diff --git a/claude/memory/MEMORY.md b/claude/memory/MEMORY.md index f8f7407..ce14c92 100644 --- a/claude/memory/MEMORY.md +++ b/claude/memory/MEMORY.md @@ -6,7 +6,7 @@ metadata: type: note permalink: claude-memory/memory originSessionId: 22915403-bc5d-4796-9c7d-196b7c30d2f9 - modified: 2026-07-20T19:12:08.293Z + modified: 2026-07-20T19:19:54.153Z permalink: claude-memory/memory --- @@ -28,7 +28,7 @@ permalink: claude-memory/memory - [Studium Engine = Sixtus-V craftsman collaboration](feedback-studium-engine-sixtus-v-collaboration.md) — work the ground freely (I build, surface only vision-forks); **constraint-candidates** = 3rd governed instrument (I name, steward applies). Studium-engine only; heavier loop for L1/L2. - [Trust prior pass frame](feedback-trust-prior-pass-frame.md) — When extending a prior verification, re-run it at the scope of the extension. Frame-inheritance from a deep-read is contamination shape: the prior pass tested what it tested; your extension claims things it did not test. Caught 2026-05-28 → four-pass audit. Verify-before-compose at draft time, not build time. - [MemPalace is an unaffiliated stopgap](mempalace-is-unaffiliated-stopgap.md) — MemPalace is third-party; steward/Seb build BMF/CapableMind (hoped to replace it). Don't conflate them (3rd steward correction 2026-06-05 — the conflation even reached a skill name and was retracted); MemPalace PRs await MemPalace's maintainers, NOT Seb. -- [Skill-harvest register](skill-harvest-register.md) — **canonical home for proposed skills** (governed analog of PENDING.md for tooling). **FULL REVIEW RULED 2026-07-19, all four strokes** (⚖ block at top is authoritative): §3 consolidation BUILT · ladder batch-append + register compaction = next housekeeping slot. **`/jurist-package` BUILT 2026-07-20 (proven 2×);** `/model-handoff` = next build · `/graduate-chamber-source` hold-condition now MET (one-door lane RULED, v2.3.0 operative). **New PROPOSED patch (2026-07-20): `/jurist-package` — trace a ruled finding's inference direction when transcribing it, not just its words (2× jurist-caught).** +- [Skill-harvest register](skill-harvest-register.md) — **canonical home for proposed skills** (governed analog of PENDING.md for tooling). **FULL REVIEW RULED 2026-07-19, all four strokes** (⚖ block at top is authoritative): §3 consolidation BUILT · ladder batch-append + register compaction = next housekeeping slot. **`/jurist-package` BUILT 2026-07-20 (proven 2×);** `/model-handoff` = next build · `/graduate-chamber-source` hold-condition now MET (one-door lane RULED, v2.3.0 operative). **Patch BUILT 2026-07-20 (steward-authorized): `/jurist-package` — "trace a ruled finding's inference, not just its words" (Load-bearing disciplines; 2× jurist-caught).** - [Copy-paste-clean governance drafts](feedback-governance-drafting-copy-paste-clean.md) — draft PENDING/REVIEWED placement blocks as plain fenced markdown; display formatting leaks into the placed record (REVIEWED-59 header, 07-16). - [Verification ladder](reference-verification-ladder.md) — the named instruments (byte-identical compile gate, delta classification, censused-routes, fresh-clone gate, measure-toolchain-before-spec…); reach for the gate the claim's shape demands instead of re-deriving. - [Plane coordination workflow](reference-plane-coordination-workflow.md) — CENTRAL to steward↔Seb (est. 2026-06-02): `app.plane.so/capablemind`, thin effort-tasks `[BM #N]` over canonical GH issues. ⚠ BBF = BetterBridge *product*, NOT the board. Plane MCP OAuth (`ToolSearch select:mcp__plane__*`); `create_work_item` needs `description_html`. Detail in file. diff --git a/claude/memory/skill-harvest-register.md b/claude/memory/skill-harvest-register.md index 87b9902..0dbadc3 100644 --- a/claude/memory/skill-harvest-register.md +++ b/claude/memory/skill-harvest-register.md @@ -8,7 +8,7 @@ metadata: node_type: memory type: reference originSessionId: a8eb1d46-314e-4545-a133-f747c69ad5b4 - modified: 2026-07-20T19:11:51.018Z + modified: 2026-07-20T19:19:43.374Z permalink: claude-memory/skill-harvest-register --- @@ -36,11 +36,11 @@ The single place proposed skills live so they don't evaporate between sessions. **BUILT this session (was authorized "build next" at the 07-19 harvest review):** **`/jurist-package`** — `~/dotfiles/claude/skills/jurist-package/SKILL.md` (symlinked into `~/.claude/skills/`; the authored-skill convention). Grounded in the 2 proven exemplars, not recall. **Proven 2× same session** (the PENDING-67 package + the F2 correction relay, both hook-passed on first write, both ruled). Absorbs `/spec-amendment` (supersession → the ladder, as ruled). `/model-handoff` remains the next authorized build. -**New PATCH proposal (awaiting steward):** +**PATCH — BUILT 2026-07-20 (steward-authorized):** | Skill | Kind | One-line | Origin | Status | |---|---|---|---|---| -| `/jurist-package` | patch | Add to the **after-ruling / Part-A drafting** guidance: *when transcribing a RULED finding into constitutional/amendment prose, trace the finding's own **inference direction**, not just quote its words — a faithful transcription of the WORDS can invert the INFERENCE.* Earned HARD this session, **twice**, both jurist-caught: (a) the PENDING-67 Q1 lean ("no new constitutional text") faithfully read §V's prohibitions but missed §V's *silence* on the enforcement locus — the gap itself; (b) the v2.3.0 Part-A draft wrote "re-conversion is *not* vacuous," a different sentence producing the *identical* misreading the Q2 ruling was written to prevent, inside that very subsection. The skill already names consequence-trace-one-level-deeper for the PACKAGE's own claims; this extends it to the act of **transcribing someone else's ruled finding** — a distinct, recurring failure surface. Kin to Symmetria §3 `the-say-do-seam` / `consequence-trace-one-level-shallow`, at the constitution-drafting layer. | 2026-07-20 (2× jurist-caught) | **PROPOSED** | +| `/jurist-package` | patch | Added to the **Load-bearing disciplines**: *"Trace a ruled finding's inference, not just its words"* — when transcribing a RULED finding into a package claim / Addendum correction / constitutional prose, a faithful transcription of the WORDS can invert the INFERENCE; ask which way the inference runs and whether the sentence produces the reading the ruling was written to *prevent*. Earned HARD **twice**, both jurist-caught: (a) the PENDING-67 Q1 lean read §V's prohibitions but missed §V's *silence* on the enforcement locus — the gap itself; (b) the v2.3.0 Part-A draft wrote "re-conversion is *not* vacuous," the identical misreading the Q2 ruling was written to prevent, inside that very subsection. Extends the existing consequence-trace (which covers the PACKAGE's own claims) to the act of transcribing someone else's ruled finding. | 2026-07-20 (2× jurist-caught) | **BUILT 2026-07-20** (provenance comment in SKILL.md; steward-authorized) | *(One candidate, load-bearing: it recurred twice in one session and the jurist caught both. The skill carries the right discipline for its own claims but not for the transcription act; the patch closes exactly the gap I fell through — the yardstick met, the jurist had to correct the same shape twice.)* diff --git a/claude/skills/jurist-package/SKILL.md b/claude/skills/jurist-package/SKILL.md index 69bd2e3..f1e73fd 100644 --- a/claude/skills/jurist-package/SKILL.md +++ b/claude/skills/jurist-package/SKILL.md @@ -66,6 +66,7 @@ Both exemplars carry these roles in order. Part *numbers* vary with the proposal - **Path-verify the reading list before you cite it.** Every file path, every § reference, every companion doc named in the package — confirm it exists and says what you claim, in this session. The jurist can't check; you must. - **Surface, don't resolve, the sub-questions you're unsure of.** A numbered gate question with your lean beats a silent decision the jurist never sees. The one-door package's Q5 (minimal-sidecar) was surfaced-not-answered, and the jurist ruled it on a stronger ground than the executor had. - **Preserve the ruled-on text.** After the ruling, never silently rewrite the Parts the jurist read. Layer the disposition on top (the Addendum pattern) so the audit trail — what was proposed, what was ruled — stays intact. +- **Trace a ruled finding's inference, not just its words.** When you transcribe a jurist's ruled finding — into a package claim, an Addendum correction, or the constitutional/amendment prose that lands it — *a faithful transcription of the words can invert the inference*. Quoting the finding is not carrying it. For each ruled finding you restate, ask: **which way does the inference run in this sentence, and does it produce the reading the ruling was written to *prevent*?** Earned twice in one session, both jurist-caught: (a) a lean that faithfully read a section's *prohibitions* but missed its **silence** as the actual gap (§V forbids the acts, but is silent on who-must-demonstrate-compliance — that silence was the point); (b) a draft that wrote *"X is **not** vacuous"* — the identical misreading the ruling it was landing existed to stop, inside that very subsection. Kin to the consequence-trace above and to Symmetria's `the-say-do-seam`, at the transcription layer. ## After the ruling — the Addendum + the REVIEWED draft