dotfiles/claude/memory/MEMORY.md

name, metadata, permalink

name	metadata	permalink
	node_type title type permalink originSessionId modified memory MEMORY note claude-memory/memory 22915403-bc5d-4796-9c7d-196b7c30d2f9 2026-08-17T13:20:44.481Z	claude-memory/memory

Claude Code Memory

Standing preferences

Entries keep their rule inline when they fire at a moment I would not recognize as needing a lookup; they shrink to a pointer when the trigger is loud enough that I'd open the file anyway. A ⚠ constraint always travels with the workaround it limits.

Rules that fire silently — keep these in front of me

• Fowler's rules for quotation — single quotes primary, double for nested, logical British punctuation order. All writing.
• Canadian spelling in ARC prose — centre/colour ("almost EU"). Draft all steward-voiced prose this way; corpus "center" = autocorrect drift (cleanup open).
• Close thoroughly — no frequent deferrals — frequent deferrals ARE how the cloud accumulated. Close ALL of a block that's closable-now; for the rest, name the specific dependency.
• Shorter, concentrated sessions — ONE tightly-scoped high-leverage bite taken all the way, then wrap; hold the rest as ranked horizons.
• Constitution-as-block, then pull-based corpus — finish the constitution as one block FIRST, then corpus-into-spec pulled by what each engine phase needs. Bounded question → bounded answer; keep open-thread count LOW.
• Removing a claim ≠ removing the reliance — cutting an unsupported sentence can hide the gap; the dependency survives, now invisible. Test: does the conclusion still need it?
• Derive the rule from the consumer, not the survivor — choosing between two disagreeing implementations is selection, not derivation. Derive from what a CONSUMER must do.
• Rank on fields you actually write — a consumer ranking by an evaluative field nothing populates degrades to trivial order while claiming to rank. Verify scoring fields end-to-end; prefer signals already captured.
• The central path — answerability, not purity — the contamination recursion is probably irresolvable, so bind the claims, don't certify the parties. Route by claim-type: checkable → produce the check + a falsifier; judgment → disclose standpoint in one line, decide, record; undecidable → name it open. One layer, then act — never audit the audit.
• Notes are part of the work — footnotes/endnotes are integral: KEEP+CONVERT (<sup><a>→[^N]), never drop on graduation.
• One-shot instruments are proportionate — a measurement answering a question asked once is NOT a directive violation; its counterfactual is an assertion, not a durable tool. The violation is re-writing what's already banked (rule of three → ladder). Too few promoted, not too many built.
• Grounding finds my errors, not my support — three packages running, every omission cut AGAINST my own case. Ground in TWO passes: (1) what did I get wrong? (2) what already says this? Search the register for the CONCLUSION, not just the citations. ⚠ Quote from the FILE, never from the relayed message — placement adds and cuts.
• Resurface banked notes before re-deriving · Checkable claim surfaces bugs · Census by mechanism, not proxy · Completion is a tripwire · Trust prior pass frame — the five epistemic disciplines. Kernels: read the banked note before re-deriving · a checkable claim over a soft classification is itself a defect-detector · census by RUNNING the real pipeline · the feeling of "done" is the cue to verify the tail · re-run a prior verification at the scope of your extension. ⚠ Also carried as Symmetria §3 flags — two surfaces, deliberately: §3 loads only when Symmetria is invoked, so these stay here for sessions where it isn't.

Loud trigger — pointer suffices

• Chamber work: ground in constitution + charter + runbook FIRST — 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 — 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 — the named instruments; reach for the gate the claim's shape demands instead of re-deriving one.
• Skill-harvest register — 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. Recommendation (a): HOLD until graded — the null action, in force by default while PENDING-141 is open. ⚠ 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 — draft PENDING/REVIEWED blocks as plain fenced markdown; display formatting leaks into the placed record.
• Verify-before-compose hook — chamber constitutional writes are BLOCKED without <!-- GROUNDED-IN: … --> + verbatim Grounding. Don't fight the block.
• Tool review after each use — 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 — 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 — 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 — 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 — the engine's constitutional doc. Read before building. · Sixtus-V collaboration — build freely, surface only vision-forks; constraint-candidates = 3rd governed instrument. Studium-engine only.
• CapableHands standing authorization — 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 — ~20 type masters at ~/.mempalace/palace-chamber-typography; mempalace --palace <that> search "…". For ARC typography; don't re-ask where it lives.
• Steward maps live in ~/dotfiles/maps — a map = an artifact David reads directly to orient. Write to ~/dotfiles/maps/, symlink to Desktop, never straight onto the Desktop.
• Plane coordination workflow — CENTRAL to steward↔Seb: app.plane.so/capablemind, thin effort-tasks [BM #N] over canonical GH issues. ⚠ BBF = BetterBridge product, NOT the board.
• MemPalace is an unaffiliated stopgap — third-party; don't conflate with BMF/CapableMind. MemPalace PRs await MemPalace's maintainers, not Seb.
• The maturation of the chamber — a dialogue — the 2026-06-28 exchange on the chamber's telos (fidelity-without-trust; reading-is-unsolvable-is-the-feature). Companion to project-studium-engine-telos-chamber-of-voices.

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 — 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 — 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 — 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 — 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 — it lives in seven sources across two repos + memory. A single home would become an eighth unless it supersedes or points.
• L1 reliability — canonical L1 tracker. BLOCKED ON SEB (PENDING-94); BMF is down and staying down. The replay has never resumed, only restarted (minCursor is a minimum over 11 modules, two never participate ⇒ every start rebuilds from seq 0). Completion is gated by uninterrupted run length, not rate. Recall never worked either (retrieval_count = 0). Read the tracker before ANY L1 work — walked past once on 2026-08-03.
• Instrument censuses — have our gates ever fired? — census 01 (has each gate a real negative instance? → decay, not construction, is the failure mode) + census 02 (has it fired at all? → the record divides by whether a human invokes it). Both pre-registered. Read before trusting any gate's silence.
• ARC open-work register — the single code-verified source of truth for what is OPEN on ARC. Read THIS for remaining ARC work, not the chronological tracker. · ARC — chronological record; Stage G DONE/SEALED (GPG ac0a7ee) — reactive mode governs.
• Source library — link + dedupe — master ebook library ~/Documents/___The Library [ePub_AWZ3]/ (2190 ebooks). GOAL: link chamber↔sources + dedupe; a real link needs EPUB/PDF internal metadata + edition-identity, not filenames.
• Sidecar typology — protocol-dependent reading-indexes — .meta.json structural sidecar = PROTOCOL-NEUTRAL (the graduated bar); reading-indexes = PROTOCOL-DEPENDENT and probably PLURAL — don't design the schema yet.
• Character-as-image hazard — EPUBs rendering diacritics as inline images are SILENTLY MUTILATED by image-drop. Mechanism built + wired; per-source glyph-maps still owed. VIEW the glyph; map to SOURCE form.
• Making sequence source set — COMPLETE against the ReadingList (reconciliation-verified). Sourced ≠ ingested. Read before any Making/studium source work.
• Studium = CM's unfettered sandbox — experiment freely on library/engine without risking CM's runtime; breakthroughs transfer back. Steward-framed 2026-07-08.
• Be (laundromat) — 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.
• 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

🔑 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 — 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.

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 — 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. ⚠ 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.