Step 9 (post-lock distribution gate) får to tillegg, begge scoped til utgave-promo:
1. Hook-forge (E#7): 5-8 krok-varianter for delingsteksten. 110-140-båndet
håndheves PER VARIANT og MÅLES (perl -CSD; awk length/wc -c teller bytes og
lyver på æ/ø/å). Utenfor båndet = diskvalifisert, ikke rangert lavere.
Settet må spenne minst tre krok-typer, ellers er det omskrivinger, ikke valg.
Hver variant må spores til en påstand kroppen faktisk gjør (ingen bait).
Ingen predicted-engagement score — et tall som påstår å vite hva som sprer
seg er oppfunnet (N22-defektklassen); operatøren rangerer.
Valgt variant går GJENNOM randsone-gaten, aldri utenom.
2. Shareability-gate (E#8): konverter-modus får en ANDRE binær — deling.
«Hvem deler dette til en kollega, og hvorfor?» + RESHARE/SAVE/SEND.
Svaret må navngi en rolle og et avsender-motiv; «nyttig for alle i tech»
er NEI. Blokkerende: to mislykkede omramminger => operatørvalg (pivot eller
registrert foldIn), aldri en stille passering.
Ti suiter grønne: test-runner 300/0 (287->300, +13 ubetingede; floor 268->281)
· trends 300 · analytics 202 · hooks 191 · brain 134 · editions 72 · render 63
· specifics-bank 45 · tests 35 · contract-gate 33. Begge nye compound-predikater
mutasjonstestet mot faktisk fil (fjernet literal => rød).
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RvtDSvQDUmjd5bXdAxUu6D
C-8: gjør «praktisk anvendbar på alle nivå» til en konfigurerbar gate-akse og
fjerner den hardkodede primær-personaen. 6-fils scope (KTG-valgt) — gjør
targetLevel til en EKTE ende-til-ende-dimensjon i stedet for et fantomfelt:
- references/longform-quality-rules.md: «non-technical line manager» → brukerens
konfigurerte target-level span (domene-generelt).
- config/personas.template.md: «primær trumfer» krever nå obligatorisk sekundær i
MOTSATT ende av spennet; sekundær-NEI kan kun avskrives som «signal, ikke svikt»
med eksplisitt ceiling-begrunnelse. Ny tekniker-ende-seed (Persona 4,
Løsningsutvikler/AI-ingeniør) — tidligere kun 3 leder-personas.
- config/edition-state.template.json: additivt articles.NN.targetLevel-slot
(default null, INGEN schemaVersion-bump — samme mønster som sourceTrendId/language).
- commands/newsletter.md: persister resolvert targetLevel ved Step 1.5-checkpointet.
- agents/persona-reviewer.md: leser articles.NN.targetLevel og plasserer personaene
på spennet (fallback til persona-ekspertise om feltet er null).
Premiss-korreksjon: planens 4-fils scope antok targetLevel fantes i edition-state
via N7-broen; det stemte ikke (fantes kun i trend-store + fritekst-mapping). +2 filer
(edition-state-slot + newsletter-persist) gjør konsumet reelt.
TDD: ny Section 16q i test-runner (9 UNCOND. .md/.json-greps + non-vacuity self-test);
en vacuity-bug i egen edition-state-check fanget og skjerpet (grep slot-literal
"targetLevel": null, ikke bare ordet — sourceTrendId-docstringen inneholder allerede
"targetLevel"). test-runner 154→163/0, anti-erosion floor 137→146. Øvrige fem suiter
uendret grønne (trends 300 · brain 134 · hooks 140 · tests 35 · render 60).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014bE7VbkmR3cqHFEeGfzgwb
Cold, adversarial review package for the long-form pipeline + configurable
per-edition personas. Motivated by Del 4 (Security Champions pivot): the
in-session editor + persona sweep shared the drafting session's framing-bias,
so the shipped version was never independently re-reviewed.
Headless package (9a/9b):
- New Step 6.5 (headless-review) in /linkedin:newsletter, after the persona
sweep, before lock — the independence layer the in-session gates can't be.
- New standalone /linkedin:headless-review command (run in a fresh session for
maximum isolation; reconstructs frozen draft + contract + personas from disk).
- 3 new Opus archetypes, each with a cardinal context-isolation block that
refuses drafting-session framing as "context pollution":
- content-reviewer (argument integrity C1–C5, ≤8 flags)
- language-reviewer (Norwegian language L1–L5, ≤10 flags)
- fact-reviewer (cold re-verification F1–F4, risk-sort + pivot-risk, WebSearch)
- Deliberate redundancy with fact-checker / editorial-reviewer documented so
the pairs are never de-duplicated.
Pivot-reopen (9c):
- New /linkedin:pivot command: logs articles.NN.pivots[], resets currentPhase,
un-locks, marks gates to re-run.
- Pivot-detection gate in Step 8 lock precondition (>20% word-count change or
>2 new sections re-opens cleared gates). Del 4 v8→v11 worked example.
Per-artifact personas (new requirement):
- articles.NN.personas with resolution order (edition-state → series file →
plugin library → interactive). One or more readers configurable per edition.
Schema/docs:
- edition-state.template.json: additive personas[], pivots[], headlessReview,
headless-review phase (16 phases); personaSweep.resonance.wordCount baseline.
- 3 fasit fixtures + 3 structural lint tests (Del 4 worked cases).
- Counts: 24→26 commands, 16→19 agents, 15→16 newsletter phases.
- README + CLAUDE.md (plugin + root) + CHANGELOG synced.
Verification: 35 agent-fixture + 59 hook + 20 render tests green. Backward-
compatible (additive state); reload required before the 3 new agents resolve.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Implements the 6-change spec from the Seres-serien production
(linkedin-plugin-endringsspec.md). All acceptance criteria met.
1. Avoid-patterns (modell-/navne-katalog, completeness-over-reader-action,
self-referential overhead openings) → longform-quality-rules.md (rule 1+3)
+ user-profile.template.md.
2. Persona gate now BLOCKING with explicit hard-fail list (primær mistet meg /
doesn't own action / sjargong-mur / modell-navne-katalog → BLOCK;
"JA med store forbehold" = NEI) → persona-reviewer.md + personas.template.md.
3. Fact-check declared orthogonal to narrative strength + post-cutoff
web-search mandate + high-frequency-error checklist → fact-checker.md.
4. NEW agent voice-scrubber.md (Opus) — de-AI scrub + Norwegian-chronicle
voice-drift; gold standard = approved Norwegian editions, NOT the English
post corpus. Wired into newsletter.md Step 4.
5. Operator gates = render+annotate rounds (build-html.mjs to file://) as
primary flow, AskUserQuestion as receipt/fallback → newsletter.md 2.5+3a.
6. Edition state reconciled with STATE.md (ONE-system). edition-HANDOVER
template deleted; narrative to <serie>/STATE.md, machine data
(factcheckLog, personaSweep, immutableRules) to edition-state.json.
Agents 14 to 15; commands unchanged (24). Backward-compatible (additive
state-shape only). Docs updated across all three levels + CHANGELOG.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
