session 2026-08-07 evening: PENDING-112 + REVIEWED-95 (route harvested capabilities by firing moment)

Register censused and rebuilt from the archive: 177 claimed -> 154 real live
proposals, legible, with exact archive:L### pointers. The 2026-08-01 compaction
was lossless but illegible (55 scraped header rows; 95% of cells cut mid-word);
completeness verified 124 = 124, so nothing had been dropped.

Skills pruned 63 -> 12 after measuring that 53 had never been invoked across 64
sessions / ~5 months. The finding underneath: retrieval is set by a capability's
HOME, not its importance -- MEMORY.md 83%, register 77% (named in a wake step),
ladder 14%, 'THE GOVERNING FRAME' 12%, 'Read at Step 0' 9%, recall-bound skills 0%.

PENDING-112 filed, jurist design-gated, steward concurred; REVIEWED-95 drafted.
Landed: the /wrap-up 1.6 filing gate (prospective) and the /wake-up ladder
sentence (a pre-registered trial intervention, landed alone). The 20-session
falsifier is WIRED, not intended -- DEFERRED-DECISION ladder-ritual-trial,
trigger: transcripts 84. Wiring it exposed two defects in the deferral checker:
no way to express a session count except as a date proxy, and a scan that never
looked at claude/governance/. Controls 16 -> 19.

Stroke 2's 41-entry ladder append deliberately NOT done: REVIEWED-95 Q3
sequences it after the ladder trigger, which now exists.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01NEWjLBP4quXbDPDL2byEzZ

claude/skills/wake-up/SKILL.md

@@ -61,6 +61,7 @@ Run these in parallel to minimize latency:
 - **Load-integrity gate (self-bounding backstop):** if the harness reports MEMORY.md was truncated / only-partially-loaded (a "MEMORY.md is N KB, only part was loaded" warning), that is a **budget breach** — the wake is not seeing the whole index. Flag it loudly in the briefing and trim the index (relocate the least-wake-critical section to `MEMORY-reference.md`, back up first) before proceeding. A silently-truncated index reads as "complete" when it isn't — the exact failure the split exists to prevent.
 - Read the Active Session memory file referenced there — **specifically extract the pulling thread + literal question + open horizons + any skill-harvest proposals left unauthorized**
 - Read `skill-harvest-register.md` directly — the canonical surface for open skill proposals (wrap §1.6 appends there); surface any awaiting steward authorization <!-- 2026-06-05: register wiring, authorized 2026-05-29, applied with wrap-up §1.6 counterpart -->
+- Read `reference-verification-ladder.md` directly — the canonical surface for the named verification instruments; hold the one or two the session's work will actually need <!-- 2026-08-07: PENDING-112 → REVIEWED-95. THIS SENTENCE IS A PRE-REGISTERED TRIAL INTERVENTION, landed alone and deliberately parallel to the register line above. Baseline before it: the ladder was reached in 9 of 64 sessions (14%), while the register — identical in kind, differing only in being named here — sat at 77%. Prediction: >60% over the 20 sessions following. Graded automatically at 84 transcripts via the `ladder-ritual-trial` DEFERRED-DECISION trigger; the result is filed as a dated PENDING entry whichever way it falls. Do not add to, reword, or "improve" this line before the trial is graded — a second change confounds the only check standing behind PENDING-112's causal claim. -->
 - Read `~/.claude/projects/-Users-davidglidden/memory/session-ledger-[previous-date].md` if it exists — **specifically read the "Returns" and "Confidence to recalibrate" sections** for mood signal
 - **Link-resolution canary (seconds-cheap):** verify MEMORY.md's file pointers resolve — every `](file.md)` target exists in the memory dir. Flag dead pointers in the briefing, distinguishing pre-existing-broken from newly-broken (grep the previous git state if in doubt). A pointer to a missing file is the index lying about what memory holds. <!-- 2026-07-19 harvest review (steward-authorized): the wake-canary link-resolution half, proposed 2026-06-07, partially built 2026-07-06 (truncation half), now standing. -->
 - **Telos conditional:** if the pulling thread touches the studium engine / The Making / ARC-as-public-proof (the engine's reason-for-being), also read `project-studium-engine-telos-chamber-of-voices.md` and hold ONE line of the why in the briefing — the telos lane drawn first, never only the production lanes. Do NOT recite it on unrelated wakes (decorative). <!-- 2026-07-19 harvest review (steward-authorized): proposed 2026-06-18 after the steward had to re-disclose the chamber's origin; second evidence instance 2026-07-19 (map-drawn-from-production-lanes-not-telos, steward corrected twice). -->

claude/skills/wrap-up/SKILL.md

@@ -79,6 +79,17 @@ Drawing on the session and the merged ledger (1.5), ask:
 
 The yardstick is the steward's own: *did the steward have to re-explain something a skill could have carried next time?* If yes, that is a harvest candidate.
 
+**Declare the firing moment before filing — route by it, never by importance.** A harvested capability is only worth what a protocol exercises: *storage is not memory* (`~/CLAUDE.md` §Memory Discipline). Measured 2026-08-07 across 64 sessions, retrieval is set by **home**, not by merit — `MEMORY.md` 83%, the register 77% (it is named in a `/wake-up` step), the verification ladder 14%, files labelled *THE GOVERNING FRAME* and *Read at Step 0* 12% and 9%, and **53 skills requiring executor recall: 0%**. Emphasis buys nothing; being named in a ritual buys everything. So, per proposal:
+
+| the capability fires… | route to |
+|---|---|
+| mechanically, and should always fire | a hook or a wake/wrap script |
+| at a ritual juncture that already exists | a named step in `/wake-up` or `/wrap-up` |
+| at a recurring workflow someone announces out loud | a skill |
+| on a condition the executor must first *notice* | **neither a skill nor a bare ladder entry** — find the mechanical detector and route up; or attach it to the nearest existing ritual step; or accept ~10% retrieval **and record that estimate on the proposal** |
+
+**Where no firing moment can be named, the proposal is documentation and must say so on its face.** This is a labelling requirement, not a filing barrier — nothing is blocked, but nothing may be filed as though it will fire when it will not. It applies **prospectively**: the 154 items already in the register are not swept, though they may be re-routed opportunistically as they are touched. <!-- 2026-08-07: PENDING-112 → jurist design gate → REVIEWED-95. Q2 authorized the gate as enforceable, expressly bound to a pre-registered 20-session falsifier rather than to jurist–executor agreement (the executor flagged, on the differently-biased-checkers doctrine, that concurrence between two same-formation parties is a weak check on a self-serving claim). The falsifier is wired as a DEFERRED-DECISION trigger (`transcripts 84`) in claude/governance/harvest-routing-JURIST-PACKAGE-2026-08-07.md, not left as an intention — the proposal's own thesis being that intentions do not fire. A result below 60% reopens Q2's rationale, not the gate by default: the gate may still stand on Constraint 4 alone. -->
+
 **Default: surface each as a proposal in §8.** The steward converts proposal to action; only then is a skill changed, and the changed skill carries a one-line provenance note in its source (e.g. `<!-- 2026-05-27: … -->`) so the chain of improvements stays legible.
 
 **The FIX lane — the one narrow exception.** Ask the classification test: