feat(linkedin-studio): N23 — positioning-brief-motor (generering + konsum) [skip-docs]

Persistert posisjonering som alle drafts bindes mot. Innplassert i
/linkedin:setup (Step 3g) etter operatør-friksjonskriteriet — setup eier
allerede ${DATA}/profile/ og har menyen; telling forblir 30.

- config/positioning-brief.template.md (NY): fire seksjoner (Who I am ·
  Who this is for · What I hold · How I differ), hver med _Evidence:_-linje.
- setup.md Step 3g: DELEGERER til linkedin-studio:strategy-advisor.
  Brain-konsum-blokken forblir i én kopi (N21-lærdommen), lint-håndhevet.
- strategy-advisor.md: distillasjonen, kildepresedens, anti-flatteri
  (What I hold må bære påstander en leser kan være UENIG i) og
  evidensgulv ([insufficient evidence] framfor plausibel oppfinnelse).
- Distillat, ikke andre profil: briefen REFERERER user-profile.md framfor
  å gjenta den. Operatørens deklarasjon og daterte anker slår maskinens
  inferens; motstrid rapporteres som spenning, aldri stille anvendt.
- Konsum: post/quick/batch + newsletter Step 1 + differentiation-checker
  (scorer originalitet mot How I differ, ikke generisk nyhet).
- Regenerering er operatør-gatet: explicit go + seksjonsvis diff + aldri
  stille overskriving av operatørens egne redigeringer.

Lint: Section 16y, 17 nye ubetingede sjekker (self-test 1 akseptert /
4 underspesifiserte avvist). Floor 251 → 268. Alle ti suiter grønne:
test-runner 270→287/0 · trends 300 · analytics 202 · hooks 191 · brain 134
· editions 72 · render 63 · specifics-bank 45 · tests 35 · contract-gate 33.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AbwkH8phPsgv9xFd8Qbq7E

commands/newsletter.md

@@ -341,6 +341,16 @@ Establish the edition brief with **at most ~3 calibration questions**. Infer
 everything you can from Step 0 (series brief, STATE.md, prior edition); only ask
 what genuinely changes the work.
 
+**Read the positioning brief first** —
+`${LINKEDIN_STUDIO_DATA:-$HOME/.claude/linkedin-studio}/profile/positioning-brief.md`.
+A long-form edition is the format where a missing position shows most: 1,500 words of
+competent survey that takes no stance is the failure mode. Use **What I hold** to fix
+what this edition *argues* (not merely covers) and **How I differ** as the brief-level
+test — if the edition as briefed could carry another author's byline unchanged, the
+angle is not yet an angle. Where the brief and the operator's stated brief for THIS
+edition disagree, the operator wins; note the tension in one line rather than quietly
+steering to the file. Absent file: proceed silently on the other sources.
+
 > **Trend intake (optional bridge — N7).** If this edition is being started from a
 > `/linkedin:trends` candidate — the operator supplies a **trend id** (shown in the
 > trends brief and via `CLI list --json`, where