session 2026-07-25→27: spec v2.7.0 (REVIEWED-75) + v2.8.0 (REVIEWED-73 voice-purity) landed; source_lines FIX ×2; 2 skill proposals

Session file + ledger returns + 7 KG appends (2 drift-patterns, 3 good-direction,
2 facts) + feedback-derive-the-rule-from-the-consumer-not-from-the-survivor.
MEMORY.md: prior Active Session demoted to MEMORY-reference.md, new promoted.
Skill-harvest register: /wake-up backlog substrate-check patch + /field-divergence-sweep
create, both PROPOSED for steward authorization.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Xefg5EXwcpd9RMAr63dWrD

claude/memory/skill-harvest-register.md

@@ -48,6 +48,15 @@ The single place proposed skills live so they don't evaporate between sessions.
 
 *(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.)*
 
+## Harvest 2026-07-27 (the two-supersessions session — 2 candidates, both evidence-backed)
+
+| Skill | Kind | One-line | Origin | Status |
+|---|---|---|---|---|
+| `/wake-up` | patch | **Substrate-check the briefing's backlog section.** §3's "What's unresolved" currently lets REVIEWED.md's *"If AUTHORIZED: build …"* clauses be read as *status*. They are **forward instructions, not status** — I told the steward at wake that REVIEWED-72/73/74 were all authorized-but-unbuilt; **2 of 3 were already built and landed** (v2.6.0), and the wave I reported as blocked was already unblocked. Proposed patch: before listing an authorized item as outstanding, verify against the substrate (code / spec header / repo CLAUDE.md), and say "verified against substrate" or "unverified" in the briefing. The wake briefing is a claim surface like any other, and it is the **highest-leverage place** for a false claim to land — it shapes the steward's picture of their own project before any work begins. | 2026-07-27 (steward-visible error, self-caught within the same turn) | **PROPOSED** |
+| `/field-divergence-sweep` | create | **Sweep for one field computed in more than one place, then derive the rule from the consumer.** Method proven this session at steward direction, and the yield was not zero on the first run: grep the fleet for multi-site computations of the same field → for each, ask *what must a consumer be able to DO with this value* and derive the rule from that (never pick the surviving implementation — that is selection, not derivation) → enumerate the shapes where each existing candidate happens to be right and test **all** of them (complementary-correctness defeats sampling) → collapse to ONE imported implementation → any migration RECOMPUTES, never does arithmetic on the stored value. Found `source_lines` wrong **twice** (including in a fix committed an hour earlier; lintott off by **308 lines**), and cleared `sha256` + the tokenizers with an empirical cross-check. Same probe as the no-op orphan sweep, aimed at **values** instead of stages. Steward: *"this instance says the yield won't be zero."* | 2026-07-27 (steward-directed; grounded in [[feedback-derive-the-rule-from-the-consumer-not-from-the-survivor]]) | **PROPOSED** |
+
+*(Both are load-bearing rather than tidy-up: the first is a correction to a briefing surface that misled the steward, the second is a method that found a live 308-line coordinate error on its first run. No other harvest — the session's other lessons are banked as feedback memories, not skills.)*
+
 ## Open proposals
 
 *Full review with steward 2026-06-05 (housekeeping session) — every item ruled, evidence-checked against the KG drift/built record. Verdicts below.*