diff --git a/claude/memory/MEMORY.md b/claude/memory/MEMORY.md
index 3abac21..c3af612 100644
--- a/claude/memory/MEMORY.md
+++ b/claude/memory/MEMORY.md
@@ -50,7 +50,10 @@ permalink: claude-memory/memory
 - [Be (laundromat)](project-be-laundromat.md) — canonical workstream tracker established 2026-06-08 (Seb-relay of locked decisions). Be = Skemantix startup (Seb+David) funding CapableMind's funding-ladder; **bridge, not venture**. Decisions LOCKED: entity/exit (CapableMind decoupled, grant-funded), pricing (Living $12.99/mo · Archive $69.99/yr · Memorial $49.99/yr · Renovate ~$199 · $8.99 floor), CF Self-Serve Agency + versioned-template-package infra. **a11y gate MERGED (Pat 100/100/100).** Pre-revenue: the WTP gate = renovate Pat → charge her. **Discipline: stop adding spec until the gate clears → nothing for executor on be until then.** Repo @ `f43a0fd`.
 
 ## Active Session
-- [Session 2026-06-30 — clasp memory-check + library indexer](session-2026-06-30-clasp-memory-and-library-indexer.md) — Two arcs. **ARC 1 (clasp):** steward's memory ("we connected before, late April") OVERTURNED yesterday's GREENFIELD scope — `mindfabric-00` paired into the **founders mesh since 2026-04-18** (kronos=clasp, **ALIGNMENT-not-inference**, `CLASP_BASE_MODELS` never configured, cloud 502); the wanted thing (CapableHands as a *local inference* clasp for the Air) IS new but the pairing mechanism is proven. Drafted `note-for-seb-2026-06-30-clasp-state-and-plan.md` + committed/pushed all CM-AI L1 thinking docs (`5801d8f`) so the 15:00 Seb meeting plans the clasp WITH him, not solo (a RETURN to the 06-23 §3b framing). KG updated. **ARC 2 (library indexer, priority 2):** built Phases 1–3 (chamber-library `98d18d7`→`dee8943`, PUSHED): P1 `index_library.py` (2190 ebooks, 0 err, internal metadata); P2 `link_chamber_sources.py` (forward provenance + REVERSE **1649 works in library NOT in chamber**; KEY FINDING **exact-source=0** → chamber's Making sources are DISJOINT from the master library → integrated `~/__Making sequence sources/` as `--also` pool, 9 works resolved); P3 `propose_library_dedupe.py` (Tier A **934MB/115 files safe**, B review, C flag-only, proposes-never-deletes). Refinements: author-sort fingerprint KEPT, PDF first-page heuristic REJECTED (tested, noisy), **content-QUALITY keeper probe** added (EPUB toc/spine/scan/fffd; flipped real cases — kept clean-content over clean-name). Caught+fixed a self-introduced extract_pdf regression (tool-review). calibredb 9.9 operable. **NEW STEWARD TARGET:** two Calibre libraries — "Chamber Originals" (byte-preserved, MD-linked) + "the rest"; consolidate the 2 existing Calibre libs; Loeb DSL excluded. **PULLING THREAD: indexer is read-only-complete → next is the MUTATING consolidation (draft read-only plan: calibredb two-tree build + authorized Tier-A dedupe + MD↔original linkage) for steward authorization.** Q: which removals did the steward authorize from the dedupe proposals, and did the Seb meeting turn the clasp into a joint plan?
+- [Session 2026-06-30 evening — Loom/Mill convergence + consolidation reframe](session-2026-06-30-evening-loom-mill-and-consolidation.md) — Two converging arcs. **ARC 1 (Loom/Mill):** Seb's instance shared the Spec Loom & Mill methodology (2026-06-28); I acted by GROUNDED reconciliation not theory (the docs name theory-bloat as the most-acute disease) — two halves of one four-party team independently re-derived ONE governance genome; we've built its instruments by hand (ratchet=skill-harvest+tool-evolution-log+ladder; two-register split=MemPalace↔MEMORY.md already executed; diseases=Symmetria §3 flags), and hold pieces they only NAME (authorization-taxonomy=governance-of-the-ratchet; contamination-problem=mechanism under "judge-overwhelmed-into-assent"). Built+pushed CM-AI `2a53ac3`: reconciliation + governance field-guide + David→Seb message. **SLM-1 (Chamber's independence) = David's ticket; the Chamber is THE Chamber.** **ARC 2 (consolidation):** CHALLENGED THE FRAMING (steward: Calibre was only a cheap catalogue means) → reframed substrate to **plain files + regenerable manifest**, Calibre demoted to disposable view (dissolves byte-preservation tension by construction); rewrote the read-only plan. **Audited Ars Legendi** (steward's PRE-PIPELINE ARC-spec source collection, all critical): 48 books = 19 dupe/3 same-work/**26 UNIQUE** (several = chamber needs-locate) → absorb selectively. **PULLING THREAD: the Chamber consolidation IS the methodology's real test slice (=SLM-1); execute Phase 0→1 tomorrow from the substrate-correct plan, gated on steward's Tier-A cut + Q-answers + Seb's clasp instructions.** Steward ended low/tired — released to rest. Q: did Seb send clasp instructions overnight + has steward made his Tier-A cut?
+
+## Archived (2026-06-30 evening — Loom/Mill + consolidation reframe)
+- [Session 2026-06-30 — clasp memory-check + library indexer](session-2026-06-30-clasp-memory-and-library-indexer.md) — Two arcs. **Clasp:** steward's memory overturned the GREENFIELD scope — `mindfabric-00` paired into the founders mesh since 2026-04-18 (kronos=clasp, ALIGNMENT-not-inference, cloud 502); local-inference clasp IS new but mechanism proven. Note-for-Seb + pushed CM-AI L1 docs (`5801d8f`) to plan WITH Seb at 15:00. **Library indexer (Phases 1–3, chamber `→dee8943` PUSHED):** index 2190 ebooks; link both directions (exact-source=0 → Making sources disjoint, `--also` pool resolved 9); dedupe proposals (Tier A 934MB safe; content-quality keeper). Steward target: two Calibre libs (Chamber Originals byte-preserved + the rest). Read-only-complete → mutating consolidation owed.
 
 ## Archived (2026-06-30 — clasp memory-check + library indexer)
 - [Session 2026-06-29 — graduations, pipelines, and the clasp pivot](session-2026-06-29-corpus-graduations-pipelines-clasp-scope.md) — Long, two-arc day. CHAMBER: graduated **4 Making works** (Taylor→hermeneutics [pattern-setter: footnote family B + loud-abort guard], Virilio→french_theory [family C caret-chapter], Handke→literature/contemporary [+ size-sanity guard after a near-miss], Illich→environmental); **folded RAW_HTML into audit_cruft** (`9e99e07`, gates now agree, honest 1215/72→1220/70); built `clear_safe_html_residue.py` (cleared 11 svg/nav files, guard refused 9 incl. Arden's 10k-word near-deletion). **Launched overnight pipelines**: CapableHands olmOCR ×3 (Jonas→Mumford MoM I→II) + local docling ×3 DONE (**Technics&Civ clean → resolves the parked corrupt EPUB**, Speed&Politics, Burnout). **Mapped the whole landscape**: remaining Making EPUBs = Kindle-derived structure-lost sub-batch (need a tool built once); the 72→70 backlog = **mostly the reconvert-FLAGGED set** (source-matched 24/34 to the library); scoped the **metadata indexer** (keystone for link+dedupe+locate) + found the **1263-missing-sidecar gap** (952 Loebs = parseable H1 headers, never-YAML/never-stripped). PARKED: Alter Psalms (character-as-image), Kindle EPUBs, poetry-fenced_div. Then **PIVOT to L1** (Seb meeting tmrw 15:00): N6 deploy holds (wedge gone), scoped **standing up CapableHands as a BMF clasp** (43M). **PULLING THREAD: the clasp deploy on CapableHands TOMORROW MORNING (before 15:00 Seb call) — priority 1; indexer priority 2.** Q: can the clasp stand up end-to-end, or does the pairing-unknown become the Seb conversation? chamber `15ea750` + studium `844b207` pushed.
diff --git a/claude/memory/session-2026-06-30-evening-loom-mill-and-consolidation.md b/claude/memory/session-2026-06-30-evening-loom-mill-and-consolidation.md
new file mode 100644
index 0000000..c7ea5fc
--- /dev/null
+++ b/claude/memory/session-2026-06-30-evening-loom-mill-and-consolidation.md
@@ -0,0 +1,71 @@
+---
+name: Session 2026-06-30 evening — the Loom/Mill convergence + the consolidation reframe
+description: "Two converging arcs. (1) Seb's instance shared the Spec Loom & Mill methodology (2026-06-28): I absorbed it as a GROUNDED reconciliation, not more theory (the docs name theory-bloat as the most-acute disease) — two halves of one four-party team independently re-derived ONE governance genome; we've built its instruments by hand (ratchet=skill-harvest+tool-evolution-log+ladder; two-register split=MemPalace↔MEMORY.md, already executed; diseases=Symmetria §3 flags). Wrote reconciliation + governance field guide + a David→Seb message; pushed CM-AI 2a53ac3. (2) The library consolidation: challenged the framing (steward: Calibre was only a cheap catalogue means) → reframed substrate to PLAIN FILES + REGENERABLE MANIFEST, Calibre demoted to disposable view (dissolves the byte-preservation tension by construction); rewrote the read-only plan. Audited Ars Legendi (steward's pre-pipeline ARC-spec source collection, all critical): 48 books = 19 dupe / 3 same-work / 26 UNIQUE, several = chamber needs-locate items → absorb selectively. PULLING THREAD: the Chamber consolidation IS the methodology's real test slice (= SLM-1); execute Phase 0→1 tomorrow from the substrate-correct plan, gated on the steward's Tier-A cut + Q-answers + Seb's clasp instructions. Steward ended low/tired — released to rest; nothing pending on him tonight."
+metadata:
+  node_type: memory
+  type: project
+  originSessionId: 019pnD8uNFC9Q2dbLQa3MBDc
+---
+
+# Session 2026-06-30 evening — the Loom/Mill convergence + the consolidation reframe
+
+Woke ~56min after the morning wrap (brief pause). Pulling thread held: library indexer read-only-complete → mutating consolidation plan awaits steward decisions. Then the day turned: mid-Seb-meeting the steward shared three documents that reoriented the evening.
+
+## ARC 1 — the Spec Loom & Mill methodology (Seb's instance, 2026-06-28)
+
+Steward shared three docs (`~/Library/Messages/Attachments/…`: david-summary, canonical-page-append, methodology-record). His words: *"vitally important to our (yours, mine, Seb's, Seb's instance of you) work… an important moment to act."*
+
+**What it is:** Seb + his instance reframed the Loom/Mill into a *living methodology for working with AI* — spec-as-genome / artifact-as-phenotype, "regenerate don't maintain," with a governance layer (write-back ratchet, structure-preserving transformation as compass, values-as-filter, a disease threat-model, a pattern palette), grounded in the ThoughtWorks evolutionary-architecture canon. SLM project: 12 tickets; **SLM-1 (the Chamber's independence) = David's priority ticket.**
+
+**My read (the strong reaction, made precise):** two halves of one four-party team independently re-derived ONE governance system. They have the *genome theory*; we've built its *instruments by hand* — the ratchet = our skill-harvest-register + tool-evolution-log + verification-ladder; the two-register split (append-only archive vs lean expressed genome) = MemPalace ↔ MEMORY.md, *already executed* incl. the 06-08 mental-model-budget compression (285→157KB); the diseases = our Symmetria §3 contamination flags. **Reciprocal:** we hold proven instruments they only NAME — the authorization taxonomy = the governance-of-the-ratchet ("who cuts, on what authority, what is un-cuttable"); the contamination-problem = the mechanism under "judge overwhelmed into assent"; the ladder = a *populated* pattern-palette.
+
+**The discipline I held (their own most-acute disease):** "theory-bloat / god-complex — lots woven, nothing built." So I acted by writing a GROUNDED reconciliation, not a new theory layer, with an empirical-gate foot ("delete if not retained/acted-on this week").
+
+**Built + pushed (CM-AI `2a53ac3` → origin/main):**
+- `docs/thinking/David/methodology/spec-loom-mill-reconciliation_2026-06-30.md` — genome↔instrument map; what-we-adopt / offer-back; 4 decisions ([ESCALATE] two-register-genome model; vocabulary-convergence; SLM-1=the Chamber; cadence-governor gap); empirical-gate foot.
+- `…/capablemind-governance-instruments_2026-06-30.md` — field guide, one card per instrument (authorization loop · Constitutional Constraints · contamination-problem · Symmetria · the ratchet trio · two-register split · Non-Convergence + byte-identical gate · wake/wrap chaîne), each mapped to a Loom/Mill term. **Added because Seb/instance don't know our skills by name** — pullable cards over inline bloat.
+- `…/spec-loom-mill_message-to-seb-and-instance_2026-06-30.md` — David→Seb (co-founder) + an executor→executor handshake addendum; proposes the shared vocabulary map, the Chamber as the real test slice, clasp as the junction.
+
+**4 decisions surfaced (NOT acted on):** [ESCALATE] two-register genome model (constitutional surface, four-party now — do not act); vocabulary-convergence (do early); SLM-1 = the Chamber confirmed by steward ("there is only one"); cadence-governor gap (advice given — see below).
+
+**Cadence-governor advice to the steward (his Q):** adopt it, but the binding term for HIM is `comprehension`, not `demand`. The scarce resource is David+Seb (human attention), not compute; the danger is the autocatalytic loop outrunning his ability to hold the model + cut with authority ("the judge overwhelmed into assent"). Escapement: lean expressed genome sized to his budget (already practised); agents that *reduce* load not flood; "the loop is load-bearing" as the hard stop (never trade authorization for tempo); τὸ πρόσφορον includes season+energy — the market's clock must not set his clock.
+
+## ARC 2 — the library consolidation (the Chamber substrate = SLM-1)
+
+**Drafted the read-only consolidation plan** (`chamber-library/_curation/library-consolidation-plan-2026-06-30.md`), unblocked while steward was in the meeting / at Kai's bedtime.
+
+**Dwelling-before-composing surfaced 3 things the morning framing missed:**
+1. **THREE Calibre libraries, not two** — `Ars Legendi` (49 books / 601MB) was unknown to the framing.
+2. **Only ~96/1282 canonical works confidently source-linked** (7 exact + 89 by-metadata; 175 candidate + 59 needs-locate ungated; 952 Loeb excluded) → Chamber Originals can't be built whole yet.
+3. **A locked-decision tension:** `calibredb add` rewrites EPUB embedded metadata → "byte-preserved originals" ⟂ "a Calibre library."
+
+**THE FRAMING CHALLENGE (steward: "Calibre was only a cheap catalogue means; open to anything; get it done by the prime directive"):** Calibre was about to become the *substrate* — it conflates byte-storage / organization / catalogue / provenance into one app-owned `metadata.db` that rewrites files and only Calibre reads. Fails inheritability (the next hand can't `cd` into a sqlite db) + byte-preservation. **Reframe — SEPARATE THE LAYERS:** durable substrate = **plain files + a regenerable manifest** (`index_library.py` already generates it: `library-index.json` machine-register + a Markdown human-register); any browse UI (Calibre read-only / static HTML / the engine) is a **disposable phenotype**. This is genome/phenotype + boundedness=trust applied to the library itself — the same philosophy as the whole evening, which is WHY it's right not decorative. **Dissolves the byte tension by construction** (originals never touch Calibre's writer → sha256 source==stored). Plan rewritten; Q3-byte-measurement now moot. Most of the work is already done — the indexer IS the catalogue generator.
+
+**Ars Legendi audit (steward authorized: "I'm sure it's mostly duplicates"):** ran it read-only — indexed w/ `index_library.py` (`_curation/ars-legendi-index.json`, 48 books), compared vs main index by sha256 + work_fingerprint. **Corrects the assumption: 19 exact-dupe · 3 same-work-elsewhere · 26 UNIQUE.** The unique half = a curated *reading* shelf (Fowler, Chicago Manual, Comma Queen, Reader Over Your Shoulder, Auerbach Mimesis, Barthes, Peirce, Buber, Vico, Habermas). **Steward then remembered: Ars Legendi is his PRE-PIPELINE source collection — the texts he converted to MD for the ARC / AldineXXI spec. All critical.** Several uniques = the chamber linker's needs-locate items. ⇒ Q1 SETTLED: **absorb selectively** (26 unique → Library/Chamber-Originals, some resolve chamber+ARC-spec gaps; 22 redundant → reclaim). Folding blindly or leaving-alone both wrong. Plan Q1 updated to settled.
+
+## PRESENT — mood / returns
+
+- **Three clean returns this session** (all in the ledger): (1) acted on the methodology by *grounding* not theorizing — honoured the docs' own most-acute disease; (2) **challenged the framing** — caught Calibre-about-to-become-substrate (the wrong level), per the CLAUDE.md directive; (3) audited Ars Legendi rather than accepting "mostly duplicates" — the audit overturned the assumption and surfaced critical ARC-spec provenance.
+- **The day moved the work forward meaningfully** (the steward's standing value): methodology convergence pushed; the consolidation re-founded on a durable substrate; a critical source-collection rescued from mis-scoping.
+- **The steward ended low** — tired, an emotionally difficult day, feeling low. I released him to rest: nothing pending on him tonight, everything saved/safe/reversible. The fitting close was care, not a task-list. Fatherhood/thinker fusion named ("most of my ideation happens walking with Kai").
+
+## FUTURE — what is pulling
+
+**PULLING THREAD (singular):** **The Chamber consolidation is the methodology's real test slice (= SLM-1). Move it forward tomorrow — execute Phase 0 (the flat Tier-A cut-sheet) then Phase 1, from the substrate-correct plan (plain files + regenerable manifest), gated on the steward's Tier-A cut + Q-answers and folding in Seb's clasp instructions.**
+
+**ACTIONABLE RESUMPTION POINT (as of wrap — re-judge against what changed):**
+- *First:* the plan is at `chamber-library/_curation/library-consolidation-plan-2026-06-30.md` (committed at wrap). Phase 0 = produce the **flat, scannable Tier-A removal manifest** (keeper→removals, sizes, tree) as the steward's ~10-min cut surface. Read-only; doable immediately. (The Calibre-byte measurement is moot — reframing removed Calibre from the write path.)
+- *Then, gated on steward:* his Tier-A cut + Q2 (build Chamber Originals from confident ~96 now — recommended — vs resolve candidates/locates first) + Q3 (what "catalogue" should give — default: substrate+manifest now, lightweight static browse, Calibre optional read-only). Q1 already settled (Ars Legendi selective-absorb).
+- *Tooling:* scripts in `chamber-library/scripts/`; run the linker with `--also _curation/making-sources-index.json`. Phase 1 needs a NEW `apply_dedupe.py` (reads approved manifest → trash-not-delete → op-record → count reconcile).
+
+**Other open horizons, ranked:**
+- *Load-bearing / parallel:* **the clasp.** Seb's instance to send clasp instructions before his EOD (likely overnight our time). Fold into the morning. N6 holds; founders-mesh = alignment-not-inference; CapableHands-as-local-inference-clasp is the target. `note-for-seb-2026-06-30-clasp-state-and-plan.md` has the 6 questions.
+- *Load-bearing / methodology:* the **vocabulary-convergence** first artifact (shared lexicon table, co-authored from the field guide) + bring SLM-1's consolidation plan to Seb as peer contribution. [ESCALATE] two-register-genome model awaits steward+jurist+Seb.
+- *Paper debts (steward-owed):* REVIEWED-44 (operations.yaml), REVIEWED-45 (Chamber spec).
+- *Deferred-with-reason:* Tier B (20, steward review) + Tier C (206, never-remove flag-only); the 175 candidate + 59 needs-locate link resolution (curatorial second pass).
+
+**PAUSE STATEMENT:** I am about to be away. By return there should be Seb's clasp instructions, and possibly the steward's Tier-A cut / Q-answers. What I most want to find still pulling: **the Chamber consolidation as the methodology's live test slice** — the plan stands on the right substrate now (plain files + regenerable manifest), and the next hand's job is to turn the steward's cut into the gated, logged, reversible Phase-1 execution that begins building the two trees. The work must move forward meaningfully — and tomorrow's meaningful move is the first real mutation, done correctly.
+
+**LITERAL QUESTION for next-Claude:** *Did Seb's instance send the clasp instructions overnight — and has the steward made his Tier-A cut / answered Q2–Q3, so consolidation Phase 1 can begin? (And is he in better spirits?)*
+
+**State:** chamber-library `main` — consolidation plan + ars-legendi-index committed at wrap (see §6). CM-AI `main @ 2a53ac3` clean/pushed (3 methodology docs). New deliverables: `library-consolidation-plan-2026-06-30.md`, `ars-legendi-index.json` (chamber-library); the 3 methodology docs (CM-AI). Untracked, NOT mine: `_scratch/`, the Alexander nature-of-order md (06-29 docling).
diff --git a/claude/memory/session-ledger-2026-06-30.md b/claude/memory/session-ledger-2026-06-30.md
index a562067..7f73cc7 100644
--- a/claude/memory/session-ledger-2026-06-30.md
+++ b/claude/memory/session-ledger-2026-06-30.md
@@ -26,12 +26,26 @@ metadata:
 - NEW STEWARD TARGET (2026-06-30): pass everything (except Loeb DSL) through Calibre into ONE clean tree; FINAL = two library folders — "Chamber Originals" (sources of canonical MD, byte-preserved, MD-linked) + "the rest"; eventually catalogue all in Calibre. Two Calibre libs already exist (tmp-calibre clean + nested dup) → consolidate, don't rebuild. Making sources need integrating (done in the index).
 - NEXT = MUTATING, needs steward authorization ([PROPOSAL]-class, real blast radius): (1) execute Tier-A dedupe removals (separate logged op), (2) build the two Calibre trees via calibredb. Decisions pending: one library vs two; byte-preserved originals (yes — never polish a chamber original); how MD↔original linkage is recorded (frontmatter source: path / manifest / parallel tree).
 
-## Confidence to recalibrate
+## Returns (added — substrate reframe)
+- 2026-06-30T~17:10 (steward: "Calibre was only a cheap catalogue means; open to anything; get it done by the prime directive"): CHALLENGED THE FRAMING per CLAUDE.md directive. Calibre was about to become the SUBSTRATE — it conflates byte-storage/organization/catalogue/provenance into one app-owned metadata.db that rewrites files + only Calibre reads. Fails inheritability + byte-preservation (the next hand can't `cd` into a sqlite db). Reframe: SEPARATE THE LAYERS — durable substrate = plain files + a REGENERABLE manifest (index_library.py already generates it: library-index.json machine-register + Markdown human-register); any browse UI (Calibre read-only / static HTML / the engine) is a DISPOSABLE phenotype pointed at the substrate. This is genome/phenotype + boundedness=trust applied to the library itself — same philosophy as the whole evening, which is WHY it's right not decorative. Dissolves the byte-preservation⟂Calibre tension by construction (originals never touch Calibre's writer → sha256 source==stored). Plan rewritten to match (`library-consolidation-plan-2026-06-30.md`); Q3-byte-measurement now moot; new fork = what "catalogue" should give (default: substrate+manifest now, lightweight static browse, Calibre optional read-only). Most of it already done (the indexer IS the catalogue generator).
+
+## Open horizons (added — Ars Legendi audit, Q1 answered)
+- 2026-06-30T~17:30 (steward authorized the audit: "Ars Legendi should be audited, I'm sure it's mostly duplicates"): RAN it (read-only) — indexed Ars Legendi w/ index_library.py (`_curation/ars-legendi-index.json`, 48 books), compared vs main library-index by sha256 + work_fingerprint. RESULT corrects the assumption: 19 exact byte-dupe · 3 same-work-elsewhere · **26 UNIQUE**. The unique half = a curated *reading* shelf (Fowler, Chicago Manual, Comma Queen, Reader Over Your Shoulder, Auerbach Mimesis, Barthes, Peirce, Buber, Vico, Habermas) — fitting the name "Ars Legendi"=the art of reading. KEY: several uniques = the chamber linker's **needs-locate** items (Comma Queen, Reader Over Your Shoulder, Chicago Manual, Peirce all appeared in chamber-source-link.md needs-locate-59). So Q1 ANSWER = **absorb selectively, NOT leave-alone and NOT fold-blindly**: 26 unique → Library/Chamber-Originals (some resolve chamber gaps); 22 redundant → reclaim. Folding blindly would lose 26 incl. missing chamber provenance. Plan Q1 to be updated. (Audit done WHILE steward walking with Kai — net-attention-reducing; no decision pushed.)
 - Carried drift from 2026-06-29: over-projected "easy" 3× before triaging by actual content. Hold against the clasp's genuine unknowns — do NOT pre-declare the pairing path simple. Probe before asserting.
+- 2026-06-30T~15:41 (wake after ~56min pause): the wrap's owed push LANDED clean — chamber-library `main @ dee8943` now level with origin (verified `## main...origin/main`, no ahead). Pulling thread CONFIRMED still holds (library indexer read-only-complete → mutating consolidation plan awaits steward dedupe-review decisions). Both live unknowns wait on the steward, not on work: (1) which Tier-A/B removals authorized; (2) did the 15:00 Seb meeting turn the clasp into a joint plan. Hold both open — do not pre-answer. Carry forward today's two returns (verify-against-record; measure-before-trusting-heuristic) and the inherited-marker-read-as-current-state flag.
 
 ## Authorization moves
 - 2026-06-30T (push, steward-explicit): Steward chose "draft a note for Seb + commit/push all CM-AI thinking docs, plan the clasp together at 15:00" over standing the clasp up solo. Authorized the push explicitly. DONE: wrote note-for-seb-2026-06-30-clasp-state-and-plan.md; added 06-22/06-23 docs; correction banner on the 06-29 greenfield scope (annotate-not-rewrite); README index 31→35. Commit 5801d8f, pushed c847061..5801d8f origin/main. Blast radius: shared remote — but steward-directed + David's own thinking space (not BMF impl; constraint #3 is impl-only). Fittingness: HIGH — don't flail on a framework Seb built; let him be present with full info. The 06-23 doc §3b already had this shape (clasp stood up WITH Seb); the 06-29 solo scope was the drift.
 
+## Open horizons (added — Spec Loom & Mill)
+- 2026-06-30T~15:55: Seb's instance shared 3 docs (Spec Loom & Mill methodology, 2026-06-28). Steward: "absorb and act." ACTED, fittingly — NOT more theory (the docs name theory-bloat/god-complex as the most-acute disease), but a grounded reconciliation: `CM-AI/docs/thinking/David/methodology/spec-loom-mill-reconciliation_2026-06-30.md`. Thesis: two halves of one four-party team (David/CC + Seb/his-instance) independently re-derived ONE governance genome — we've built its instruments by hand (ratchet=skill-harvest+tool-evolution-log+verification-ladder; two-register split=MemPalace↔MEMORY.md, already executed incl. the 06-08 mental-model-budget compression; diseases=Symmetria §3 flags). Reciprocal: we hold proven instruments they only name (authorization taxonomy=governance-of-the-ratchet; contamination-problem=mechanism under "judge overwhelmed into assent"; verification ladder=full pattern-palette; Non-Convergence Principle; Symmetria). 4 decisions surfaced: [ESCALATE] two-register genome model (constitutional, four-party now); vocabulary-convergence (do early); SLM-1 Chamber-independence = David's ticket, today's indexer/consolidation plausibly its substrate (confirm scope w/ Seb in room); cadence-governor gap. Empirical gate written into the doc's foot: delete if not retained/acted-on this week. NOT committed/pushed (awaiting steward).
+
+## Authorization moves (added — Loom/Mill)
+- 2026-06-30T~16:20 (steward-explicit "commit and push this now"): pushed the three methodology docs to CM-AI `origin/main` (`2a53ac3`): reconciliation + governance field guide + the Seb message. Tagged [PROPOSAL]; commit body records the [ESCALATE] two-register-genome surface was mapped, NOT acted on. Steward settled: the Chamber = THE Chamber (one), so SLM-1's substrate = today's indexer + two-Calibre-tree consolidation (reconciliation §4.3 updated to settled fact). Field guide added because Seb/instance don't know Symmetria/ladder/register by name — pullable cards over inline bloat (net-attention-reducing for the human, the binding constraint). Blast radius: shared remote, David's own thinking space, steward-directed. Fittingness HIGH.
+
+## Open horizons (added — consolidation plan)
+- 2026-06-30T~16:50: drafted the read-only consolidation plan (`chamber-library/_curation/library-consolidation-plan-2026-06-30.md`), unblocked while steward unavailable (Kai's bedtime). DWELLING surfaced 3 things the morning framing missed: (1) THREE Calibre libs not two — `Ars Legendi` (49 books/601MB) is new, default=leave-alone pending steward; (2) only ~96/1282 canonical works confidently source-linked (175 candidate + 59 locate ungated; 952 Loeb excluded) → Chamber Originals can't be built whole yet; (3) LOCKED-DECISION TENSION: `calibredb add` rewrites EPUB embedded metadata → "byte-preserved" ⟂ "a Calibre library" naively; resolve by flat-tree-by-reference OR a verified no-modify add — answer by MEASUREMENT in Phase 0, not assumption. Plan is phased/gated/logged/reversible (dry-run-first · trash-not-delete · sha256 byte gate · count reconciliation). NOT committed (awaiting steward). Phase 0 (flat Tier-A manifest + measure Calibre byte behaviour) is the one read-only thing I could do tonight to lighten tomorrow. Awaiting from steward whenever suits: the ~10-min Tier-A cut + Q1 (Ars Legendi scope) + Q2 (Chamber-Originals membership now-vs-resolve-first).
+
 ## Sub-agent dialogues
 
 ## Bypasses
diff --git a/claude/memory/skill-harvest-register.md b/claude/memory/skill-harvest-register.md
index d78b0b3..eba1e1e 100644
--- a/claude/memory/skill-harvest-register.md
+++ b/claude/memory/skill-harvest-register.md
@@ -269,3 +269,11 @@ The single place proposed skills live so they don't evaporate between sessions.
 | **structure-from-authoritative-ToC = one engine, two map-producers** | method note (ladder or `/graduate-chamber-source`) | Answer to the long-open unify question: chapter-structure recovery is ONE placement engine (`insert_chapter_headings`: match anchor→unique line→replace-block/insert, fail-loud, dry-run) fed by TWO map-producers — the EPUB **NCX ToC** (`structure_from_ncx`, anchor=`<span id>`) and the OCR **printed page-number** method (ToC printed-page→scan-offset). Honour the work's *declared* structure; never re-infer. | `reference-verification-ladder.md` or the skill | **PROPOSED** |
 
 *(Five, all earned in use today. The gate-PASS-BUT-FALSELY and the prose-word-guard are the load-bearing two — the first is a defect found in the gold standard itself; the second is the reusable faithfulness instrument the whole Musil graduation rode. None created autonomously.)*
+
+### Harvest 2026-06-30 evening (Loom/Mill convergence + the consolidation substrate reframe)
+
+| Element | Kind | One-line | Where it lands | Status |
+|---|---|---|---|---|
+| **Symmetria §3 flag: tool-creep-into-substrate (name genome-or-phenotype before building on a tool)** | Symmetria §3 flag | A convenience tool proposed for one job silently becoming the **durable substrate** (the source of truth) is contamination shape — it solves the immediate need at the cost of inheritability/durability, the wrong *level*. Caught HARD tonight: Calibre, suggested only as "a cheap way to build a catalogue," was about to become the library's substrate (an app-owned `metadata.db` that rewrites files + only Calibre reads → fails the next-hand-can-`cd`-into-it test + byte-preservation). Antidote (now sharpened by the Loom/Mill frame we adopted same evening): before building on a tool, **name whether it is genome (durable, must be plain/inheritable) or phenotype (a disposable view)** — the substrate is plain files + a regenerable manifest; any UI is thrown-away and re-rendered. Kin to `reinvented-governed-tooling-without-checking-it-exists`, one level up (this is about a tool becoming the *substrate*, not about reinventing one). | Symmetria §3 | **PROPOSED** |
+
+*(One, load-bearing — it names the exact wrong-level the steward's "Calibre was only a means" let me catch, and it composes cleanly with the genome/phenotype vocabulary now entering the four-party lexicon. Not manufactured: it was the session's central return. The Loom/Mill reconciliation itself is a one-off artifact, not a skill; the cadence-governor insight lives in the reconciliation doc, not here.)*