied + numbered predictions *with confidences* + a discrimination condition (what result would mean the census discriminated nothing) + stopping rule → run entire, no sampling → **grade the predictions**. Census 01's lenience clause converted a pleasant miss into the real finding; census 02's condition forced the "both buckets populated" check and its prediction-5 inversion *was* the result. Also carries the two-axis discipline (engagement vs record) that kept "it works" and "we can tell it works" from collapsing. | new `/census` skill | PROPOSED |
+| **Symmetria §3 flag: `the-fix-for-an-overclaim-is-an-overclaim-candidate`** | Symmetria §3 flag | When you repair an overclaim, **the replacement inherits the frame that produced the original.** Replacing the engine's *"genuine silence, not a gap"* with *"the index is complete and current"* reproduced the identical defect one size down — "complete" is true of document coverage and unverified of query-matching, and a reader without that distinction collapses the two exactly as the engine did. Caught by the jurist, not by me. **Re-reading a replacement as a stranger is a separate act from writing it**, and it is the act that gets skipped because the repair feels like the careful part. | Symmetria §3 | PROPOSED |
+| **Widen `assert-from-derivation-not-substrate` with the null-result case** | Symmetria §3 patch | A **null** from an instrument you have not positive-controlled is a fact about your instrument, not about the world. Probed `resolve_archived_source` with *engine* `source_id`s against the *chamber's* `canonical_slug` key space; got `None` three times **including the nonsense control** — which should have been the tell — and was one sentence from reporting a healthy 349/349 resolver dead. The existing flag covers asserting *presence* from a derived form; it does not name **asserting absence from an un-controlled probe**, which is the more seductive half because a null feels like an observation rather than a claim. | Symmetria §3 (widen the existing consolidated flag) | PROPOSED |
+| **`/wake-up` patch — a tracker marked THE GOVERNING FRAME is read ENTIRE, not as its pointer** | patch | **Earned at a measured cost of ten days.** `MEMORY.md` carries *"[Chamber as versioned releases] — **THE GOVERNING FRAME for all library work.** Scope every library bite through this"* — and the file itself held the resolution to the paralysis the steward named at this wrap (*purpose choice and corpus scope are ONE decision, not sequential*), written 2026-07-28 and unopened since. The index entry cannot carry a reframe; only the file can. Proposal: where a tracker line declares itself governing, `/wake-up` opens the file rather than trusting the one-liner — the same logic as the telos-conditional already wired in §2.a. Kin to `feedback-resurface-banked-notes-before-rederiving`, one level up: not *re-deriving* a banked note but *never opening* it. | `/wake-up` §2.a | PROPOSED |