refactor(linkedin-studio): move agent fasit fixtures + tests out of agents/ (v0.5.3)

The 6 long-form-review fasit fixtures (agents/fixtures/*-cases.md) were registered
by Claude Code as junk `fixtures:*` agents because agents/ is scanned recursively.
They are test fixtures, not capabilities. Moved them + their 6 lint tests to
tests/ + tests/fixtures/ and retargeted the 5 agent fasit-refs. Count-neutral
namespace hygiene (ls agents/*.md still 19).

- agents/fixtures/*-cases.md            -> tests/fixtures/        (6)
- agents/__tests__/*-fixture.test.mjs   -> tests/                 (6; ../fixtures -> ./fixtures)
- 5 agent refs ${CLAUDE_PLUGIN_ROOT}/agents/fixtures -> /tests/fixtures
- version-sync 0.5.2 -> 0.5.3 (plugin.json / README badge / CLAUDE.md / CHANGELOG)

Verify: fixture-lint 35/35 at new path; render 20/20, hooks 139/139; test-runner 109/0/0.
Reinstall/reload required for the 6 spurious agents to leave the registry.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CrTb8ktf1XZWEVwgz5MTTo

tests/content-reviewer-fixture.test.mjs

@@ -0,0 +1,82 @@
+import { describe, test } from 'node:test';
+import assert from 'node:assert/strict';
+import { readFileSync } from 'node:fs';
+import { fileURLToPath } from 'node:url';
+
+// Lint-test for the content-reviewer fasit fixture.
+// Mirrors the structure-only discipline of editorial-reviewer-fixture.test.mjs,
+// persona-reviewer-fixture.test.mjs, and fact-checker-fixture.test.mjs: this test
+// asserts the SHAPE of the fixture — the one judging axis (argument-integritet),
+// all five checks (C1–C5), the three severities, the six Del 4 cases, the
+// direction-not-copy boundary, and the cold-reader / context-isolation rationale.
+// Whether the agent's live flags actually reproduce the fasit directions is
+// [GATE]/[OPERATØR], never self-certified here.
+
+const FIXTURE_PATH = fileURLToPath(
+  new URL('./fixtures/content-reviewer-cases.md', import.meta.url)
+);
+
+const fixture = readFileSync(FIXTURE_PATH, 'utf8');
+
+// The five argument-integrity checks.
+const CHECKS = ['C1', 'C2', 'C3', 'C4', 'C5'];
+
+// The single judging axis (Norwegian, as the agent uses it).
+const AXIS = 'argument-integritet';
+
+// The three-rung severity scale.
+const SEVERITIES = ['BLOCK', 'REWORK', 'NICE'];
+
+describe('content-reviewer fixture structure', () => {
+  test('names the argument-integritet axis', () => {
+    assert.ok(
+      new RegExp(AXIS, 'i').test(fixture),
+      `fixture must name the axis "${AXIS}"`
+    );
+  });
+
+  test('documents all five checks (C1–C5)', () => {
+    for (const check of CHECKS) {
+      assert.ok(
+        fixture.includes(check),
+        `fixture must reference the check "${check}"`
+      );
+    }
+  });
+
+  test('defines the three-rung severity scale', () => {
+    for (const sev of SEVERITIES) {
+      assert.ok(
+        fixture.includes(sev),
+        `fixture must define the severity "${sev}"`
+      );
+    }
+  });
+
+  test('documents exactly six Del 4 cases', () => {
+    const cases = fixture.match(/^###\s+Case\s+\d+\b/gim) || [];
+    assert.equal(
+      cases.length,
+      6,
+      `fixture must document exactly 6 Del 4 cases (found ${cases.length})`
+    );
+  });
+
+  test('keeps the jury-judges-writer-writes boundary (direction, not copy)', () => {
+    assert.ok(
+      /direction, not rewritten copy/i.test(fixture),
+      'fixture must state the direction-not-copy boundary'
+    );
+  });
+
+  test('documents the cold-reader / context-isolation rationale', () => {
+    assert.ok(
+      /context pollution/i.test(fixture),
+      'fixture must document the context-isolation principle (context pollution)'
+    );
+    assert.ok(
+      /cold/i.test(fixture),
+      'fixture must describe the agent as a cold reader'
+    );
+  });
+});

tests/editorial-reviewer-fixture.test.mjs

@@ -0,0 +1,87 @@
+import { describe, test } from 'node:test';
+import assert from 'node:assert/strict';
+import { readFileSync } from 'node:fs';
+import { fileURLToPath } from 'node:url';
+
+// Lint-test for the editorial-reviewer fasit fixture.
+// Mirrors the structure-only discipline of persona-reviewer-fixture.test.mjs and
+// fact-checker-fixture.test.mjs: this test asserts the SHAPE of the fixture —
+// the two judging axes, all ten checks (P1–P5 + A1–A5), the three severities,
+// and the eight Del 4 cases that form the gold standard. Whether the agent's
+// live flags actually reproduce the fasit directions is [GATE]/[OPERATØR],
+// never self-certified here.
+
+const FIXTURE_PATH = fileURLToPath(
+  new URL('./fixtures/editorial-reviewer-cases.md', import.meta.url)
+);
+
+const fixture = readFileSync(FIXTURE_PATH, 'utf8');
+
+// The ten checks: five prose-craft (P1–P5) + five narrative-architecture (A1–A5).
+const PROSE_CHECKS = ['P1', 'P2', 'P3', 'P4', 'P5'];
+const ARCH_CHECKS = ['A1', 'A2', 'A3', 'A4', 'A5'];
+
+// The two axis names (Norwegian, as the agent and the writing contract use them).
+const AXES = ['prosa-håndverk', 'narrativ-arkitektur'];
+
+// The three-rung severity scale.
+const SEVERITIES = ['BLOCK', 'REWORK', 'NICE'];
+
+describe('editorial-reviewer fixture structure', () => {
+  test('names both judging axes', () => {
+    for (const axis of AXES) {
+      assert.ok(
+        new RegExp(axis, 'i').test(fixture),
+        `fixture must name the axis "${axis}"`
+      );
+    }
+  });
+
+  test('documents all ten checks (P1–P5 + A1–A5)', () => {
+    for (const check of [...PROSE_CHECKS, ...ARCH_CHECKS]) {
+      assert.ok(
+        fixture.includes(check),
+        `fixture must reference the check "${check}"`
+      );
+    }
+  });
+
+  test('defines the three-rung severity scale', () => {
+    for (const sev of SEVERITIES) {
+      assert.ok(
+        fixture.includes(sev),
+        `fixture must define the severity "${sev}"`
+      );
+    }
+  });
+
+  test('documents the eight Del 4 cases', () => {
+    const cases = fixture.match(/^###\s+Case\s+\d+\b/gim) || [];
+    assert.equal(
+      cases.length,
+      8,
+      `fixture must document exactly 8 Del 4 cases (found ${cases.length})`
+    );
+  });
+
+  test('ties the checklist to the Maskinrommet §C2 truth source', () => {
+    assert.ok(
+      /§C2|C2/.test(fixture),
+      'fixture must reference the §C2 writing-contract truth source'
+    );
+  });
+
+  test('keeps the jury-judges-writer-writes boundary (direction, not copy)', () => {
+    assert.ok(
+      /direction, not rewritten copy/i.test(fixture),
+      'fixture must state the direction-not-copy boundary'
+    );
+  });
+
+  test('records the persona-blindspot rationale (≈6/8 editorial-only)', () => {
+    assert.ok(
+      /blindsone/i.test(fixture) && /6\/8/.test(fixture),
+      'fixture must record why the gate exists (blind spots, ~6/8 editorial-only)'
+    );
+  });
+});

tests/fact-checker-fixture.test.mjs

@@ -0,0 +1,61 @@
+import { describe, test } from 'node:test';
+import assert from 'node:assert/strict';
+import { readFileSync } from 'node:fs';
+import { fileURLToPath } from 'node:url';
+
+// Lint-test for the fact-checker fasit fixture.
+// Mirrors the structure-only discipline of state-updater.test.mjs: this test
+// asserts the SHAPE of the fixture (exactly 3 cases, one of each verdict, a
+// non-empty fasit per case). The accuracy comparison — does the agent's live
+// output actually match the fasit verdicts — is [GATE]/[OPERATØR], never
+// self-certified here.
+
+const FIXTURE_PATH = fileURLToPath(
+  new URL('./fixtures/fact-checker-cases.md', import.meta.url)
+);
+const VERDICTS = ['🟢', '🔴', '🟡'];
+
+const fixture = readFileSync(FIXTURE_PATH, 'utf8');
+
+// Split on "## Case N" headings; drop the preamble before the first case.
+const blocks = fixture
+  .split(/^##\s+Case\s+\d+\b.*$/m)
+  .slice(1)
+  .map((b) => b.trim());
+
+describe('fact-checker fixture structure', () => {
+  test('contains exactly 3 cases', () => {
+    assert.equal(blocks.length, 3, `expected 3 cases, found ${blocks.length}`);
+  });
+
+  test('each case carries exactly one verdict emoji', () => {
+    for (const [i, block] of blocks.entries()) {
+      const present = VERDICTS.filter((v) => block.includes(v));
+      assert.equal(
+        present.length,
+        1,
+        `case ${i + 1} must have exactly one of 🟢/🔴/🟡, found: [${present.join(', ')}]`
+      );
+    }
+  });
+
+  test('the three verdicts are one each of 🟢/🔴/🟡', () => {
+    const seen = blocks.map((b) => VERDICTS.find((v) => b.includes(v)));
+    assert.deepEqual(
+      [...seen].sort(),
+      [...VERDICTS].sort(),
+      `fixture must cover one true (🟢), one false (🔴), one unverifiable (🟡); saw ${JSON.stringify(seen)}`
+    );
+  });
+
+  test('each case has a non-empty Fasit field', () => {
+    for (const [i, block] of blocks.entries()) {
+      const m = block.match(/\*\*Fasit:\*\*\s*(.+)/);
+      assert.ok(m, `case ${i + 1} is missing a **Fasit:** field`);
+      assert.ok(
+        m[1].trim().length > 0,
+        `case ${i + 1} has an empty **Fasit:** field`
+      );
+    }
+  });
+});

tests/fact-reviewer-fixture.test.mjs

@@ -0,0 +1,92 @@
+import { describe, test } from 'node:test';
+import assert from 'node:assert/strict';
+import { readFileSync } from 'node:fs';
+import { fileURLToPath } from 'node:url';
+
+// Lint-test for the fact-reviewer fasit fixture.
+// Mirrors the structure-only discipline of fact-checker-fixture.test.mjs and
+// editorial-reviewer-fixture.test.mjs: this test asserts the SHAPE of the
+// fixture — the single axis (faktisk-korrekthet), the four checks (F1–F4), the
+// 🔴/🟡/🟢 risk sort, the six Del 4 (Security Champions) cases, the
+// direction-not-copy boundary, and the cold-reader / pivot-risk rationale.
+// Whether the agent's live verdicts actually reproduce the fasit is
+// [GATE]/[OPERATØR], never self-certified here.
+
+const FIXTURE_PATH = fileURLToPath(
+  new URL('./fixtures/fact-reviewer-cases.md', import.meta.url)
+);
+
+const fixture = readFileSync(FIXTURE_PATH, 'utf8');
+
+// The four checks: F1 verifiable claims · F2 quote precision · F3 number
+// attribution · F4 source quality.
+const CHECKS = ['F1', 'F2', 'F3', 'F4'];
+
+// The 🔴/🟡/🟢 risk sort (the emoji are the safest assertion).
+const VERDICTS = ['🔴', '🟡', '🟢'];
+
+describe('fact-reviewer fixture structure', () => {
+  test('names the axis "faktisk-korrekthet"', () => {
+    assert.ok(
+      /faktisk-korrekthet/i.test(fixture),
+      'fixture must name the axis "faktisk-korrekthet"'
+    );
+  });
+
+  test('documents all four checks (F1–F4)', () => {
+    for (const check of CHECKS) {
+      assert.ok(
+        fixture.includes(check),
+        `fixture must reference the check "${check}"`
+      );
+    }
+  });
+
+  test('references the 🔴/🟡/🟢 risk sort', () => {
+    for (const v of VERDICTS) {
+      assert.ok(
+        fixture.includes(v),
+        `fixture must reference the risk verdict "${v}"`
+      );
+    }
+  });
+
+  test('references the PASS/REWORK/BLOCK gate', () => {
+    for (const gate of ['PASS', 'REWORK', 'BLOCK']) {
+      assert.ok(
+        fixture.includes(gate),
+        `fixture must reference the gate decision "${gate}"`
+      );
+    }
+  });
+
+  test('documents exactly 6 Del 4 cases', () => {
+    const cases = fixture.match(/^###\s+Case\s+\d+\b/gim) || [];
+    assert.equal(
+      cases.length,
+      6,
+      `fixture must document exactly 6 Del 4 cases (found ${cases.length})`
+    );
+  });
+
+  test('states the direction-not-copy boundary', () => {
+    assert.ok(
+      /direction, not rewritten copy/i.test(fixture),
+      'fixture must state the direction-not-copy boundary'
+    );
+  });
+
+  test('documents the cold-reader / context-pollution principle', () => {
+    assert.ok(
+      /context pollution/i.test(fixture) && /framing-bias/i.test(fixture),
+      'fixture must document the cold-reader / context-pollution / framing-bias principle'
+    );
+  });
+
+  test('records the pivot-premise-risk rationale', () => {
+    assert.ok(
+      /pivot/i.test(fixture),
+      'fixture must record why the gate exists (pivot premise never met Step 5)'
+    );
+  });
+});

tests/fixtures/content-reviewer-cases.md

@@ -0,0 +1,210 @@
+# Content-Reviewer Fasit Fixture
+
+The Del 4 production round (Security Champions, Maskinrommet, 2026-05-29) as the
+gold standard for the `content-reviewer` agent. Late in the round the draft took
+a **Security Champions pivot**: a new ~260-word section introducing the Champions
+model and a new ~270-word role-description section were added after the
+in-session gates had already formed their reading. The in-session gates
+(fact-check Step 5, editorial Step 5.5, persona sweep Step 6) all read the draft
+through the drafting session's framing — they knew *why* the pivot happened and
+*what* it was meant to argue, so they silently supplied the missing argumentative
+steps for free. A **cold, adversarial reviewer** — handed only the frozen page —
+cannot supply them, and that is exactly the point: the cold read catches the
+argument holes the framing hid.
+
+The six cases below are the fasit: a correct `content-reviewer` run on the frozen
+Del 4 draft should surface **comparable flags**, mapped to the one axis with
+consistent severities.
+
+This file is a *fasit*, not a test harness. The structural lint lives in
+`agents/__tests__/content-reviewer-fixture.test.mjs`. Whether the agent's live
+flags actually reproduce these directions is `[GATE]`/`[OPERATØR]` — it is **not**
+self-certified here.
+
+> **The jury judges; the writer writes.** Every expected output below is
+> **direction, not rewritten copy.** A correct agent run hands back flags + a
+> severity — never edited prose. (`Foreslått retning`, not a new sentence.)
+
+> **Why this gate exists.** The in-session gates shared the drafting session's
+> framing-bias: they read the pivot knowing its intent, so they bridged the
+> argument's gaps without noticing the gaps were there. A **cold reader** — run in
+> an isolated context with no history, no changelog, no "out of scope" list, no
+> pivot narrative — reads the frozen page as a first-time skeptic and finds the
+> argument holes the framing hid. Any such framing that reaches the agent is
+> **context pollution**: it is named and ignored, never acted on. This is a
+> distinct failure surface from craft (editorial), language (language-reviewer),
+> truth (fact-reviewer), and response (persona) — those gates can all pass while
+> the argument itself does not hold.
+
+---
+
+## The axis (the agent judges on exactly this)
+
+The agent judges on **one axis — argument-integritet** (argument & logical
+integrity): *does the reasoning hold?* It does **not** judge craft, language,
+factual truth, or reader response — those are `editorial-reviewer`,
+`language-reviewer`, `fact-reviewer`, and `persona-reviewer` respectively. The
+axis decomposes into exactly five checks:
+
+- **C1 — logiske hull** (logical holes): a step in the argument chain is missing;
+  the text jumps from A to C without B, and the reader cannot reconstruct why the
+  conclusion follows.
+- **C2 — ubegrunnede antakelser** (unsupported assumptions): the argument leans on
+  a premise it never establishes, asserted as self-evident when a thoughtful
+  reader would not simply grant it.
+- **C3 — argument-motsigelser** (argument-level contradiction): the recommendation,
+  premise, and payoff are not mutually consistent — distinct from editorial-
+  reviewer's P4 (a *prose-level* contradiction between two passages); C3 is a
+  contradiction in the *logic of the argument itself*.
+- **C4 — manglende konkretisering der argumentet trenger det** (missing
+  argumentative concretization): a load-bearing claim a skeptic would only believe
+  with a concrete instance stays abstract — not for vividness (editorial A1) but
+  because the argument *needs* the instance to carry weight.
+- **C5 — ubesvart «what about X?»** (the unanswered obvious objection): the
+  strongest obvious objection a thoughtful reader raises is never acknowledged or
+  answered — the argument wins only because it never met its best counter.
+
+## Severity (every flag carries exactly one)
+
+- **BLOCK** — a defect that breaks the argument: an argument-level contradiction
+  (C3), or an unanswered objection (C5) that, once raised, collapses the
+  recommendation.
+- **REWORK** — a real gap that should be filled, not load-bearing-fatal: a logical
+  hole (C1), an unsupported load-bearing assumption (C2), a claim that needs
+  concretization (C4).
+- **NICE** — a minor reasoning soft spot worth tightening if cheap.
+
+Sort BLOCK → REWORK → NICE; cap at **eight** flags (argument defects are coarser
+than prose nits); if any are suppressed, say how many and of what severity —
+never silently truncate.
+
+---
+
+## The six Del 4 argument points (fasit)
+
+Each case states the argument defect a cold read would catch on the frozen Del 4
+draft, the check (C1–C5) it belongs to, the expected severity, and the direction a
+correct agent run returns. Every case is an **argument blind spot** — distinct
+from craft (what `editorial-reviewer` would catch) and response (what
+`persona-reviewer` would catch). The in-session gates passed the draft; the cold
+read does not, because the framing they shared is gone.
+
+### Case 1 — pivot-premisset asserted uten støtte (unsupported pivot premise)
+
+- **Axis:** argument-integritet · **Check:** C2 · **Severity:** BLOCK
+- **Cold-read defect:** The new ~260-word Security Champions section opens by
+  treating "Security Champions er svaret" as an established premise the rest of
+  the part builds on — but the frozen page never establishes *why* the Champions
+  model is the right response rather than one option among several. The drafting
+  session knew the rationale; the cold reader is handed only the assertion.
+- **Fasit / direction:** The pivot's load-bearing premise is asserted as
+  self-evident with no support a first-time skeptic would grant. Direction:
+  establish why the Champions model follows from the part's problem, or hedge it
+  as one option — do not let the whole section rest on an un-earned premise. (An
+  unsupported *load-bearing* premise that the section depends on is BLOCK: the
+  argument has not earned the right to make its central move.)
+
+### Case 2 — ubesvart «hva med små organisasjoner?» (unanswered obvious objection)
+
+- **Axis:** argument-integritet · **Check:** C5 · **Severity:** BLOCK
+- **Cold-read defect:** The strongest obvious objection a thoughtful reader raises
+  on first reading the Champions pivot — *"what about small organisations that
+  cannot staff a dedicated Champion?"* — is never acknowledged or answered. The
+  recommendation effectively assumes an org large enough to nominate a Champion,
+  and the argument wins only because it never meets this counter.
+- **Fasit / direction:** Name the objection and answer it (a small-org variant, an
+  explicit scope boundary, or a rule of thumb) — an unanswered objection that, once
+  raised, collapses the recommendation for a whole class of readers is BLOCK.
+  Direction only; the agent does not write the answer.
+
+### Case 3 — sprang fra «Champions finnes» til «dømmekraft bevart» (logical hole)
+
+- **Axis:** argument-integritet · **Check:** C1 · **Severity:** REWORK
+- **Cold-read defect:** The text jumps from *"Security Champions finnes i
+  organisasjonen"* (A) to *"dermed er dømmekraften bevart"* (C) with no connecting
+  step (B): existence of a role does not on its own establish that judgment is
+  preserved. The reader cannot reconstruct why the conclusion follows. The session
+  carried the missing step in its head; the page does not state it.
+- **Fasit / direction:** Supply the missing step — *how* the Champion's presence
+  translates into preserved judgment (mechanism, mandate, practice) — or soften the
+  conclusion to a hypothesis. A bridgeable-but-unbridged jump on a supporting line
+  is REWORK.
+
+### Case 4 — rolle-seksjonen aldri forankret i én konkret org (missing concretization)
+
+- **Axis:** argument-integritet · **Check:** C4 · **Severity:** REWORK
+- **Cold-read defect:** The new ~270-word role-description section describes what a
+  Champion *does* entirely in the abstract and never grounds it in **one concrete
+  organisation** where this role actually operates. This is not a vividness nit
+  (that would be editorial A1) — the *argument* that the role works needs one real
+  instance to be believed; a skeptic will not grant an abstract job description as
+  evidence the model functions.
+- **Fasit / direction:** Anchor the role in a single concrete (preferably
+  Norwegian) org where a Champion operates, so the load-bearing claim "this role
+  works" carries weight. Flag the *absence of the argument-bearing instance*; do
+  not supply the org. (Boundary: route any pure craft/vividness face to editorial
+  A1; this flag is the argument face — the claim cannot be believed abstractly.)
+
+### Case 5 — anbefaling delegerer den dømmekraften serien sier ikke kan settes ut (argument contradiction)
+
+- **Axis:** argument-integritet · **Check:** C3 · **Severity:** BLOCK
+- **Cold-read defect:** The series premise is *"du kan ikke sette ut dømmekraft"*
+  (you cannot outsource judgment). The Champions recommendation, read cold on the
+  frozen page, effectively **delegates that judgment** to the Champion — the close
+  recommends the very move the premise rules out. Premise, recommendation, and
+  payoff are not mutually consistent. This is an argument-level contradiction (C3),
+  not a prose-level one between two passages (that would be editorial P4): the
+  *logic* defeats itself.
+- **Fasit / direction:** Hold premise, recommendation, and gevinst side by side and
+  resolve one side — either reframe the Champion as *supporting* judgment that
+  stays distributed (not a delegate it is outsourced to), or qualify the series
+  premise. A recommendation that defeats the series premise is BLOCK.
+
+### Case 6 — gevinst-leddet antar utbredt modenhet (unsupported assumption)
+
+- **Axis:** argument-integritet · **Check:** C2 · **Severity:** REWORK
+- **Cold-read defect:** The promised payoff of the Champions model leans on an
+  unstated assumption that the surrounding organisation is mature enough to use a
+  Champion well (clear mandate, time allocation, leadership backing). The frozen
+  page asserts the gevinst as if it follows automatically; the cold reader sees an
+  un-earned premise standing between the model and its benefit.
+- **Fasit / direction:** Establish or hedge the maturity assumption the payoff
+  depends on — name the conditions under which the gevinst holds, or mark it
+  conditional. A load-bearing assumption left unstated under the payoff is REWORK
+  (it weakens the case rather than defeating it outright).
+
+---
+
+## Expected aggregate (what a correct run looks like)
+
+- **Total flags:** 6 (well within the ≤8 cap — no suppression needed).
+- **By check:** C1 = 1 (Case 3) · C2 = 2 (Cases 1, 6) · C3 = 1 (Case 5) ·
+  C4 = 1 (Case 4) · C5 = 1 (Case 2).
+- **By severity:** BLOCK = 3 (Cases 1, 2, 5 — unsupported pivot premise,
+  unanswered small-org objection, premise/recommendation contradiction) ·
+  REWORK = 3 (Cases 3, 4, 6) · NICE = 0.
+- **All six are argument blind spots:** none is a craft defect (`editorial-
+  reviewer`'s domain), a language defect (`language-reviewer`), a factual error
+  (`fact-reviewer`), or a resonance miss (`persona-reviewer`). The in-session
+  gates passed the draft on every one of those axes — and still the argument did
+  not hold, because they read it through the session's framing. The cold read is
+  the quantified case for the gate.
+
+A run that reproduces ~these six directions, on the one argument-integritet axis,
+with ~these severities, is **comparable** to the cold adversarial read the gate is
+built to deliver. Exact wording is the editor's; the agent returns
+**direction, not rewritten copy.**
+
+## Calibration boundary
+
+Whether the agent's live flags truly match this fasit is judged by the operator
+(`[OPERATØR]`), not self-certified here. This fixture is the calibration target,
+the same way `editorial-reviewer-cases.md`, `persona-reviewer-cases.md`, and
+`fact-checker-cases.md` are fasits for their agents.
+
+> **Live-run note.** A live run on the frozen Del 4 draft requires (a) a Claude
+> Code session reload — a freshly added agent is not invokable until the plugin
+> agent set is rebuilt at session start — and (b) a genuinely **cold** invocation
+> (an isolated context with no drafting-session history, changelog, scope list, or
+> pivot narrative reaching the agent). Until both hold, this fixture is the
+> gold-standard of record.

tests/fixtures/editorial-reviewer-cases.md

@@ -0,0 +1,157 @@
+# Editorial-Reviewer Fasit Fixture
+
+The Del 4 production round (Maskinrommet, 2026-05-28) as the gold standard for the
+`editorial-reviewer` agent. The persona resonance sweep returned 15 flags across
+three personas (Linjeleder C primær + KI-seksjon B sekundær + IT-direktør A
+sekundær) and **every persona reported PASS / ready-to-publish**. KTG then found
+**eight editorial points on first reading** — and only ~25 % of them overlapped
+anything the personas had touched. The other six were craft/architecture blind
+spots. Those eight points are the fasit below: a correct `editorial-reviewer` run
+on Del 4 v5 should surface **comparable flags**, mapped to the two axes with
+consistent severities.
+
+This file is a *fasit*, not a test harness. The structural lint lives in
+`agents/__tests__/editorial-reviewer-fixture.test.mjs`. Whether the agent's live
+flags actually reproduce these directions is `[GATE]`/`[OPERATØR]` — it is **not**
+self-certified here.
+
+> **The jury judges; the writer writes.** Every expected output below is
+> **direction, not rewritten copy.** A correct agent run hands back flags + a
+> severity — never edited prose. (`Foreslått retning`, not a new sentence.)
+
+> **Why this gate exists.** A persona PASS measures *reader response*, not *craft*.
+> Six of these eight points were invisible to the persona sweep because they are
+> architecture and prose-craft defects, not resonance defects. The numbers tell
+> the story: persona overlap ≈ 2/8; editorial-only ≈ 6/8.
+
+---
+
+## The two axes (the agent judges on exactly these)
+
+Both axes are the operationalized mirror of the **Maskinrommet skrivekontrakt
+§C2** — §C2 is the source of truth; this fixture and the agent's checklist follow
+it. (§C2 is the craft half of the writing contract; §A — skeleton-before-prose —
+is codified in `references/longform-quality-rules.md` rule 8.)
+
+
+- **Prosa-håndverk** (mechanical, grep-able): P1 tankestrek-tetthet · P2 ordrette
+  gjentakelser · P3 postulerte tall uten kilde/hedge · P4 indre selvmotsigelse ·
+  P5 versal-tic.
+- **Narrativ-arkitektur** (evaluative): A1 konkret instansiering · A2 teori-anker
+  for hypoteser · A3 serietittel-symmetri · A4 like-brukbar handling per adressat ·
+  A5 konklusjon ikke overlastet.
+
+## Severity (every flag carries exactly one)
+
+- **BLOCK** — misrepresents the piece or loses the takeaway.
+- **REWORK** — a real craft/architecture weakness, not load-bearing-fatal.
+- **NICE** — cheap polish, fold in if convenient.
+
+---
+
+## The eight Del 4 editorial points (fasit)
+
+Each case states the point KTG raised, the axis it belongs to, the expected
+severity, and the direction a correct agent run returns. The persona-overlap
+column records whether the persona sweep had already (partially) touched it —
+the whole reason the gate is needed is the rows marked **blindsone**.
+
+### Case 1 — manglende konkret eksempel (abstract figure never instantiated)
+
+- **Axis:** A1 (arkitektur) · **Severity:** REWORK
+- **Persona overlap:** delvis (KI-seksjon B brushed it) — *not* a pure blind spot.
+- **Fasit / direction:** An abstract figure carries the section but never lands on
+  one concrete case the reader can picture. Direction: instantiate with a single
+  verifiable (preferably Norwegian) case — do not list several. The agent flags
+  the *absence of instantiation*; it does not supply the case.
+
+### Case 2 — postulert tall uten kilde eller hedge (postulated number)
+
+- **Axis:** P3 (prosa) · **Severity:** REWORK
+- **Persona overlap:** delvis (IT-direktør A brushed it).
+- **Fasit / direction:** A specific figure is stated as fact with neither an inline
+  source marker nor a hedge. This is distinct from a fact-check finding — Step 5
+  verifies numbers that *have* a provenance; here the provenance is simply
+  **absent**. Direction: source it or hedge it ("anslagsvis"); else cut.
+
+### Case 3 — manglende SDT-anker for tillit-effekt (unanchored hypothesis) — BLINDSONE
+
+- **Axis:** A2 (arkitektur) · **Severity:** BLOCK
+- **Persona overlap:** none — pure blind spot.
+- **Fasit / direction:** A psychological hypothesis about a trust effect is asserted
+  as if established, with no named theory anchor (e.g. Self-Determination Theory)
+  and no explicit hedge. A hypothesis dressed as a finding is an architecture
+  defect. Direction: anchor in a named model OR mark it explicitly as hypothesis.
+
+### Case 4 — brutt serietittel-kobling (broken series-title symmetry) — BLINDSONE
+
+- **Axis:** A3 (arkitektur) · **Severity:** REWORK
+- **Persona overlap:** none — pure blind spot.
+- **Fasit / direction:** The part does not bind back to the series premise / its own
+  title — it floats free of the whole. Direction: tie the part's argument back to
+  the series title so the reader feels the part-of-a-whole. (N/A only for a
+  standalone edition; Del 4 is part of a series, so it applies.)
+
+### Case 5 — manglende småbedrifts-tommelfingerregel (stranded addressee) — BLINDSONE
+
+- **Axis:** A4 (arkitektur) · **Severity:** BLOCK
+- **Persona overlap:** none — pure blind spot.
+- **Fasit / direction:** The text addresses more than one reader but the actionable
+  takeaway only serves one; the small-business reader leaves with nothing they can
+  do. Direction: add a small-business rule of thumb so each addressee gets an
+  equally-usable action. (Stranding an addressee = BLOCK: that reader has no
+  takeaway at all.)
+
+### Case 6 — ordrette gjentakelser (verbatim repetition) — BLINDSONE
+
+- **Axis:** P2 (prosa) · **Severity:** REWORK
+- **Persona overlap:** none — pure blind spot.
+- **Fasit / direction:** A distinctive phrase recurs more than twice. Direction:
+  vary or cut the repeats; keep at most the one load-bearing use. `grep`-findable.
+
+### Case 7 — tankestrek-tetthet (em-dash over-density) — BLINDSONE
+
+- **Axis:** P1 (prosa) · **Severity:** REWORK
+- **Persona overlap:** none — pure blind spot.
+- **Fasit / direction:** Em-dashes run above ~1 per 50 words (clusters within
+  paragraphs). Direction: thin them to the local target; the em-dash is a tool,
+  not a tic. Report the count. `grep`-findable.
+
+### Case 8 — indre selvmotsigelse (internal contradiction) — BLINDSONE
+
+- **Axis:** P4 (prosa) · **Severity:** BLOCK
+- **Persona overlap:** none — pure blind spot.
+- **Fasit / direction:** Two passages cannot both be true (an assertion the
+  conclusion silently reverses). Direction: name the contradiction and resolve one
+  side — a contradiction misrepresents the piece, so BLOCK.
+
+---
+
+## Expected aggregate (what a correct run looks like)
+
+- **Total flags:** 8 (well within the ≤10 cap — no suppression needed).
+- **By axis:** prosa-håndverk = 4 (P1, P2, P3, P4) · narrativ-arkitektur = 4 (A1,
+  A2, A3, A4). A5 (overloaded conclusion) and P5 (versal-tic) did **not** flag on
+  Del 4 v5 — record them clean.
+- **By severity:** BLOCK = 3 (A2, A4, P4) · REWORK = 5 (A1, P3, A3, P2, P1) ·
+  NICE = 0.
+- **Persona overlap:** 2/8 (Cases 1 + 2, both delvis) · editorial-only blind
+  spots: 6/8 (Cases 3–8). This 6/8 is the quantified case for the gate.
+
+A run that reproduces ~these eight directions, on ~these axes, with ~these
+severities, is **comparable** to KTG's actual editorial round — the bar
+acceptance-criterion #8 sets. Exact wording is the editor's; the agent returns
+direction, never copy.
+
+## Calibration boundary
+
+Whether the agent's live flags truly match this fasit is judged by the operator
+(`[OPERATØR]`), not self-certified here. This fixture is the calibration target,
+the same way `persona-reviewer-cases.md` and `fact-checker-cases.md` are fasits
+for their agents.
+
+> **Live-run note.** A live run on Del 4 v5 requires (a) a Claude Code session
+> reload — a freshly added agent is not invokable until the plugin agent set is
+> rebuilt at session start — and (b) read access to the Del 4 v5 draft in the
+> Maskinrommet series folder. Until both hold, this fixture is the gold-standard
+> of record.

tests/fixtures/fact-checker-cases.md

@@ -0,0 +1,52 @@
+# Fact-Checker Fasit Fixture
+
+Three reference claims with known ground truth, used to sanity-check the
+`fact-checker` agent. Each case states the claim, the **fasit** (the correct
+answer + why), and the expected risk verdict.
+
+- 🟢 = verified true against a primary/credible source
+- 🔴 = contradicted by evidence (false), or a high-risk claim asserted without support
+- 🟡 = unverifiable from available sources — flagged, never guessed
+
+This file is a *fasit*, not a test harness. The structural lint lives in
+`agents/__tests__/fact-checker-fixture.test.mjs`. Whether the agent's live
+output actually reproduces these verdicts is `[GATE]`/`[OPERATØR]` — it is
+not self-certified.
+
+Each case block below carries exactly one verdict emoji (in its **Verdict**
+field); the prose deliberately avoids emoji so the structural lint can read a
+single, unambiguous verdict per case.
+
+---
+
+## Case 1 — verifiable true
+
+- **Claim:** The EU AI Act entered into force on 1 August 2024.
+- **Verdict:** 🟢
+- **Fasit:** True. Regulation (EU) 2024/1689 was published in the Official
+  Journal on 12 July 2024 and entered into force 20 days later, on
+  1 August 2024. This is confirmable against the primary source (EUR-Lex)
+  and the European Commission's own communications. A correct agent run
+  returns the verified verdict with a primary-source citation.
+
+## Case 2 — verifiable false
+
+- **Claim:** GPT-4 was developed and released by Anthropic.
+- **Verdict:** 🔴
+- **Fasit:** False. GPT-4 was released by OpenAI (March 2023). Anthropic
+  develops the Claude model family. The claim is contradicted by both
+  vendors' primary documentation. A correct agent run returns the high-risk
+  verdict and names the contradicting source — it must not soften a
+  contradicted claim to the unverified tier.
+
+## Case 3 — unverifiable
+
+- **Claim:** A Norwegian public-sector agency cut its case-handling time by
+  exactly 37% in Q3 2025 after deploying an internal AI assistant.
+- **Verdict:** 🟡
+- **Fasit:** Unverifiable. No named agency, no published report, and no
+  primary source exists for this precise figure; an internal operational
+  metric of this kind is not independently confirmable from open sources.
+  A correct agent run returns the unverified verdict and states explicitly
+  that the claim cannot be verified — it must not fill the gap by inventing
+  a plausible source or promoting the claim to the verified tier.

tests/fixtures/fact-reviewer-cases.md

@@ -0,0 +1,196 @@
+# Fact-Reviewer Fasit Fixture
+
+The Del 4 production round (Security Champions, Maskinrommet, 2026-05-29) as the
+gold standard for the `fact-reviewer` agent. The in-session `fact-checker`
+(Step 5) ran on a still-moving draft. A **late Security Champions pivot** — a new
+argument anchor — arrived **after** that Step 5 sweep, so the pivot's premise was
+**never fact-checked**. The pivot then went through the in-session persona sweep
+(Step 6) and reached the frozen, publish-ready version with an unverified premise
+intact. KTG's cold re-reading caught a misattribution, a quote-precision error, a
+postulated number with no provenance, a "settled standard" that actually varies,
+and a secondary source trusted for a precise figure — six points in all. Those six
+points are the fasit below: a correct `fact-reviewer` run on the frozen/pivoted Del
+4 should surface **comparable verdicts**, mapped to the four checks with consistent
+risk verdicts and the pivot-risk flag.
+
+This file is a *fasit*, not a test harness. The structural lint lives in
+`agents/__tests__/fact-reviewer-fixture.test.mjs`. Whether the agent's live
+verdicts actually reproduce these is `[GATE]`/`[OPERATØR]` — it is **not**
+self-certified here.
+
+> **The jury judges; the writer writes.** Every expected output below is
+> **direction, not rewritten copy.** A correct agent run hands back a verdict + a
+> source (or "none found") + a fix-as-direction (source it / hedge it / cut it) —
+> **never** edited prose.
+
+> **Why this gate exists.** Fact-checking was **post-hoc relative to the pivot** in
+> Del 4: the in-session Step 5 sweep ran *before* the Security Champions pivot was
+> added, so the pivot premise never met it. A **cold re-verification on the
+> frozen/pivoted version** closes that gap — it re-checks every claim with equal
+> suspicion, with no knowledge of which passages were pivot-fresh, and so catches
+> exactly the premise Step 5 missed.
+
+---
+
+## The axis and the four checks (the agent judges on exactly these)
+
+The single axis is **faktisk-korrekthet** — factual correctness, re-verified COLD
+on the frozen/pivoted version. It is checked through four lenses:
+
+- **F1 — Verifiserbare påstander** (verifiable claims): every checkable assertion
+  (numbers, dates, named examples, attributions, causal claims) searched against
+  primary/credible sources; opinions and predictions skipped.
+- **F2 — Sitat-presisjon** (quote precision): any quotation must match the source
+  verbatim — wording, attribution, and who said it. «Vi» vs «Vi i Nav» is a
+  precision failure even when the gist is right.
+- **F3 — Tall-attribusjon** (number attribution): every figure must trace to a
+  named source; a postulated number with no provenance is 🟡/🔴. Here provenance is
+  VERIFIED (distinct from `editorial-reviewer`'s P3, which only flags the absence
+  of a source/hedge without searching).
+- **F4 — Kilde-kvalitet** (source quality): primary over secondary; a source
+  supporting "around a third" does not verify "exactly 37 %"; post-cutoff claims
+  must be web-searched.
+
+## Context isolation — cold reader (the agent's cardinal rule)
+
+The agent runs in a **cold context**: its only input is this prompt, the frozen
+draft, and the writing contract. Any pivot narrative, changelog, omission list, or
+"what the author intended" is **context pollution** — the agent states it is
+ignoring it and judges only the text. That independence (no main-session
+**framing-bias**) is the whole reason a defect that survived the in-session gates
+can still be caught here.
+
+**Pivot-premise risk (the design feature).** Because the agent does **not** know
+which passages were added in a late pivot, it re-checks **every** claim with equal
+suspicion — a claim's age in the draft buys it no trust. A claim that looks freshly
+bolted on (new anchor, new section topic, a 2025/2026 figure) is surfaced in a
+**pivot-risk** subsection. A pivot-risk claim that fails verification is the
+headline catch: the pivot premise that never met Step 5.
+
+## Risk sort and gate (every claim carries exactly one verdict)
+
+- 🔴 **høy risiko** (high risk) → **BLOCK** — contradicted by evidence, or a precise
+  claim with no usable source.
+- 🟡 **uverifisert** (unverified) → **REWORK** — cannot be confirmed / weak sources;
+  asserted as fact must be hedged, sourced, or cut.
+- 🟢 **verifisert** (verified) → keep — confirmed by a primary/credible source
+  matching the claim.
+
+The agent recommends PASS / REWORK / BLOCK; the operator (`[OPERATØR]`) holds the
+gate. Each case block below carries exactly one verdict emoji in its **Verdict**
+field; the surrounding prose deliberately avoids the emoji so the structural lint
+can read a single unambiguous verdict per case.
+
+---
+
+## The six Del 4 worked cases (fasit)
+
+Each case states the point, the check it belongs to (F1–F4), the verdict, whether
+it is a pivot-risk claim, and the direction a correct cold run returns.
+
+### Case 1 — pivot-premissen aldri faktasjekket (pivot premise never met Step 5) — PIVOT-RISK
+
+- **Check:** F1 (verifiable claim — the pivot's anchor assertion) · **Verdict:** 🔴
+- **Pivot-risk:** YES — this is the late Security Champions pivot, added *after* the
+  Step 5 fact-check; its premise was never verified in-session.
+- **Fasit / direction:** The Security Champions pivot rests on a premise asserted as
+  established fact, but no primary source confirms it as stated. Because the pivot
+  arrived after Step 5, the in-session sweep never touched it. The cold re-check
+  — applying equal suspicion to a claim it does not know is pivot-fresh — searches
+  primary sources, finds none that confirm the premise as worded, and returns high
+  risk. **This is the exact catch the gate exists for:** the cold pass on the frozen
+  version surfaces the pivot premise that Step 5 missed. Direction: source the
+  premise to a primary record or recast it as a hedged hypothesis; do not assert.
+  The agent returns the verdict + "none found", not a rewritten premise.
+
+### Case 2 — feilattribusjon (misattribution) — editor caught on cold read
+
+- **Check:** F1 (attribution) + F2 (who said it) · **Verdict:** 🔴
+- **Pivot-risk:** no.
+- **Fasit / direction:** A statement is attributed to the wrong source/originator —
+  the named party is not who said or published it. Contradicted by the primary
+  record, so high risk (a contradicted claim is 🔴 regardless of partial score).
+  Direction: correct the attribution to the verified originator, or cut the
+  attribution; the agent names the contradicting source, never invents one.
+
+### Case 3 — sitat-presisjon «Vi» vs «Vi i Nav» (quote precision) — editor caught
+
+- **Check:** F2 (quote precision) · **Verdict:** 🟡
+- **Pivot-risk:** no.
+- **Fasit / direction:** A quotation's gist is right but the wording/attribution is
+  not verbatim: the source said «Vi i Nav», the draft renders «Vi». Changing who the
+  «vi» refers to is a precision failure even though the meaning is close. The source
+  exists, so this is unverified-as-worded rather than contradicted. Direction: match
+  the source verbatim — restore «Vi i Nav» — or mark it as a paraphrase, not a
+  quote. The agent flags the precision gap; it does not supply the corrected line.
+
+### Case 4 — postulert tall uten proveniens (postulated number, no provenance)
+
+- **Check:** F3 (number attribution) · **Verdict:** 🟡
+- **Pivot-risk:** plausible — a figure of this kind often arrives with a late anchor;
+  surface it in the pivot-risk subsection if it reads freshly bolted on.
+- **Fasit / direction:** A specific figure is stated as fact with **no named
+  source**. Distinct from `editorial-reviewer`'s P3, which would only flag the
+  *absence* of a source/hedge: here the agent **searches for the provenance**, finds
+  none that supports the exact figure, and returns unverified. Direction: trace it to
+  a named source or hedge it ("anslagsvis"); else cut. The agent never invents a
+  provenance to promote it to verified.
+
+### Case 5 — «Security Champions» som settet standard (a settled standard that varies)
+
+- **Check:** F1 (claim) + source-scope · **Verdict:** 🔴
+- **Pivot-risk:** YES — part of the same Security Champions pivot.
+- **Fasit / direction:** The "Security Champions" practice is presented as a settled,
+  universal standard, but in reality it is a practice that **varies per
+  organization** — implementations, scope, and definitions differ. A local
+  convention dressed as a universal standard is a source-scope failure; asserting it
+  as settled with no source that supports the universal framing is high risk.
+  Direction: scope the claim to where it actually holds ("varies; in some orgs…") or
+  source the universal framing to a standard that does establish it. The agent flags
+  the over-broad scope; it does not rewrite the passage.
+
+### Case 6 — sekundærkilde brukt for et presist tall (secondary source for a precise figure)
+
+- **Check:** F4 (source quality) + F3 (number) · **Verdict:** 🟡
+- **Pivot-risk:** no.
+- **Fasit / direction:** A precise figure is backed only by a **secondary source**
+  that summarizes the number — the primary record supports a *directional* claim
+  ("around a third"), not the precise figure ("37 %") the draft asserts. A source
+  supporting "around a third" does not verify "exactly 37 %". Direction: trace to the
+  primary source and confirm the exact figure, soften the draft to the directional
+  claim the secondary source actually supports, or hedge. The agent records the
+  secondary source found and the precision gap, not a corrected number.
+
+---
+
+## Expected aggregate (what a correct cold run looks like)
+
+- **Total verdicts surfaced:** 6 (within a reasonable verification-log cap; no 🔴
+  silently dropped).
+- **By check:** F1 = 3 (Cases 1, 2, 5) · F2 = 2 (Cases 2, 3) · F3 = 2 (Cases 4, 6) ·
+  F4 = 1 (Case 6). (Cases overlap checks; the headline check is listed first.)
+- **By risk verdict:** 🔴 høy risiko = 3 (Cases 1, 2, 5 → BLOCK) · 🟡 uverifisert = 3
+  (Cases 3, 4, 6 → REWORK) · 🟢 verifisert = 0 among the flagged points (the rest of
+  the draft's claims verify clean and are not listed here).
+- **Pivot-risk:** Cases 1 and 5 are the Security Champions pivot; Case 4 is a
+  plausible pivot-risk. **Case 1 is the headline catch** — the pivot premise that
+  was never fact-checked in-session, caught only because the cold pass re-checks
+  every claim with equal suspicion.
+
+A run that reproduces ~these six verdicts, on ~these checks, with ~these risk
+levels — and that surfaces the Security Champions pivot premise as a pivot-risk 🔴
+— is **comparable** to KTG's actual cold re-reading. Exact wording is the editor's;
+the agent returns **direction, not rewritten copy**.
+
+## Calibration boundary
+
+Whether the agent's live verdicts truly match this fasit is judged by the operator
+(`[OPERATØR]`), not self-certified here. This fixture is the calibration target, the
+same way `fact-checker-cases.md`, `editorial-reviewer-cases.md`, and
+`persona-reviewer-cases.md` are fasits for their agents.
+
+> **Live-run note.** A live cold run on the frozen Del 4 requires (a) a Claude Code
+> session reload — a freshly added agent is not invokable until the plugin agent set
+> is rebuilt at session start — and (b) the agent run in a genuinely cold context
+> (no drafting-session history, no pivot narrative) with read access to the frozen
+> draft and web search. Until both hold, this fixture is the gold-standard of record.

tests/fixtures/language-reviewer-cases.md

@@ -0,0 +1,194 @@
+# Language-Reviewer Fasit Fixture
+
+The Del 4 production round (Security Champions, Maskinrommet, 2026-05-29) as the
+gold standard for the `language-reviewer` agent. By Step 6 the in-session persona
+resonance sweep had returned PASS across the personas and the in-session craft
+gate (`editorial-reviewer`, Step 5.5) had run — both *inside* the drafting session,
+both sharing its framing-bias. On a **cold, first-time reading of the frozen
+draft** (the F5 finding), the editor then caught Norwegian-language defects the
+in-session passes had all read straight past: a verbatim **quote error** («Vi»
+where the source said «Vi i Nav»), anglicisms, and verbatim repetitions across
+sections. Those are the fasit below: a correct `language-reviewer` run on the
+Del 4 frozen draft should surface **comparable flags**, mapped to the one axis
+with consistent severities.
+
+This file is a *fasit*, not a test harness. The structural lint lives in
+`agents/__tests__/language-reviewer-fixture.test.mjs`. Whether the agent's live
+flags actually reproduce these directions is `[GATE]`/`[OPERATØR]` — it is **not**
+self-certified here.
+
+> **The jury judges; the writer writes.** Every expected output below is
+> **direction, not rewritten copy.** A correct agent run hands back flags + a
+> severity — never edited prose. (`Foreslått retning`, not a new sentence.)
+
+> **Why this gate exists — the cold re-read.** The in-session gates (fact-check,
+> craft, persona) all ran while the drafting session's framing-bias was still in
+> the room: the same blind spots that let the author miss «Vi» vs «Vi i Nav» let
+> those gates miss it too. `language-reviewer` is run in a **cold context** with
+> no access to version history, intent, pivots, or how any gate voted — exactly so
+> it carries none of that bias. Any such framing that reaches it is **context
+> pollution** to be named and ignored. A cold Norwegian re-read catches what the
+> bias hid. That is the F5 finding made into a gate.
+
+---
+
+## The axis (the agent judges on exactly this)
+
+**Axis: norsk-språkkvalitet** (Norwegian language quality) — one axis, five
+checks. L1, L2, L5 start grep-able; L3, L4 need a read. The voice under judgment
+is a **personal chronicle**, not a saksframlegg.
+
+- **L1 — Ordrette gjentakelser** (verbatim repetition): the same distinctive
+  phrase or sentence-opening repeats mechanically across the draft (grep 3–6-word
+  phrases, then read in context).
+- **L2 — Anglisismer** (anglicisms): English calques / loan-constructions where
+  idiomatic Norwegian exists («adressere et problem», «på en daglig basis», «i
+  terms av»). Flag the calque **and name the Norwegian idiom direction.**
+- **L3 — Stivt tjenesteskriftspråk** (stiff bureaucratic register): «kanselli-stil»
+  — nominalisations, passive overload, «det vises til», agentless sentences that
+  drain the chronicle voice.
+- **L4 — Indre språklige selvmotsigelser** (language-level self-contradiction): a
+  sentence/phrase that undercuts itself, or two phrasings that cannot both be the
+  intended register/meaning. The *wording* contradicting itself — **not** the
+  argument-level logic (that is `content-reviewer`).
+- **L5 — Klang / rytme** (clang & rhythm): sentences that read badly aloud —
+  monotone cadence, every sentence the same length, a jarring word, run-ons that
+  lose the breath.
+
+## Severity (every flag carries exactly one)
+
+- **BLOCK** — misrepresents or embarrasses: a quote rendered wrong (a verbatim
+  error inside a quotation — «Vi» vs «Vi i Nav»), or a self-contradicting phrasing
+  (L4) that changes the meaning.
+- **REWORK** — a real language weakness a reader notices: a repeated phrase (L1),
+  an anglicism (L2), a bureaucratic passage (L3), a rhythm stumble (L5).
+- **NICE** — cheap polish: a single mild repetition, one slightly stiff sentence.
+
+## Direction, not copy (the boundary)
+
+Every expected output is **direction, not rewritten copy**: "§3 'adressere' —
+anglicism; use the Norwegian idiom («ta tak i»)" is the agent's job; supplying the
+rewritten sentence is not. Each flag carries a **quote or line reference.**
+
+---
+
+## The six Del 4 language points (fasit)
+
+Each case states the point the editor raised on the cold reading, the check it
+belongs to, the expected severity, and the direction a correct agent run returns.
+These are **language blind spots** — distinct from craft (`editorial-reviewer`),
+de-AI / voice (`voice-scrubber`), and reader response (`persona-reviewer`). They
+survived to the cold pass precisely because the in-session gates shared the
+author's framing-bias.
+
+### Case 1 — sitat gjengitt feil: «Vi» i stedet for «Vi i Nav» (verbatim quote error)
+
+- **Check:** L4 (language-level self-contradiction / verbatim quotation error)
+  · **Severity:** BLOCK
+- **Cold-read finding:** A quotation in the chronicle is rendered «Vi …» where the
+  source said «Vi i Nav …». The clipped quote changes who "vi" refers to — the
+  wording now misrepresents the source. (Maps to L4 as a wording-level
+  self-contradiction; the same defect could be filed under L1 as a near-verbatim
+  repetition of the source gone wrong — the agent files it once, as the BLOCK it
+  is.)
+- **Fasit / direction:** Quote misrenders «Vi i Nav» as «Vi»; restore the source
+  wording. A misquote misrepresents the piece, so BLOCK. The agent flags the
+  *wrong rendering*; it does not supply the corrected sentence.
+- **Why blind to the in-session gates:** the persona sweep measured whether the
+  passage *landed* (it did — PASS); none of the in-session gates re-checked the
+  quote against the source on a cold reading. This is the canonical F5 finding.
+
+### Case 2 — anglisisme: «adressere problemet» (anglicism)
+
+- **Check:** L2 (anglicisms) · **Severity:** REWORK
+- **Cold-read finding:** «adressere et problem» is an English calque (to *address*
+  a problem) where idiomatic Norwegian reads «ta tak i / håndtere / ta opp».
+- **Fasit / direction:** Anglicism; use the Norwegian idiom («ta tak i» /
+  «håndtere»). Name the idiom direction, do not write the sentence.
+- **Why blind:** an anglicism reads fluently to a reader inside the drafting
+  session — the calque *sounds* like normal prose until a cold ear hits it.
+
+### Case 3 — anglisisme: «på en daglig basis» (anglicism)
+
+- **Check:** L2 (anglicisms) · **Severity:** REWORK
+- **Cold-read finding:** «på en daglig basis» is a calque of *on a daily basis*;
+  idiomatic Norwegian is «daglig» / «til daglig».
+- **Fasit / direction:** Anglicism; collapse to the Norwegian adverb («daglig»).
+  Direction only.
+- **Why blind:** same mechanism as Case 2 — a second calque the in-session passes
+  read straight through. Two L2 flags is itself a signal the draft drifted into
+  English construction.
+
+### Case 4 — ordrette gjentakelser: samme frase 3× på tvers av seksjoner (verbatim repetition)
+
+- **Check:** L1 (verbatim repetition) · **Severity:** REWORK
+- **Cold-read finding:** A distinctive phrase recurs three times across §1, §4 and
+  §6 — mechanical, not load-bearing. `grep`-findable as a repeated 3–6-word
+  string.
+- **Fasit / direction:** Vary or cut the repeats; keep at most the one
+  load-bearing use. Report the count (3×).
+- **Why blind:** a reader inside the session sees each section in isolation; the
+  repetition only shows when a cold reader takes the whole draft at once. This is
+  the verbatim-repetition half of the F5 finding.
+
+### Case 5 — stivt tjenesteskriftspråk: «det vises til»-passasje i en personlig krønike (stiff bureaucratic register)
+
+- **Check:** L3 (stiff bureaucratic register / «kanselli-stil») · **Severity:**
+  REWORK
+- **Cold-read finding:** A passage slides into saksframlegg register — «det vises
+  til», nominalised, agentless, passive-stacked — inside a piece whose voice is a
+  personal chronicle. The register break drains the chronicle voice.
+- **Fasit / direction:** Kanselli-stil in a personal chronicle; restore an agent
+  and an active verb so the passage reads as the chronicle, not a memo. Direction
+  only. (This is a *language-register* defect, distinct from `voice-scrubber`'s
+  de-AI tells and from `editorial-reviewer`'s craft.)
+- **Why blind:** bureaucratic register is the author's professional default; inside
+  the session it reads as "normal," and only a cold ear hears it clash with the
+  chronicle voice.
+
+### Case 6 — klang / rytme: fem like lange setninger på rad (monotone cadence)
+
+- **Check:** L5 (clang & rhythm) · **Severity:** NICE
+- **Cold-read finding:** A run of five sentences shares the same length and a
+  near-identical opening — a monotone cadence that reads flat aloud. Chronicle
+  prose has a varied cadence; this passage loses it.
+- **Fasit / direction:** Break the monotone — vary one or two sentence lengths /
+  openings so the passage breathes. NICE: noticeable on a read-aloud, not
+  load-bearing. `grep`/scan-findable (same-length run, repeated opening).
+- **Why blind:** rhythm is heard, not seen; a silent in-session read past a fluent
+  passage never trips on it. A cold read-aloud does.
+
+---
+
+## Expected aggregate (what a correct run looks like)
+
+- **Total flags:** 6 (well within the ≤10 cap — no suppression needed).
+- **By check:** L1 = 1 (Case 4) · L2 = 2 (Cases 2 + 3) · L3 = 1 (Case 5) ·
+  L4 = 1 (Case 1) · L5 = 1 (Case 6).
+- **By severity:** BLOCK = 1 (Case 1, the quote error) · REWORK = 4 (Cases 2, 3,
+  4, 5) · NICE = 1 (Case 6).
+- **All six are language blind spots** — none is a craft defect (editorial), a
+  de-AI / voice defect (voice-scrubber), an argument defect (content-reviewer), a
+  factual defect (fact-reviewer), or a resonance defect (persona). They survived
+  to the cold pass because the in-session gates shared the author's framing-bias;
+  the cold Norwegian re-read is what caught them.
+
+A run that reproduces ~these six directions, on ~these checks, with ~these
+severities, is **comparable** to the editor's actual cold reading of Del 4 — the
+acceptance bar. Exact wording is the editor's; the agent returns direction, never
+copy.
+
+## Calibration boundary
+
+Whether the agent's live flags truly match this fasit is judged by the operator
+(`[OPERATØR]`), not self-certified here. This fixture is the calibration target,
+the same way `editorial-reviewer-cases.md`, `persona-reviewer-cases.md` and
+`fact-checker-cases.md` are fasits for their agents.
+
+> **Live-run note.** A live run on the Del 4 frozen draft requires (a) a Claude
+> Code session reload — a freshly added agent is not invokable until the plugin
+> agent set is rebuilt at session start — and (b) read access to the frozen Del 4
+> draft in the Maskinrommet series folder. Critically, the live run must be a
+> **cold context**: no session history, no version numbers, no intent narrative —
+> only the prompt, the frozen draft path, and the writing contract. Until both
+> hold, this fixture is the gold-standard of record.

tests/fixtures/persona-reviewer-cases.md

@@ -0,0 +1,106 @@
+# Persona-Reviewer Fasit Fixture
+
+One reader persona, one sample draft, the six judging axes, and the two review
+modes — used to sanity-check the `persona-reviewer` agent. This is a *fasit*,
+not a test harness. The structural lint lives in
+`agents/__tests__/persona-reviewer-fixture.test.mjs`. Whether the agent's live
+flags actually match the directions below is `[GATE]`/`[OPERATØR]` — it is not
+self-certified here.
+
+**The jury judges; the editor writes.** Every expected output in this fixture is
+**direction, not rewritten copy**. A correct agent run hands back flags and a
+verdict — never edited text.
+
+---
+
+## Persona under review (primær)
+
+Drawn from `config/personas.template.md` — the primær Linjeleder. Field keys are
+lowercase to match the library contract.
+
+- **rolle** — Mellomleder med fag- og personalansvar i offentlig virksomhet;
+  skal beslutte om og hvordan AI tas i bruk i egen enhet, uten dyp teknisk
+  bakgrunn.
+- **avkobler** — Teknisk dypdykk uten «hva betyr dette for meg og mine»;
+  frykt-retorikk; abstrakt policy; språk som forutsetter at hen kan koden.
+- **overbeviser** — Konkrete eksempler fra arbeidshverdagen, et klart ansvars- og
+  dømmekraftsbilde, og en leder-takeaway hen kan handle på allerede i morgen.
+- **ekspertise** — Lav-til-middels teknisk; høy på ledelse og forvaltning.
+  Trenger oversettelse, ikke nedlatenhet.
+- **sjargong** — Lav toleranse for teknisk sjargong; setter pris på presise,
+  hverdagsnære formuleringer.
+
+> Primær trumfer: a primær NO is not accepted — the text is revised until this
+> reader reaches a clean JA. A sekundær NO from a role or expertise ceiling is a
+> SIGNAL the gate works, not a defect.
+
+---
+
+## Sample-tekst
+
+The draft excerpt this persona reads, read-only. Deliberately mixed: a workable
+human angle ("you don't outsource judgment") buried under one wall of jargon —
+exactly the case where the jury should flag direction without touching the copy.
+
+> Transformatorarkitekturen vår utnytter selvoppmerksomhets-mekanismer over en
+> 175-milliarders parametermodell for å maksimere inferens-gjennomstrømning på
+> tvers av distribuerte GPU-clustere. Men det egentlige poenget er enklere: en
+> språkmodell tar ikke beslutningen for deg. Den foreslår — du svarer for
+> resultatet. Dømmekraften kan ikke settes ut. Spørsmålet er ikke om verktøyet
+> er smart nok, men om du fortsatt eier valget når det teller.
+
+---
+
+## The six axes
+
+The persona-reviewer judges the sample on exactly six axes and returns **at most
+five flags** as direction (the sixth that passes cleanest is simply not flagged):
+
+1. **Krok** — does the hook hold for THIS reader in the first two lines? Here:
+   IKKE — the opening jargon wall ("transformatorarkitektur… inferens-
+   gjennomstrømning") hits `avkobler` head-on; the linjeleder stops reading
+   before the real point.
+2. **Resonans** — does the central point land for this reader? DELVIS — the
+   "judgment can't be outsourced" core is exactly their concern, but it arrives
+   too late to land.
+3. **Tone** — right for this reader (no condescension, no fear-rhetoric)? LØST —
+   tone is respectful and non-alarmist once past the opening.
+4. **Troverdighet** — does the reader believe it? DELVIS — the closing claim is
+   credible but abstract; no lived example from a leader's workday to anchor it.
+5. **Leder-takeaway** — one concrete thing this reader can act on tomorrow?
+   IKKE — there is an insight but no action the linjeleder can take in their
+   own unit.
+6. **Lengde/driv** — does it keep moving or sag? DELVIS — the front half drags
+   under the jargon; the back half drives well.
+
+Each flag is **direction**, not a rewrite: "the hook hits `avkobler` — open on
+the decision the leader owns" is correct; supplying the new opening line is not.
+
+---
+
+## The two modes
+
+Both modes run the same persona but differ in scope and output.
+
+### Resonans-modus (before lock)
+
+Runs at the newsletter pipeline's pre-lock resonance sweep. Judges all six axes
+and returns ≤5 flags as direction, each tracked **LØST / DELVIS / IKKE**. The
+primær must reach a clean JA before the draft is locked. For this sample, the
+primær verdict is **NEI** (Krok + Leder-takeaway both IKKE) → REWORK, with the
+two IKKE flags as the priority directions.
+
+### Konverter-modus (after lock)
+
+Runs at the post-lock conversion sweep. Judges the **hook only**, binary:
+«would YOU click?» **JA / NEI**. No axis scoring, no copy — just the click
+verdict and a single reason. For this sample's current hook the verdict is
+**NEI** — "I'd scroll past; the first line is machinery, not me."
+
+---
+
+## Convergence loop
+
+Re-run per persona until the primær returns a clean JA. Each flag is re-judged
+LØST / DELVIS / IKKE against the editor's revision. The jury never writes the
+fix — it only re-judges whether the revision now lands.

tests/language-reviewer-fixture.test.mjs

@@ -0,0 +1,80 @@
+import { describe, test } from 'node:test';
+import assert from 'node:assert/strict';
+import { readFileSync } from 'node:fs';
+import { fileURLToPath } from 'node:url';
+
+// Lint-test for the language-reviewer fasit fixture.
+// Mirrors the structure-only discipline of editorial-reviewer-fixture.test.mjs,
+// persona-reviewer-fixture.test.mjs and fact-checker-fixture.test.mjs: this test
+// asserts the SHAPE of the fixture — the one judging axis (norsk-språkkvalitet),
+// all five checks (L1–L5), the three severities, the six Del 4 cases that form
+// the gold standard, the direction-not-copy boundary, and the cold-reader /
+// context-isolation principle. Whether the agent's live flags actually reproduce
+// the fasit directions is [GATE]/[OPERATØR], never self-certified here.
+
+const FIXTURE_PATH = fileURLToPath(
+  new URL('./fixtures/language-reviewer-cases.md', import.meta.url)
+);
+
+const fixture = readFileSync(FIXTURE_PATH, 'utf8');
+
+// The five checks of the one axis.
+const CHECKS = ['L1', 'L2', 'L3', 'L4', 'L5'];
+
+// The single axis name (Norwegian, as the agent and the writing contract use it).
+const AXIS = 'norsk-språkkvalitet';
+
+// The three-rung severity scale.
+const SEVERITIES = ['BLOCK', 'REWORK', 'NICE'];
+
+describe('language-reviewer fixture structure', () => {
+  test('names the judging axis (norsk-språkkvalitet)', () => {
+    assert.ok(
+      new RegExp(AXIS, 'i').test(fixture),
+      `fixture must name the axis "${AXIS}"`
+    );
+  });
+
+  test('documents all five checks (L1–L5)', () => {
+    for (const check of CHECKS) {
+      assert.ok(
+        fixture.includes(check),
+        `fixture must reference the check "${check}"`
+      );
+    }
+  });
+
+  test('defines the three-rung severity scale', () => {
+    for (const sev of SEVERITIES) {
+      assert.ok(
+        fixture.includes(sev),
+        `fixture must define the severity "${sev}"`
+      );
+    }
+  });
+
+  test('documents the six Del 4 cases', () => {
+    const cases = fixture.match(/^###\s+Case\s+\d+\b/gim) || [];
+    assert.equal(
+      cases.length,
+      6,
+      `fixture must document exactly 6 Del 4 cases (found ${cases.length})`
+    );
+  });
+
+  test('keeps the jury-judges-writer-writes boundary (direction, not copy)', () => {
+    assert.ok(
+      /direction, not rewritten copy/i.test(fixture),
+      'fixture must state the direction-not-copy boundary'
+    );
+  });
+
+  test('documents the cold-reader / context-isolation principle', () => {
+    assert.ok(
+      /cold/i.test(fixture) &&
+        /(context pollution|framing-bias)/i.test(fixture),
+      'fixture must document the cold-reader / context-isolation principle ' +
+        '(context pollution / framing-bias)'
+    );
+  });
+});

tests/persona-reviewer-fixture.test.mjs

@@ -0,0 +1,69 @@
+import { describe, test } from 'node:test';
+import assert from 'node:assert/strict';
+import { readFileSync } from 'node:fs';
+import { fileURLToPath } from 'node:url';
+
+// Lint-test for the persona-reviewer fasit fixture.
+// Mirrors the structure-only discipline of state-updater.test.mjs and
+// fact-checker-fixture.test.mjs: this test asserts the SHAPE of the fixture —
+// one reader persona carrying all five library fields, a non-empty sample
+// draft, the six judging axes, and both review modes documented. Whether the
+// agent's live flags actually match the fasit directions is [GATE]/[OPERATØR],
+// never self-certified here.
+
+const FIXTURE_PATH = fileURLToPath(
+  new URL('./fixtures/persona-reviewer-cases.md', import.meta.url)
+);
+
+const fixture = readFileSync(FIXTURE_PATH, 'utf8');
+
+// The five persona field keys, lowercase to match config/personas.template.md.
+const PERSONA_FIELDS = ['rolle', 'avkobler', 'overbeviser', 'ekspertise', 'sjargong'];
+
+// The six judging axes (plan Step 6 / fasit §6.3).
+const AXES = [
+  'Krok',           // hook holds?
+  'Resonans',       // does the point land?
+  'Tone',           // tone fit for this reader
+  'Troverdighet',   // credibility
+  'Leder-takeaway', // leader takeaway + concrete action
+  'Lengde',         // length / drive
+];
+
+// Both review modes must be documented (resonance + conversion).
+const MODES = ['resonans', 'konverter'];
+
+describe('persona-reviewer fixture structure', () => {
+  test('documents one persona with all five library fields', () => {
+    for (const field of PERSONA_FIELDS) {
+      assert.ok(
+        new RegExp(`\\*\\*${field}\\*\\*`).test(fixture),
+        `fixture must document the persona field **${field}**`
+      );
+    }
+  });
+
+  test('contains a non-empty sample-text section', () => {
+    const m = fixture.match(/##\s+Sample-tekst\b([\s\S]*?)(?=\n##\s|$)/i);
+    assert.ok(m, 'fixture must have a "## Sample-tekst" section');
+    assert.ok(
+      m[1].trim().length > 80,
+      'the sample-text section must contain a real draft excerpt, not a stub'
+    );
+  });
+
+  test('documents all six judging axes', () => {
+    for (const axis of AXES) {
+      assert.ok(fixture.includes(axis), `fixture must name the axis "${axis}"`);
+    }
+  });
+
+  test('documents both review modes (resonance + conversion)', () => {
+    for (const mode of MODES) {
+      assert.ok(
+        new RegExp(mode, 'i').test(fixture),
+        `fixture must document the "${mode}" mode`
+      );
+    }
+  });
+});