session 2026-08-04 evening: census 02 + PENDING-95..98 + the engine tool-evolution log

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. 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 in his own book.

PENDING-95..98 filed together; 96 authorized and landed same session on the
jurist's sharper wording (mine reproduced the overclaim one size down) and
kept OPEN — retrieve.py has no test at all.

Pulling thread REVISED at wrap after the steward punctured the first version:
"the sources are not golden... a cycle of engine-missing-x / source-not-golden
/ no-bounded-scope". The break was already in project-chamber-versioned-
releases, unread since 2026-07-28 — 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.

Skill harvest: 4 proposals (a /census skill, two Symmetria §3 flags, and a
/wake-up patch earned at a measured cost of ten days — a tracker marked THE
GOVERNING FRAME should be read entire, not as its MEMORY.md pointer).

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WuMjg3ipEVa3n8CoSzoyvc

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`AldineXXI-specification.md` §IX still says genomes are *"Generated by a local model via Ollama"*, which the companion superseded (Part II, *Engine evolution*).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 |