session 2026-08-07: N1+R0+N2 built, @3 corrected under PENDING-111, D-5 recorded, two governance checkers, V2 unblocked

claude/skills/wake-up/SKILL.md

@@ -84,7 +84,7 @@ The durable memory *is* the Markdown + JSONL files (git-tracked, dual-remote). T
 - Read `~/PENDING.md` — extract items with status PENDING
 - Read `~/REVIEWED.md` — extract recent AUTHORIZED/DEFERRED/REJECTED decisions
 - Run `git -C ~/dotfiles status -sb` — if dirty or ahead of its remote, the previous wrap's push (wrap-up §6.5) failed or something wrote outside a session. Surface it in the briefing. **Do not commit or push at wake** — the wake reads, it doesn't mutate; the push belongs to the wrap.
-- **Governance drift check** — run `python3 ~/dotfiles/scripts/governance-drift-check.py` (~0.2 s). It reports state claims in `~/CLAUDE.md` that the substrate contradicts: unresolvable paths, named tools with no configured server, hooks claimed to fire that are unconfigured, expired date horizons, and structural damage. **Report the count in the briefing; list the findings only if the count changed since the last wake.** Do not correct — correction of doctrine or steward-held state requires `[ESCALATE]` (Constitutional Constraint #1); this step is detection only, which needs no authorization. If the script prints `INSTRUMENT NOT VERIFIED`, its positive controls failed — treat the result as unestablished rather than clean. <!-- 2026-07-27: built on steward authorization. The governance document had carried 9 substrate-contradicted claims for up to 4 months because detection and correction were priced identically; separating them makes staleness *visible* rather than *misleading* — Constitutional Constraint #4 applied to the governance document itself. Every check carries a same-run positive control per the epistemic standard ratified in the jurist's Q2 ruling: an absence is not evidence until the instrument is shown capable of detecting presence. -->
+- **Governance drift check** — run `python3 ~/dotfiles/scripts/governance-drift-check.py` (~0.2 s). It reports three things. (a) **State claims in `~/CLAUDE.md` the substrate contradicts**: unresolvable paths, named tools with no configured server, hooks claimed to fire that are unconfigured, expired date horizons, structural damage. (b) **Register integrity** — an amendment in `~/REVIEWED.md` that replaced the record it amends rather than joining it (earned 2026-08-07, when REVIEWED-87's original entry was overwritten by its own amendment and nothing detected it). (c) **Deferred decisions whose trigger has COME DUE** — a deferral is the claim *not yet*, and a fired trigger is the substrate saying otherwise. ⏰ **A COME DUE item must be surfaced in the briefing, named, under "What's unresolved"** — it is a decision the steward now owes, not a defect. Earned 2026-08-07: the 2026-05-16 TEI-native deferral's condition was met and sat unobserved for months because nothing checked it. **Report the count in the briefing; list the findings only if the count changed since the last wake.** Do not correct — correction of doctrine or steward-held state requires `[ESCALATE]` (Constitutional Constraint #1); this step is detection only, which needs no authorization. If the script prints `INSTRUMENT NOT VERIFIED`, its positive controls failed — treat the result as unestablished rather than clean. <!-- 2026-07-27: built on steward authorization. The governance document had carried 9 substrate-contradicted claims for up to 4 months because detection and correction were priced identically; separating them makes staleness *visible* rather than *misleading* — Constitutional Constraint #4 applied to the governance document itself. Every check carries a same-run positive control per the epistemic standard ratified in the jurist's Q2 ruling: an absence is not evidence until the instrument is shown capable of detecting presence. -->
 
 
 **d. Git state**