feat(linkedin-studio): N11 — serie-destillat + skjelett-sjekk + specifics-bank bruks-logging [skip-docs]

Every long-form gate agent sees ONE edition, so «the reader has heard this
before» was structurally invisible — and the specifics-bank dedupe actively
encouraged re-surfacing the same material. At series cadence that is the
fastest-growing defect class. N11 makes it visible BEFORE the skeleton is
approved, at two grains:

- Series grain — new scripts/editions package: each locked edition's spent
  anecdotes/arguments/hooks are written to <serie>/linkedin/series-distillate.json
  at Step 8 lock (distil-append), and the next skeleton is checked against it at
  Step 2.5 (distil-check) with the finding folded into the annotation gate the
  operator already reads. Advisory, never blocking: a deliberate callback is a
  legitimate move, an unnoticed retread is not.
- Material grain — specifics-bank usedIn log: record-usage stamps «used in
  edition NN» on the specifics an edition actually consumed (read from the bound
  slot-map, so abstrakt/ekstern stamp nothing). At lock, so it means published;
  idempotent under a pivot re-lock. Additive-optional, schema stays v1.

Placement deviates from the plan text (${DATA}) after premise-verification:
per-series state belongs in the series root beside edition-state.json, where
Step 0 already resolves the path and no slug→path map is needed. Operator
approved. The distillate module also lands in scripts/editions now rather than
at N12, since the AC required a testable roundtrip and N12 planned that package
anyway — N12 extends it instead of creating it.

Similarity is character-trigram Jaccard, not word overlap: the plugin is
language-general and inflection (migrere/migreringen) breaks word tokens.
Calibrated on real paraphrase pairs — retellings 0.44-0.55, unrelated 0.04-0.06,
same-topic-different-story 0.24 — so the default threshold sits in the gap at
0.40. Word-Jaccard scored a shortened hook paraphrase at 0.11.

TDD (Iron Law): tests written first and verified red before implementation, for
both the new package and the bank logging.

Suites: editions 27/0 (new suite line + guard, floor 27) · specifics-bank
28 -> 45 · test-runner 163 -> 173 (Section 16r: 9 unconditional greps +
non-vacuity self-test; anti-erosion floor 146 -> 155) · trends 300/0 ·
brain 134/0 · hooks 140/0 · tests 35/0 · render 60/0. tsc --noEmit clean.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QxvWAjte7vPcF79QeSRvRJ

CHANGELOG.md

@@ -32,6 +32,14 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - **WebFetch on both fact agents (C-7)** — `fact-checker` and `fact-reviewer` gain `WebFetch`: quote precision (F2) and exact-figure attribution (F3) require the verbatim source text in context, not a search snippet.
 - test-runner 146 → 154 (Section 16p: 8 unconditional randsone-gate greps + self-test; anti-erosion floor 129 → 137). Domain-general; no KTG-specific values hardcoded.
 
+### Added — series-level protection: make the retread visible before prose (N11 / C-5)
+
+- **`scripts/editions/` — series distillate (new package)** — each locked edition leaves behind the narrative units it spent (anecdotes told, arguments argued, hooks used) in `<serie>/linkedin/series-distillate.json`, beside `edition-state.json` in the **series root** — series-scoped state where the series' other state already lives, so it travels with the series and needs no slug→path map. `distil-append` (Step 8 lock) folds an edition in; a re-lock after `/linkedin:pivot` **replaces** its entry rather than duplicating it.
+- **Step 2.5 destillat-sjekk — the check runs BEFORE prose** — the skeleton gate now compares the proposed skeleton against everything the series has published and folds any finding into the annotation page the operator already reads, while changing course is still cheap. **Advisory, never blocking** (exit 0 either way): a deliberate callback is a legitimate move — an *unnoticed* retread is not. Until now every one of the long-form gate agents saw exactly one edition, so "the reader has heard this before" was structurally invisible; at series cadence it is the fastest-growing defect class.
+- **Deterministic comparison, AI extraction** — the units are distilled from locked prose by the command layer, but the store, the similarity and the verdict are plain code: **character-trigram Jaccard**, chosen because the plugin is language-general and inflection (*migrere* / *migreringen*) breaks word-token overlap. Calibrated against real paraphrase pairs — retellings 0.44–0.55, unrelated 0.04–0.06, same-topic-different-story 0.24 — so the default threshold sits in the gap at **0.40** (word-Jaccard scored a shortened hook paraphrase at 0.11 and would have let it through). Units are compared within their kind; an argument re-used as a hook is a new move.
+- **Specifics-bank usage log (`usedIn`)** — the material grain of the same defect: `recordUsage` + the `record-usage` CLI verb stamp «used in edition NN» on the specifics an edition actually consumed (read from the bound slot-map via `boundSpecificIds`, so `abstrakt`/`ekstern` slots stamp nothing). Recorded at **lock**, so it means published rather than merely considered, and idempotent under a pivot re-lock. The bank's dedupe deliberately *encourages* re-surfacing the same material; this log is what makes that re-use visible at the next Step 1.5 instead of silent. Additive-optional — schema stays v1, existing banks load unchanged.
+- Suites: new `editions` 27/0; specifics-bank 28 → 45; test-runner 163 → 173 (Section 16r: 9 unconditional greps + non-vacuity self-test; anti-erosion floor 146 → 155). `tsc --noEmit` clean in both packages. Domain-general throughout.
+
 ### Built feedback (awaiting consumer-side proof)
 
 - **MR-F9** (demand-sweep «innenfra og ut») — built; the (a)/(b)/(c) evidence gate is a runtime demonstration, proven consumer-side (plugin agents don't resolve in the dev repo).