Merge remote-tracking branch 'origin/main' into ponytail-inspiration-review

# Conflicts:
#	CHANGELOG.md
#	TODOS.md
#	VERSION
#	docs/TESTING_INTERNALS.md
#	package.json
#	scripts/test-free-shards.ts
#	test/helpers/llm-judge.ts
#	test/helpers/touchfiles-data.ts

test/helpers/budget-override.test.ts

@@ -8,16 +8,28 @@
  * timestamp + scope + reason + CI provenance.
  */
 
-import { describe, test, expect, beforeEach } from 'bun:test';
+import { describe, test, expect, beforeAll, beforeEach, afterAll } from 'bun:test';
 import * as fs from 'fs';
 import * as path from 'path';
 import * as os from 'os';
 import { logBudgetOverride } from './budget-override';
 
 const TMP_HOME = fs.mkdtempSync(path.join(os.tmpdir(), 'budget-override-test-'));
-process.env.GSTACK_HOME = TMP_HOME;
 const AUDIT_PATH = path.join(TMP_HOME, 'analytics', 'spend-overrides.jsonl');
 
+// GSTACK_HOME is scoped to this file's execution window (beforeAll/afterAll),
+// never set at module load: bun evaluates sibling modules before running
+// their tests, so a module-scope assignment leaks into every other file in
+// the shard process (pinned by test/gstack-home-module-scope.test.ts).
+const ORIGINAL_GSTACK_HOME = process.env.GSTACK_HOME;
+beforeAll(() => {
+  process.env.GSTACK_HOME = TMP_HOME;
+});
+afterAll(() => {
+  if (ORIGINAL_GSTACK_HOME === undefined) delete process.env.GSTACK_HOME;
+  else process.env.GSTACK_HOME = ORIGINAL_GSTACK_HOME;
+});
+
 describe('logBudgetOverride', () => {
   beforeEach(() => {
     // Start each test with a clean audit file

test/helpers/e2e-helpers.ts

@@ -61,7 +61,55 @@ export function computeDiffSelection(
   return selection.selected;
 }
 
-export let selectedTests: string[] | null = computeDiffSelection(E2E_TOUCHFILES, 'E2E'); // null = run all
+/**
+ * Parse the sharded paid runner's precomputed selection (EVALS_SELECTION_JSON,
+ * written by serializePaidDiffSelection in scripts/test-paid-shards.ts).
+ * Returns { selected: null } for run-all. THROWS on any parse/shape failure —
+ * resolveModuleSelection turns that into a fail-open local recompute.
+ */
+export function parseEvalsSelectionJson(raw: string): { selected: string[] | null; reason: string } {
+  const parsed: unknown = JSON.parse(raw);
+  if (!parsed || typeof parsed !== 'object' || Array.isArray(parsed)) throw new Error('not an object');
+  const { selected, reason } = parsed as { selected?: unknown; reason?: unknown };
+  if (selected !== null
+    && !(Array.isArray(selected) && selected.every((s) => typeof s === 'string'))) {
+    throw new Error('selected must be null or string[]');
+  }
+  return {
+    selected: selected as string[] | null,
+    reason: typeof reason === 'string' ? reason : 'parent selection',
+  };
+}
+
+/**
+ * Resolve the module-load E2E selection: prefer the parent shard runner's
+ * EVALS_SELECTION_JSON — skipping this module's own git walk and, when
+ * touchfiles-data.ts is in the diff, the per-child bun subprocess that
+ * evaluates the old data file (test-selection.ts map-diff path, one per
+ * shard). On ANY parse/shape failure, fall back to computing locally
+ * (fail-open preserved) with one stderr warning.
+ */
+export function resolveModuleSelection(
+  raw: string | undefined,
+  compute: () => string[] | null,
+  stderrWrite: (text: string) => void = (text) => process.stderr.write(text),
+): string[] | null {
+  if (raw) {
+    try {
+      const { selected, reason } = parseEvalsSelectionJson(raw);
+      stderrWrite(`\nE2E selection (parent-propagated: ${reason}): ${selected === null ? 'all' : selected.length} tests\n`);
+      return selected;
+    } catch (err) {
+      stderrWrite(`WARNING: malformed EVALS_SELECTION_JSON (${err instanceof Error ? err.message : String(err)}) — falling back to local selection\n`);
+    }
+  }
+  return compute();
+}
+
+export let selectedTests: string[] | null = resolveModuleSelection(
+  evalsEnabled ? process.env.EVALS_SELECTION_JSON : undefined,
+  () => computeDiffSelection(E2E_TOUCHFILES, 'E2E'),
+); // null = run all
 
 // EVALS_TIER: filter tests by tier after diff-based selection.
 // 'gate' = gate tests only (CI default — blocks merge)

test/helpers/eval-budgets.ts

@@ -0,0 +1,43 @@
+/**
+ * Timeout policy for paid tests — five tiers instead of hand-tuned sprawl.
+ *
+ * Before this module the paid suite carried 46×300s, 46×120s, 44×360s,
+ * 44×180s, 27×240s, 19×150s, 13×420s, 12×600s, 7×700s… hand-ratcheted
+ * per test, several inflated to paper over the old 40-way in-shard
+ * concurrency (session startup queued behind 39 siblings and ate the
+ * budget before turn one — dead with the sharded runner's 1-file-per-shard
+ * model). Pick the tier that matches the test's SHAPE; escape-hatch raw
+ * literals stay legal with a justification comment (count-ratcheted by
+ * test/eval-budgets-policy.test.ts).
+ *
+ * Every tier must fit inside the lane walls — pinned by the fit test in
+ * test/eval-budgets-policy.test.ts against the sharded runner's
+ * DEFAULT_SHARD_TIMEOUT_MS. Budget above the wall is fiction, not headroom.
+ */
+
+/** LLM-judge call over an existing capture (no agent session). */
+export const JUDGE_MS = 120_000;
+
+/** One `claude -p` / SDK capture, bounded turns. */
+export const CAPTURE_MS = 300_000;
+
+/** Multi-capture or long multi-turn `claude -p` flows. */
+export const CAPTURE_LONG_MS = 600_000;
+
+/** Interactive real-PTY flow (spawn + skill + a few interactions). */
+export const PTY_MS = 900_000;
+
+/**
+ * Chained/judged PTY observation — the ceiling tier. 1200s leaves the
+ * 1800s shard wall real overhead; anything that genuinely needs more
+ * should be SPLIT, not budgeted past the wall.
+ */
+export const PTY_LONG_MS = 1_200_000;
+
+export const ALL_TIERS = {
+  JUDGE_MS,
+  CAPTURE_MS,
+  CAPTURE_LONG_MS,
+  PTY_MS,
+  PTY_LONG_MS,
+} as const;

test/helpers/llm-judge.ts

@@ -11,6 +11,8 @@
 
 import Anthropic from '@anthropic-ai/sdk';
 
+import { resolveEvalModel } from '../../lib/eval-model';
+
 export interface JudgeScore {
   clarity: number;       // 1-5
   completeness: number;  // 1-5
@@ -52,9 +54,10 @@ export interface RecommendationScore {
 
 /**
  * Call an Anthropic model with a prompt, extract JSON response.
- * Retries once on 429 rate limit errors. Defaults to Sonnet 4.6 for
- * existing callers; pass a model id (e.g. claude-haiku-4-5-20251001)
- * for cheaper bounded judgments like judgeRecommendation.
+ * Jittered exponential backoff over three 429 retries. Model resolves via
+ * lib/eval-model's `judge` kind (Sonnet default); pass a model id
+ * (e.g. claude-haiku-4-5-20251001) for cheaper bounded judgments like
+ * judgeRecommendation.
  */
 // Default judge model: Sonnet. D1a tried Haiku 4.5 here and the first live
 // run regressed the doc-rubric family — a controlled A/B on the identical
@@ -68,27 +71,42 @@ export interface RecommendationScore {
 // distill — see lib/eval-model.ts).
 export async function callJudge<T>(
   prompt: string,
-  model: string = process.env.GSTACK_EVAL_MODEL_JUDGE || 'claude-sonnet-4-6',
+  model?: string,
   opts?: { temperature?: number; max_tokens?: number },
 ): Promise<T> {
+  // Routed through the documented single resolution point: explicit arg >
+  // GSTACK_EVAL_MODEL_JUDGE > GSTACK_EVAL_MODEL > sonnet default. The old
+  // inline `GSTACK_EVAL_MODEL_JUDGE || sonnet` silently ignored the global
+  // GSTACK_EVAL_MODEL override that every other eval call site honors.
+  // opts (temperature/max_tokens) exist for bounded judgments like armJudge;
+  // defaults preserve prior behavior.
+  const resolvedModel = resolveEvalModel('judge', model);
   const client = new Anthropic();
 
   const makeRequest = () => client.messages.create({
-    model,
+    model: resolvedModel,
     max_tokens: opts?.max_tokens ?? 1024,
     ...(opts?.temperature !== undefined ? { temperature: opts.temperature } : {}),
     messages: [{ role: 'user', content: prompt }],
   });
 
+  // 429s under CI concurrency: jittered exponential backoff over 3 retries
+  // (~1s/4s/16s + jitter), honoring the server's retry-after when present.
+  // The old single fixed 1s retry lost races reliably at 40-way concurrency.
   let response;
-  try {
-    response = await makeRequest();
-  } catch (err: any) {
-    if (err.status === 429) {
-      await new Promise(r => setTimeout(r, 1000));
+  let attempt = 0;
+  for (;;) {
+    try {
       response = await makeRequest();
-    } else {
-      throw err;
+      break;
+    } catch (err: any) {
+      if (err?.status !== 429 || attempt >= 3) throw err;
+      const retryAfterSecs = Number(err?.headers?.['retry-after']);
+      const baseMs = Number.isFinite(retryAfterSecs) && retryAfterSecs > 0
+        ? retryAfterSecs * 1000
+        : 1000 * 4 ** attempt;
+      await new Promise((r) => setTimeout(r, baseMs + Math.random() * 500));
+      attempt += 1;
     }
   }
 

test/helpers/paid-test-set.ts

@@ -11,12 +11,20 @@ import { matchGlob } from './touchfiles';
 
 /** The exact globs package.json's `test:gate` passes to `bun test`. */
 export const PAID_TEST_GLOBS = [
-  'test/skill-llm-eval.test.ts',
+  // skill-llm-eval* (not just the base file): skill-llm-eval-spec.test.ts
+  // fell outside the exact glob and could never run in any lane.
+  'test/skill-llm-eval*.test.ts',
   'test/skill-e2e-*.test.ts',
   'test/skill-routing-e2e.test.ts',
-  'test/codex-e2e.test.ts',
-  'test/codex-e2e-sol-scope.test.ts',
+  // codex-e2e* (was two exact names): codex-e2e-plan-format.test.ts and
+  // codex-e2e-recommendation-substance.test.ts were API-spending orphans —
+  // outside these globs they self-skipped in the free suite AND never
+  // entered the paid census. The same bug class as the deleted pre-split
+  // monolith (see test/paid-shards.test.ts's regression pin).
+  'test/codex-e2e*.test.ts',
   'test/gemini-e2e.test.ts',
+  'test/llm-judge-recommendation.test.ts',
+  'test/carve-section-loading.test.ts',
 ] as const;
 
 /** True when a repo-relative path (either slash style) is a paid test file. */

test/helpers/periodic-exclude-data.ts

@@ -0,0 +1,34 @@
+/**
+ * Periodic-lane exclusions — LITERALS ONLY (own file, deliberately NOT in
+ * touchfiles-data.ts: that file is evaluated standalone by map-diff against
+ * old git versions, and its contract must not grow unrelated exports).
+ *
+ * The weekly periodic CI lane runs EVERY periodic-tier file (EVALS_ALL=1) so
+ * tests can't rot invisibly — the coverage contract. A file lands here only
+ * when running it weekly is KNOWN waste (documented-red or requires manual
+ * hardware), and every entry must carry a tracking pointer with a re-entry
+ * condition, so an exclusion is a decision with an owner, not a place tests
+ * go to die. Pinned by test/periodic-exclude-policy.test.ts: entries must
+ * name real files and carry non-empty reason + tracking.
+ *
+ * Removing an entry re-activates the file on the next weekly run — that IS
+ * the re-entry mechanism.
+ */
+export const PERIODIC_CI_EXCLUDE: Record<string, { reason: string; tracking: string }> = {
+  'test/skill-e2e-ship-idempotency.test.ts': {
+    reason:
+      'documented-red: the PTY child sits at the Claude Code welcome screen for the full budget '
+      + '(readiness/typing race vs CLI 2.1.x); never green since it was born in v1.63',
+    tracking: 'TODOS.md "periodic tier — three documented-red tests need structural repair" (1 of 3 resolved: sidebar trio already deleted)',
+  },
+  'test/skill-e2e-brain-privacy-gate.test.ts': {
+    reason:
+      'documented-red: the artifacts-sync stop-gate preconditions do not survive the hermetic env '
+      + 'even with per-test HOME/GSTACK_HOME injection; never green anywhere',
+    tracking: 'TODOS.md "periodic tier — three documented-red tests need structural repair"',
+  },
+  'test/skill-e2e-ios.test.ts': {
+    reason: 'requires a live iOS device/simulator toolchain (xcodebuild, devicectl) — manual hardware, not a CI runner capability',
+    tracking: 'TODOS.md "skill-e2e-ios CI story" (device/runner decision)',
+  },
+};

test/helpers/run-bin.test.ts

@@ -0,0 +1,39 @@
+import { describe, expect, test } from 'bun:test';
+import * as fs from 'node:fs';
+import * as os from 'node:os';
+import * as path from 'node:path';
+
+import { runBin } from './run-bin';
+
+describe('runBin', () => {
+  test('captures status/stdout/stderr with utf-8 shaping', () => {
+    const r = runBin('sh', ['-c', 'printf out; printf err >&2; exit 3']);
+    expect(r).toEqual({ status: 3, stdout: 'out', stderr: 'err' });
+  });
+
+  test('gstackHome sets both GSTACK_HOME and GSTACK_STATE_DIR (config precedence)', () => {
+    const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'run-bin-'));
+    try {
+      const r = runBin('sh', ['-c', 'printf "%s|%s" "$GSTACK_HOME" "$GSTACK_STATE_DIR"'], { gstackHome: dir });
+      expect(r.stdout).toBe(`${dir}|${dir}`);
+    } finally {
+      fs.rmSync(dir, { recursive: true, force: true });
+    }
+  });
+
+  test('env undefined deletes a key; input feeds stdin; trim shapes output', () => {
+    const r = runBin('sh', ['-c', 'cat; printf "  padded  "; test -z "$LANG" && printf noLANG >&2'], {
+      env: { LANG: undefined },
+      input: 'piped|',
+      trim: true,
+    });
+    // trim shapes the ENDS of the whole stream; interior whitespace stays.
+    expect(r.stdout).toBe('piped|  padded');
+    expect(r.stderr).toBe('noLANG');
+  });
+
+  test('spawn failure yields -1, never a fake success', () => {
+    const r = runBin('/definitely/not/a/binary');
+    expect(r.status).toBe(-1);
+  });
+});

test/helpers/run-bin.ts

@@ -0,0 +1,71 @@
+/**
+ * Shared spawnSync wrapper for free unit tests that shell out to bin/
+ * scripts. Before this helper, ~36 test files each carried a near-identical
+ * local `run()` (spawnSync + utf-8 + {status, stdout, stderr} normalization)
+ * differing only in env composition, cwd, and timeout — drift-prone copies
+ * of one idea.
+ *
+ * Free-test-only by design: nothing under the paid globs should import this,
+ * so it never becomes a de facto global touchfile (paid selection is owned
+ * by test/helpers/e2e-helpers.ts and friends).
+ */
+import { spawnSync } from 'node:child_process';
+
+export interface RunBinResult {
+  status: number;
+  stdout: string;
+  stderr: string;
+}
+
+export interface RunBinOptions {
+  cwd?: string;
+  /** Merged over process.env (an `undefined` value deletes the key). */
+  env?: Record<string, string | undefined>;
+  /**
+   * Isolation shorthand: sets GSTACK_HOME + GSTACK_STATE_DIR (gstack-config
+   * precedence is GSTACK_HOME > GSTACK_STATE_DIR > $HOME/.gstack, so both
+   * must move to isolate from the operator's real ~/.gstack).
+   */
+  gstackHome?: string;
+  /** Also move $HOME (bins that write $HOME-anchored files, e.g. artifacts-remote pointers). */
+  home?: string;
+  input?: string;
+  /** Default 60s — a wedged bin fails the test, never the shard wall. */
+  timeoutMs?: number;
+  maxBuffer?: number;
+  /** Trim stdout/stderr (config-getter style bins). */
+  trim?: boolean;
+}
+
+export function runBin(command: string, args: string[] = [], opts: RunBinOptions = {}): RunBinResult {
+  const env: Record<string, string | undefined> = { ...process.env, ...opts.env };
+  if (opts.gstackHome !== undefined) {
+    env.GSTACK_HOME = opts.gstackHome;
+    env.GSTACK_STATE_DIR = opts.gstackHome;
+  }
+  if (opts.home !== undefined) env.HOME = opts.home;
+  for (const key of Object.keys(env)) {
+    if (env[key] === undefined) delete env[key];
+  }
+
+  const result = spawnSync(command, args, {
+    cwd: opts.cwd,
+    env: env as Record<string, string>,
+    encoding: 'utf-8',
+    input: opts.input,
+    timeout: opts.timeoutMs ?? 60_000,
+    maxBuffer: opts.maxBuffer,
+  });
+
+  const shape = (text: string | null | undefined): string => {
+    const value = text ?? '';
+    return opts.trim ? value.trim() : value;
+  };
+  return {
+    // -1 for spawn failure/kill mirrors the strictest of the old locals: a
+    // null status must never alias a real exit code.
+    status: result.status ?? -1,
+    stdout: shape(result.stdout),
+    stderr: shape(result.stderr),
+  };
+}

test/helpers/touchfiles-data.ts

@@ -22,8 +22,8 @@
  */
 export const E2E_TOUCHFILES: Record<string, string[]> = {
   // Browse core (+ test-server dependency)
-  'browse-basic':    ['browse/src/**', 'browse/test/test-server.ts'],
-  'browse-snapshot': ['browse/src/**', 'browse/test/test-server.ts'],
+  'browse-basic':    ['browse/src/**', 'browse/test/test-server.ts', 'test/skill-e2e-bws.test.ts'],
+  'browse-snapshot': ['browse/src/**', 'browse/test/test-server.ts', 'test/skill-e2e-bws.test.ts'],
 
   // Hermetic isolation canaries (hermetic-env.ts is also a GLOBAL touchfile;
   // these entries exist so the canaries themselves stay tier-classified)
@@ -37,21 +37,21 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
   'first-task-scaffold': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'bin/gstack-first-task-detect', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'test/skill-e2e-first-task-scaffold.test.ts', 'test/helpers/session-runner.ts'],
 
   // SKILL.md setup + preamble (depend on ROOT SKILL.md + gen-skill-docs)
-  'skillmd-setup-discovery':  ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
-  'skillmd-no-local-binary':  ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
-  'skillmd-outside-git':      ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
+  'skillmd-setup-discovery':  ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-bws.test.ts'],
+  'skillmd-no-local-binary':  ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-bws.test.ts'],
+  'skillmd-outside-git':      ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-bws.test.ts'],
 
-  'session-awareness':        ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
-  'operational-learning':     ['scripts/resolvers/preamble.ts', 'bin/gstack-learnings-log'],
+  'session-awareness':        ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-bws.test.ts'],
+  'operational-learning':     ['scripts/resolvers/preamble.ts', 'bin/gstack-learnings-log', 'test/skill-e2e-bws.test.ts'],
 
   // QA (+ test-server dependency)
-  'qa-quick':       ['qa/**', 'browse/src/**', 'browse/test/test-server.ts'],
-  'qa-b6-static':   ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/helpers/llm-judge.ts', 'browse/test/fixtures/qa-eval.html', 'test/fixtures/qa-eval-ground-truth.json'],
-  'qa-b7-spa':      ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/helpers/llm-judge.ts', 'browse/test/fixtures/qa-eval-spa.html', 'test/fixtures/qa-eval-spa-ground-truth.json'],
-  'qa-b8-checkout': ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/helpers/llm-judge.ts', 'browse/test/fixtures/qa-eval-checkout.html', 'test/fixtures/qa-eval-checkout-ground-truth.json'],
-  'qa-only-no-fix': ['qa-only/**', 'qa/templates/**'],
-  'qa-fix-loop':    ['qa/**', 'browse/src/**', 'browse/test/test-server.ts'],
-  'qa-bootstrap':   ['qa/**', 'ship/**'],
+  'qa-quick':       ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/skill-e2e-qa-workflow.test.ts'],
+  'qa-b6-static':   ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/helpers/llm-judge.ts', 'browse/test/fixtures/qa-eval.html', 'test/fixtures/qa-eval-ground-truth.json', 'test/skill-e2e-qa-bugs.test.ts'],
+  'qa-b7-spa':      ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/helpers/llm-judge.ts', 'browse/test/fixtures/qa-eval-spa.html', 'test/fixtures/qa-eval-spa-ground-truth.json', 'test/skill-e2e-qa-bugs.test.ts'],
+  'qa-b8-checkout': ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/helpers/llm-judge.ts', 'browse/test/fixtures/qa-eval-checkout.html', 'test/fixtures/qa-eval-checkout-ground-truth.json', 'test/skill-e2e-qa-bugs.test.ts'],
+  'qa-only-no-fix': ['qa-only/**', 'qa/templates/**', 'test/skill-e2e-qa-workflow.test.ts'],
+  'qa-fix-loop':    ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/skill-e2e-qa-workflow.test.ts'],
+  'qa-bootstrap':   ['qa/**', 'ship/**', 'test/skill-e2e-qa-workflow.test.ts'],
 
   // Review
   'review-sql-injection':     ['review/**', 'test/fixtures/review-eval-vuln.rb', 'test/skill-e2e-review.test.ts'],
@@ -60,29 +60,29 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
   'review-design-lite':       ['review/**', 'test/fixtures/review-eval-design-slop.*', 'test/skill-e2e-review.test.ts'],
 
   // Review Army (specialist dispatch)
-  'review-army-migration-safety': ['review/**', 'scripts/resolvers/review-army.ts', 'bin/gstack-diff-scope'],
-  'review-army-perf-n-plus-one':  ['review/**', 'scripts/resolvers/review-army.ts', 'bin/gstack-diff-scope'],
-  'review-army-delivery-audit':   ['review/**', 'scripts/resolvers/review.ts', 'scripts/resolvers/review-army.ts'],
-  'review-army-quality-score':    ['review/**', 'scripts/resolvers/review-army.ts'],
-  'review-army-json-findings':    ['review/**', 'scripts/resolvers/review-army.ts'],
-  'review-army-red-team':         ['review/**', 'scripts/resolvers/review-army.ts'],
+  'review-army-migration-safety': ['review/**', 'scripts/resolvers/review-army.ts', 'bin/gstack-diff-scope', 'test/skill-e2e-review-army.test.ts'],
+  'review-army-perf-n-plus-one':  ['review/**', 'scripts/resolvers/review-army.ts', 'bin/gstack-diff-scope', 'test/skill-e2e-review-army.test.ts'],
+  'review-army-delivery-audit':   ['review/**', 'scripts/resolvers/review.ts', 'scripts/resolvers/review-army.ts', 'test/skill-e2e-review-army.test.ts'],
+  'review-army-quality-score':    ['review/**', 'scripts/resolvers/review-army.ts', 'test/skill-e2e-review-army.test.ts'],
+  'review-army-json-findings':    ['review/**', 'scripts/resolvers/review-army.ts', 'test/skill-e2e-review-army.test.ts'],
+  'review-army-red-team':         ['review/**', 'scripts/resolvers/review-army.ts', 'test/skill-e2e-review-army.test.ts'],
   'review-army-simplification':   ['review/**', 'scripts/resolvers/review-army.ts', 'test/fixtures/review-army-overbuild.js', 'test/fixtures/review-army-lean-complete.js', 'test/skill-e2e-review-army.test.ts'],
   'review-army-simplification-precision': ['review/**', 'scripts/resolvers/review-army.ts', 'test/fixtures/review-army-overbuild.js', 'test/fixtures/review-army-lean-complete.js', 'test/skill-e2e-review-army.test.ts'],
-  'review-army-consensus':        ['review/**', 'scripts/resolvers/review-army.ts'],
+  'review-army-consensus':        ['review/**', 'scripts/resolvers/review-army.ts', 'test/skill-e2e-review-army.test.ts'],
 
   // Office Hours
-  'office-hours-spec-review':     ['office-hours/**', 'scripts/gen-skill-docs.ts'],
-  'office-hours-forcing-energy':  ['office-hours/**', 'scripts/resolvers/preamble.ts', 'test/fixtures/mode-posture/**', 'test/helpers/llm-judge.ts'],
-  'office-hours-builder-wildness': ['office-hours/**', 'scripts/resolvers/preamble.ts', 'test/fixtures/mode-posture/**', 'test/helpers/llm-judge.ts'],
+  'office-hours-spec-review':     ['office-hours/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-plan.test.ts'],
+  'office-hours-forcing-energy':  ['office-hours/**', 'scripts/resolvers/preamble.ts', 'test/fixtures/mode-posture/**', 'test/helpers/llm-judge.ts', 'test/skill-e2e-office-hours.test.ts'],
+  'office-hours-builder-wildness': ['office-hours/**', 'scripts/resolvers/preamble.ts', 'test/fixtures/mode-posture/**', 'test/helpers/llm-judge.ts', 'test/skill-e2e-office-hours.test.ts'],
 
   // Plan reviews
-  'plan-ceo-review':                  ['plan-ceo-review/**'],
-  'plan-ceo-review-selective':        ['plan-ceo-review/**'],
-  'plan-ceo-review-benefits':         ['plan-ceo-review/**', 'scripts/gen-skill-docs.ts'],
-  'plan-ceo-review-expansion-energy': ['plan-ceo-review/**', 'scripts/resolvers/preamble.ts', 'test/fixtures/mode-posture/**', 'test/helpers/llm-judge.ts'],
-  'plan-eng-review':           ['plan-eng-review/**'],
-  'plan-eng-review-artifact':  ['plan-eng-review/**'],
-  'plan-review-report':        ['plan-eng-review/**', 'scripts/gen-skill-docs.ts'],
+  'plan-ceo-review':                  ['plan-ceo-review/**', 'test/skill-e2e-plan.test.ts'],
+  'plan-ceo-review-selective':        ['plan-ceo-review/**', 'test/skill-e2e-plan.test.ts'],
+  'plan-ceo-review-benefits':         ['plan-ceo-review/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-plan.test.ts'],
+  'plan-ceo-review-expansion-energy': ['plan-ceo-review/**', 'scripts/resolvers/preamble.ts', 'test/fixtures/mode-posture/**', 'test/helpers/llm-judge.ts', 'test/skill-e2e-plan.test.ts'],
+  'plan-eng-review':           ['plan-eng-review/**', 'test/skill-e2e-plan.test.ts'],
+  'plan-eng-review-artifact':  ['plan-eng-review/**', 'test/skill-e2e-plan.test.ts'],
+  'plan-review-report':        ['plan-eng-review/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-plan.test.ts'],
 
   // Plan-mode smoke tests — gate-tier safety regression tests. Each test file
   // contains TWO test cases as of v1.21: the baseline plan-mode case and the
@@ -93,7 +93,7 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
   // regression test outcome between 'asked' and 'auto_decided'.
   'plan-ceo-review-plan-mode':    ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-ceo-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-ceo-plan-mode.test.ts'],
   'plan-eng-review-plan-mode':    ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-eng-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-eng-plan-mode.test.ts'],
-  'plan-design-review-plan-mode': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-design-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-design-plan-mode.test.ts'],
+  'plan-design-review-plan-mode': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-design-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-design-plan-mode.test.ts', 'test/skill-e2e-design.test.ts'],
   'plan-devex-review-plan-mode':  ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-devex-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-devex-plan-mode.test.ts'],
   // Covers ceo (preamble misfire) + eng/design (scope-gate bypass must not
   // fire outside plan mode) + the named-target exception case. 4 PTY runs;
@@ -119,7 +119,7 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
   // written a never-ask preference, AUQ should still auto-decide rather than
   // surfacing the question. Touches the question-tuning + preference
   // infrastructure plus the resolvers that own the AUTO_DECIDE preamble.
-  'auto-decide-preserved':        ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'plan-ceo-review/**', 'bin/gstack-question-preference', 'bin/gstack-config', 'bin/gstack-slug', 'hosts/claude/hooks/question-preference-hook.ts', 'lib/is-conductor.ts', 'test/helpers/claude-pty-runner.ts'],
+  'auto-decide-preserved':        ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'plan-ceo-review/**', 'bin/gstack-question-preference', 'bin/gstack-config', 'bin/gstack-slug', 'hosts/claude/hooks/question-preference-hook.ts', 'lib/is-conductor.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-auto-decide-preserved.test.ts'],
 
   // Conductor → prose decision brief (Conductor signal makes prose the default;
   // the PreToolUse hook denies the flaky tool). Touches the resolver that owns
@@ -130,7 +130,7 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
   // Each one tests behavior the SDK harness can't observe (rendered TTY,
   // numbered-option lists, multi-phase ordering, idempotency state echo).
   'preamble-script-ab':                        ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-brain-sync-block.ts', 'scripts/resolvers/preamble.ts', 'plan-ceo-review/**', 'test/helpers/auq-sdk-capture.ts', 'test/skill-e2e-preamble-script-ab.test.ts'],
-  'auq-format-gate':                           ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'test/helpers/llm-judge.ts'],
+  'auq-format-gate':                           ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'test/helpers/llm-judge.ts', 'test/skill-e2e-ask-user-question-format-compliance.test.ts'],
   'auq-repetition-cut-ab':                     ['scripts/resolvers/preamble/generate-ask-user-format.ts', 'plan-ceo-review/**', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/llm-judge.ts', 'test/fixtures/auq-pre-cut-plan-ceo-review-SKILL.md', 'test/skill-e2e-auq-repetition-cut-ab.test.ts'],
   'plan-ceo-mode-routing':       ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-ceo-mode-routing.test.ts'],
   'plan-design-with-ui-scope':   ['plan-design-review/**', 'test/fixtures/plans/ui-heavy-feature.md', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-design-with-ui.test.ts'],
@@ -142,12 +142,12 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
   'tpa-absent-darwin':           ['scripts/resolvers/third-party-actions.ts', 'ship/SKILL.md.tmpl', 'ship/sections/apple-release.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/helpers/session-runner.ts', 'test/skill-e2e-third-party-actions.test.ts'],
   'tpa-apple-ban':               ['scripts/resolvers/third-party-actions.ts', 'ship/SKILL.md.tmpl', 'ship/sections/apple-release.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/helpers/session-runner.ts', 'test/skill-e2e-third-party-actions.test.ts'],
   'ship-section-loading':        ['ship/**', 'scripts/resolvers/sections.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'test/skill-e2e-ship-section-loading.test.ts'],
-  'plan-ceo-section-loading':    ['plan-ceo-review/**', 'scripts/resolvers/sections.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts'],
+  'plan-ceo-section-loading':    ['plan-ceo-review/**', 'scripts/resolvers/sections.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'test/skill-e2e-plan-ceo-review-section-loading.test.ts'],
   // Data-driven behavioral guard for the 'plan'/'prompt' carves (eng, design,
   // devex, office-hours + future PR2 carves). One file iterating CARVE_GUARDS;
   // the selector sets GSTACK_CARVE_SKILL=<name> to scope cost to the changed
   // skill (D-CODEX A). Touching the registry/helper or sections.ts runs all.
-  'carve-section-loading':       ['design-html/**', 'design-shotgun/**', 'qa/**', 'browse/**', 'retro/**', 'autoplan/**', 'spec/**', 'setup-gbrain/**', 'review/**', 'codex/**', 'land-and-deploy/**', 'plan-eng-review/**', 'plan-design-review/**', 'plan-devex-review/**', 'office-hours/**', 'document-release/**', 'design-consultation/**', 'cso/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts'],
+  'carve-section-loading':       ['design-html/**', 'design-shotgun/**', 'qa/**', 'browse/**', 'retro/**', 'autoplan/**', 'spec/**', 'setup-gbrain/**', 'review/**', 'codex/**', 'land-and-deploy/**', 'plan-eng-review/**', 'plan-design-review/**', 'plan-devex-review/**', 'office-hours/**', 'document-release/**', 'design-consultation/**', 'cso/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'test/carve-section-loading.test.ts'],
   'autoplan-chain-pty':          ['autoplan/**', 'plan-ceo-review/**', 'plan-design-review/**', 'plan-eng-review/**', 'plan-devex-review/**', 'test/fixtures/plans/ui-heavy-feature.md', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-autoplan-chain.test.ts'],
   'e2e-harness-audit':            ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-ceo-review/**', 'plan-eng-review/**', 'plan-design-review/**', 'plan-devex-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/claude-pty-runner.ts'],
 
@@ -193,18 +193,18 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
 
   // AskUserQuestion format regression (RECOMMENDATION + Completeness: N/10)
   // Fires when either template OR the two preamble resolvers change.
-  'plan-ceo-review-format-mode':      ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/helpers/llm-judge.ts'],
-  'plan-ceo-review-format-approach':  ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/helpers/llm-judge.ts'],
-  'plan-eng-review-format-coverage':  ['plan-eng-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/helpers/llm-judge.ts'],
-  'plan-eng-review-format-kind':      ['plan-eng-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/helpers/llm-judge.ts'],
+  'plan-ceo-review-format-mode':      ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/helpers/llm-judge.ts', 'test/skill-e2e-plan-format.test.ts'],
+  'plan-ceo-review-format-approach':  ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/helpers/llm-judge.ts', 'test/skill-e2e-plan-format.test.ts'],
+  'plan-eng-review-format-coverage':  ['plan-eng-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/helpers/llm-judge.ts', 'test/skill-e2e-plan-format.test.ts'],
+  'plan-eng-review-format-kind':      ['plan-eng-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/helpers/llm-judge.ts', 'test/skill-e2e-plan-format.test.ts'],
 
   // v1.7.0.0 Pros/Cons format cadence + format + negative-escape evals.
   // Dependencies: same as format-mode + the 4 plan-review templates + overlay.
   // All periodic-tier (non-deterministic Opus 4.7 behavior).
-  'plan-ceo-review-prosons-cadence':  ['plan-ceo-review/**', 'plan-eng-review/**', 'plan-design-review/**', 'plan-devex-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md'],
-  'plan-review-prosons-format':       ['plan-ceo-review/**', 'plan-eng-review/**', 'plan-design-review/**', 'plan-devex-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md'],
-  'plan-review-prosons-hardstop-neg': ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md'],
-  'plan-review-prosons-neutral-neg':  ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md'],
+  'plan-ceo-review-prosons-cadence':  ['plan-ceo-review/**', 'plan-eng-review/**', 'plan-design-review/**', 'plan-devex-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/skill-e2e-plan-prosons.test.ts'],
+  'plan-review-prosons-format':       ['plan-ceo-review/**', 'plan-eng-review/**', 'plan-design-review/**', 'plan-devex-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/skill-e2e-plan-prosons.test.ts'],
+  'plan-review-prosons-hardstop-neg': ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/skill-e2e-plan-prosons.test.ts'],
+  'plan-review-prosons-neutral-neg':  ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/skill-e2e-plan-prosons.test.ts'],
 
   // Expanded coverage (CT3) — 6 non-plan-review skills inherit Pros/Cons via preamble
   'ship-prosons-format':              ['ship/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md'],
@@ -216,24 +216,24 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
   'document-release-prosons-format':  ['document-release/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md'],
 
   // /plan-tune (v1 observational)
-  'plan-tune-inspect':         ['plan-tune/**', 'scripts/question-registry.ts', 'scripts/psychographic-signals.ts', 'scripts/one-way-doors.ts', 'bin/gstack-question-log', 'bin/gstack-question-preference', 'bin/gstack-developer-profile'],
+  'plan-tune-inspect':         ['plan-tune/**', 'scripts/question-registry.ts', 'scripts/psychographic-signals.ts', 'scripts/one-way-doors.ts', 'bin/gstack-question-log', 'bin/gstack-question-preference', 'bin/gstack-developer-profile', 'test/skill-e2e-plan-tune.test.ts'],
 
   // /plan-tune cathedral (T16 — 5 E2E scenarios, all gate per D12)
-  'plan-tune-hook-capture':      ['hosts/claude/hooks/**', 'bin/gstack-question-log', 'bin/gstack-developer-profile', 'plan-tune/**'],
-  'plan-tune-enforcement':       ['hosts/claude/hooks/**', 'bin/gstack-question-preference', 'scripts/question-registry.ts'],
-  'plan-tune-annotation':        ['hosts/claude/hooks/**', 'scripts/declared-annotation.ts', 'scripts/psychographic-signals.ts', 'scripts/question-registry.ts'],
-  'plan-tune-codex-import':      ['bin/gstack-codex-session-import', 'bin/gstack-question-log', 'docs/spikes/codex-session-format.md'],
-  'plan-tune-dream-cycle':       ['bin/gstack-distill-free-text', 'bin/gstack-distill-apply', 'hosts/claude/hooks/**', 'plan-tune/**'],
+  'plan-tune-hook-capture':      ['hosts/claude/hooks/**', 'bin/gstack-question-log', 'bin/gstack-developer-profile', 'plan-tune/**', 'test/skill-e2e-plan-tune-cathedral.test.ts'],
+  'plan-tune-enforcement':       ['hosts/claude/hooks/**', 'bin/gstack-question-preference', 'scripts/question-registry.ts', 'test/skill-e2e-plan-tune-cathedral.test.ts'],
+  'plan-tune-annotation':        ['hosts/claude/hooks/**', 'scripts/declared-annotation.ts', 'scripts/psychographic-signals.ts', 'scripts/question-registry.ts', 'test/skill-e2e-plan-tune-cathedral.test.ts'],
+  'plan-tune-codex-import':      ['bin/gstack-codex-session-import', 'bin/gstack-question-log', 'docs/spikes/codex-session-format.md', 'test/skill-e2e-plan-tune-cathedral.test.ts'],
+  'plan-tune-dream-cycle':       ['bin/gstack-distill-free-text', 'bin/gstack-distill-apply', 'hosts/claude/hooks/**', 'plan-tune/**', 'test/skill-e2e-plan-tune-cathedral.test.ts'],
 
   // Codex offering verification
-  'codex-offered-office-hours':  ['office-hours/**', 'scripts/gen-skill-docs.ts'],
-  'codex-offered-ceo-review':    ['plan-ceo-review/**', 'scripts/gen-skill-docs.ts'],
-  'codex-offered-design-review': ['plan-design-review/**', 'scripts/gen-skill-docs.ts'],
-  'codex-offered-eng-review':    ['plan-eng-review/**', 'scripts/gen-skill-docs.ts'],
+  'codex-offered-office-hours':  ['office-hours/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-plan.test.ts'],
+  'codex-offered-ceo-review':    ['plan-ceo-review/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-plan.test.ts'],
+  'codex-offered-design-review': ['plan-design-review/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-plan.test.ts'],
+  'codex-offered-eng-review':    ['plan-eng-review/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-plan.test.ts'],
 
   // Ship
   'ship-base-branch': ['ship/**', 'bin/gstack-repo-mode', 'test/skill-e2e-review-attribution.test.ts'],
-  'ship-local-workflow': ['ship/**', 'scripts/gen-skill-docs.ts'],
+  'ship-local-workflow': ['ship/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-workflow.test.ts'],
   'review-dashboard-via': ['ship/**', 'scripts/resolvers/review.ts', 'codex/**', 'autoplan/**', 'land-and-deploy/**', 'test/skill-e2e-review-attribution.test.ts'],
 
   // Retro
@@ -244,51 +244,51 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
   'global-discover':   ['bin/gstack-global-discover.ts', 'test/global-discover.test.ts'],
 
   // CSO
-  'cso-full-audit':   ['cso/**'],
-  'cso-diff-mode':    ['cso/**'],
-  'cso-infra-scope':  ['cso/**'],
+  'cso-full-audit':   ['cso/**', 'test/skill-e2e-cso.test.ts'],
+  'cso-diff-mode':    ['cso/**', 'test/skill-e2e-cso.test.ts'],
+  'cso-infra-scope':  ['cso/**', 'test/skill-e2e-cso.test.ts'],
 
   // Learnings
-  'learnings-show': ['learn/**', 'bin/gstack-learnings-search', 'bin/gstack-learnings-log', 'scripts/resolvers/learnings.ts'],
+  'learnings-show': ['learn/**', 'bin/gstack-learnings-search', 'bin/gstack-learnings-log', 'scripts/resolvers/learnings.ts', 'test/skill-e2e-learnings.test.ts'],
 
   // Session Intelligence (timeline, context recovery, /context-save + /context-restore)
-  'timeline-event-flow':            ['bin/gstack-timeline-log', 'bin/gstack-timeline-read'],
-  'context-recovery-artifacts':     ['scripts/resolvers/preamble.ts', 'bin/gstack-timeline-log', 'bin/gstack-slug', 'learn/**'],
-  'context-save-writes-file':       ['context-save/**', 'bin/gstack-slug'],
-  'context-restore-loads-latest':   ['context-restore/**', 'bin/gstack-slug'],
+  'timeline-event-flow':            ['bin/gstack-timeline-log', 'bin/gstack-timeline-read', 'test/skill-e2e-session-intelligence.test.ts'],
+  'context-recovery-artifacts':     ['scripts/resolvers/preamble.ts', 'bin/gstack-timeline-log', 'bin/gstack-slug', 'learn/**', 'test/skill-e2e-session-intelligence.test.ts'],
+  'context-save-writes-file':       ['context-save/**', 'bin/gstack-slug', 'test/skill-e2e-session-intelligence.test.ts'],
+  'context-restore-loads-latest':   ['context-restore/**', 'bin/gstack-slug', 'test/skill-e2e-session-intelligence.test.ts'],
 
   // Context skills E2E (live-fire, Skill-tool routing path) — see
   // test/skill-e2e-context-skills.test.ts. These are periodic-tier because
   // each one spawns claude -p and costs ~$0.20-$0.40. Collectively they
   // verify the thing the /checkpoint → /context-save rename was for.
-  'context-save-routing':                  ['context-save/**', 'scripts/resolvers/preamble.ts'],
-  'context-save-then-restore-roundtrip':   ['context-save/**', 'context-restore/**', 'bin/gstack-slug'],
-  'context-restore-fragment-match':        ['context-restore/**'],
-  'context-restore-empty-state':           ['context-restore/**'],
-  'context-restore-list-delegates':        ['context-restore/**'],
-  'context-restore-legacy-compat':         ['context-restore/**'],
-  'context-save-list-current-branch':      ['context-save/**'],
-  'context-save-list-all-branches':        ['context-save/**'],
+  'context-save-routing':                  ['context-save/**', 'scripts/resolvers/preamble.ts', 'test/skill-e2e-context-skills.test.ts'],
+  'context-save-then-restore-roundtrip':   ['context-save/**', 'context-restore/**', 'bin/gstack-slug', 'test/skill-e2e-context-skills.test.ts'],
+  'context-restore-fragment-match':        ['context-restore/**', 'test/skill-e2e-context-skills.test.ts'],
+  'context-restore-empty-state':           ['context-restore/**', 'test/skill-e2e-context-skills.test.ts'],
+  'context-restore-list-delegates':        ['context-restore/**', 'test/skill-e2e-context-skills.test.ts'],
+  'context-restore-legacy-compat':         ['context-restore/**', 'test/skill-e2e-context-skills.test.ts'],
+  'context-save-list-current-branch':      ['context-save/**', 'test/skill-e2e-context-skills.test.ts'],
+  'context-save-list-all-branches':        ['context-save/**', 'test/skill-e2e-context-skills.test.ts'],
 
   // Document-release
-  'document-release': ['document-release/**'],
+  'document-release': ['document-release/**', 'test/skill-e2e-workflow.test.ts'],
 
   // Codex (Claude E2E — tests /codex skill via Claude)
-  'codex-review': ['codex/**'],
+  'codex-review': ['codex/**', 'test/skill-e2e-workflow.test.ts'],
 
   // Codex E2E (tests skills via Codex CLI + worktree)
-  'codex-discover-skill':  ['codex/**', '.agents/skills/**', 'test/helpers/codex-session-runner.ts', 'lib/worktree.ts'],
-  'codex-review-findings': ['review/**', '.agents/skills/gstack-review/**', 'codex/**', 'test/helpers/codex-session-runner.ts', 'lib/worktree.ts'],
+  'codex-discover-skill':  ['codex/**', '.agents/skills/**', 'test/helpers/codex-session-runner.ts', 'lib/worktree.ts', 'test/codex-e2e.test.ts'],
+  'codex-review-findings': ['review/**', '.agents/skills/gstack-review/**', 'codex/**', 'test/helpers/codex-session-runner.ts', 'lib/worktree.ts', 'test/codex-e2e.test.ts'],
 
   // GPT-5.6 Sol scope-termination E2E (Codex CLI, full generated investigate skill)
   'codex-sol-scope-termination': ['model-overlays/gpt-5.6-sol.md', 'scripts/models.ts', 'scripts/resolvers/model-overlay.ts', 'scripts/resolvers/preamble/**', 'investigate/**', 'test/helpers/codex-session-runner.ts', 'test/codex-e2e-sol-scope.test.ts'],
 
   // Gemini E2E — smoke test only (Gemini gets lost in worktrees on complex tasks)
-  'gemini-smoke':  ['.agents/skills/**', 'test/helpers/gemini-session-runner.ts', 'lib/worktree.ts'],
+  'gemini-smoke':  ['.agents/skills/**', 'test/helpers/gemini-session-runner.ts', 'lib/worktree.ts', 'test/gemini-e2e.test.ts'],
 
 
   // Coverage audit (shared fixture) + triage + gates
-  'ship-coverage-audit': ['ship/**', 'test/fixtures/coverage-audit-fixture.ts', 'bin/gstack-repo-mode'],
+  'ship-coverage-audit': ['ship/**', 'test/fixtures/coverage-audit-fixture.ts', 'bin/gstack-repo-mode', 'test/skill-e2e-workflow.test.ts'],
   'review-coverage-audit': ['review/**', 'test/fixtures/coverage-audit-fixture.ts', 'test/skill-e2e-coverage-audit.test.ts'],
   'plan-eng-coverage-audit': ['plan-eng-review/**', 'test/fixtures/coverage-audit-fixture.ts', 'test/skill-e2e-coverage-audit.test.ts'],
   'ship-triage': ['ship/**', 'bin/gstack-repo-mode', 'test/skill-e2e-triage.test.ts'],
@@ -300,12 +300,12 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
   'review-plan-completion': ['review/**', 'scripts/gen-skill-docs.ts'],
 
   // Design
-  'design-consultation-core':       ['design-consultation/**', 'scripts/gen-skill-docs.ts', 'test/helpers/llm-judge.ts'],
-  'design-consultation-existing':   ['design-consultation/**', 'scripts/gen-skill-docs.ts'],
-  'design-consultation-research':   ['design-consultation/**', 'scripts/gen-skill-docs.ts'],
-  'design-consultation-preview':    ['design-consultation/**', 'scripts/gen-skill-docs.ts'],
-  'plan-design-review-no-ui-scope': ['plan-design-review/**', 'scripts/gen-skill-docs.ts'],
-  'design-review-fix':              ['design-review/**', 'browse/src/**', 'scripts/gen-skill-docs.ts'],
+  'design-consultation-core':       ['design-consultation/**', 'scripts/gen-skill-docs.ts', 'test/helpers/llm-judge.ts', 'test/skill-e2e-design.test.ts'],
+  'design-consultation-existing':   ['design-consultation/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-design.test.ts'],
+  'design-consultation-research':   ['design-consultation/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-design.test.ts'],
+  'design-consultation-preview':    ['design-consultation/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-design.test.ts'],
+  'plan-design-review-no-ui-scope': ['plan-design-review/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-design.test.ts'],
+  'design-review-fix':              ['design-review/**', 'browse/src/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-design.test.ts'],
 
   // Design Shotgun
   'design-shotgun-path':            ['design-shotgun/**', 'design/src/**', 'scripts/resolvers/design.ts'],
@@ -314,24 +314,24 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
 
   // /diagram (diagram-render bundle consumers). Triplet = deterministic
   // functional (gate); authoring quality = LLM-judged benchmark (periodic).
-  'diagram-triplet':            ['diagram/**', 'lib/diagram-render/**', 'browse/src/write-commands.ts', 'browse/src/read-commands.ts'],
-  'diagram-authoring-quality':  ['diagram/**', 'lib/diagram-render/**', 'test/helpers/llm-judge.ts'],
+  'diagram-triplet':            ['diagram/**', 'lib/diagram-render/**', 'browse/src/write-commands.ts', 'browse/src/read-commands.ts', 'test/skill-e2e-diagram.test.ts'],
+  'diagram-authoring-quality':  ['diagram/**', 'lib/diagram-render/**', 'test/helpers/llm-judge.ts', 'test/skill-e2e-diagram.test.ts'],
 
   // gstack-upgrade
-  'gstack-upgrade-happy-path': ['gstack-upgrade/**'],
+  'gstack-upgrade-happy-path': ['gstack-upgrade/**', 'test/skill-e2e-workflow.test.ts'],
 
   // Deploy skills
-  'land-and-deploy-workflow':      ['land-and-deploy/**', 'scripts/gen-skill-docs.ts'],
-  'land-and-deploy-first-run':     ['land-and-deploy/**', 'scripts/gen-skill-docs.ts', 'bin/gstack-slug'],
-  'land-and-deploy-review-gate':   ['land-and-deploy/**', 'bin/gstack-review-read'],
-  'canary-workflow':               ['canary/**', 'browse/src/**'],
-  'benchmark-workflow':            ['benchmark/**', 'browse/src/**'],
-  'setup-deploy-workflow':         ['setup-deploy/**', 'scripts/gen-skill-docs.ts'],
+  'land-and-deploy-workflow':      ['land-and-deploy/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-deploy.test.ts'],
+  'land-and-deploy-first-run':     ['land-and-deploy/**', 'scripts/gen-skill-docs.ts', 'bin/gstack-slug', 'test/skill-e2e-deploy.test.ts'],
+  'land-and-deploy-review-gate':   ['land-and-deploy/**', 'bin/gstack-review-read', 'test/skill-e2e-deploy.test.ts'],
+  'canary-workflow':               ['canary/**', 'browse/src/**', 'test/skill-e2e-deploy.test.ts'],
+  'benchmark-workflow':            ['benchmark/**', 'browse/src/**', 'test/skill-e2e-deploy.test.ts'],
+  'setup-deploy-workflow':         ['setup-deploy/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-deploy.test.ts'],
 
 
   // Autoplan
   'autoplan-core':  ['autoplan/**', 'plan-ceo-review/**', 'plan-eng-review/**', 'plan-design-review/**'],
-  'autoplan-dual-voice': ['autoplan/**', 'codex/**', 'bin/gstack-codex-probe', 'scripts/resolvers/review.ts', 'scripts/resolvers/design.ts'],
+  'autoplan-dual-voice': ['autoplan/**', 'codex/**', 'bin/gstack-codex-probe', 'scripts/resolvers/review.ts', 'scripts/resolvers/design.ts', 'test/skill-e2e-autoplan-dual-voice.test.ts'],
 
   // Multi-provider benchmark adapters — live API smoke against real claude/codex/gemini CLIs
   'benchmark-providers-live': ['bin/gstack-model-benchmark', 'test/helpers/providers/**', 'test/helpers/benchmark-runner.ts', 'test/helpers/pricing.ts', 'test/skill-e2e-benchmark-providers.test.ts'],
@@ -344,41 +344,46 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
   'scrape-match-path': [
     'scrape/**', 'browse/src/browser-skills.ts', 'browse/src/browser-skill-commands.ts',
     'browser-skills/hackernews-frontpage/**',
+    'test/skill-e2e-skillify.test.ts',
   ],
   'scrape-prototype-path': [
     'scrape/**', 'browse/src/browser-skills.ts', 'browse/src/browser-skill-commands.ts',
+    'test/skill-e2e-skillify.test.ts',
   ],
   'skillify-happy-path': [
     'skillify/**', 'scrape/**', 'browse/src/browser-skill-write.ts',
     'browse/src/browser-skills.ts', 'browse/src/browser-skill-commands.ts',
+    'test/skill-e2e-skillify.test.ts',
   ],
   'skillify-provenance-refusal': [
     'skillify/**', 'browse/src/browser-skill-write.ts',
+    'test/skill-e2e-skillify.test.ts',
   ],
   'skillify-approval-reject': [
     'skillify/**', 'scrape/**', 'browse/src/browser-skill-write.ts',
+    'test/skill-e2e-skillify.test.ts',
   ],
 
   // Skill routing — journey-stage tests (depend on ALL skill descriptions)
-  'journey-ideation':       ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
-  'journey-plan-eng':       ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
-  'journey-debug':          ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
-  'journey-qa':             ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
-  'journey-code-review':    ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
-  'journey-ship':           ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
-  'journey-docs':           ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
-  'journey-retro':          ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
-  'journey-design-system':  ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
-  'journey-visual-qa':      ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
+  'journey-ideation':       ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
+  'journey-plan-eng':       ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
+  'journey-debug':          ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
+  'journey-qa':             ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
+  'journey-code-review':    ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
+  'journey-ship':           ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
+  'journey-docs':           ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
+  'journey-retro':          ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
+  'journey-design-system':  ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
+  'journey-visual-qa':      ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
 
   // Opus 4.7 behavior evals — keys match testName: values in the test file.
   // Routing sub-tests use template literal `routing-${c.name}` testNames,
   // which the touchfile completeness scanner skips; they inherit selection
   // from the file-level touchfile entry via GLOBAL_TOUCHFILES.
   'fanout-arm-overlay-on':
-    ['model-overlays/claude.md', 'model-overlays/opus-4-7.md', 'scripts/models.ts', 'scripts/resolvers/model-overlay.ts'],
+    ['model-overlays/claude.md', 'model-overlays/opus-4-7.md', 'scripts/models.ts', 'scripts/resolvers/model-overlay.ts', 'test/skill-e2e-opus-47.test.ts'],
   'fanout-arm-overlay-off':
-    ['model-overlays/claude.md', 'model-overlays/opus-4-7.md', 'scripts/models.ts', 'scripts/resolvers/model-overlay.ts'],
+    ['model-overlays/claude.md', 'model-overlays/opus-4-7.md', 'scripts/models.ts', 'scripts/resolvers/model-overlay.ts', 'test/skill-e2e-opus-47.test.ts'],
 
   // Overlay efficacy harness (SDK) — measures whether overlay nudges change
   // behavior under @anthropic-ai/claude-agent-sdk (closer to real Claude Code
@@ -809,49 +814,49 @@ export const E2E_TIERS: Record<string, 'gate' | 'periodic'> = {
  * LLM-judge test touchfiles — keyed by test description string.
  */
 export const LLM_JUDGE_TOUCHFILES: Record<string, string[]> = {
-  'command reference table':          ['browse/sections/**', 'SKILL.md', 'SKILL.md.tmpl', 'browse/src/commands.ts'],
-  'snapshot flags reference':         ['browse/sections/**', 'SKILL.md', 'SKILL.md.tmpl', 'browse/src/snapshot.ts'],
-  'browse/SKILL.md reference':        ['browse/sections/**', 'browse/SKILL.md', 'browse/SKILL.md.tmpl', 'browse/src/**'],
-  'setup block':                      ['SKILL.md', 'SKILL.md.tmpl'],
-  'regression vs baseline':           ['browse/sections/**', 'SKILL.md', 'SKILL.md.tmpl', 'browse/src/commands.ts', 'test/fixtures/eval-baselines.json'],
-  'qa/SKILL.md workflow':             ['qa/sections/**', 'qa/SKILL.md', 'qa/SKILL.md.tmpl'],
-  'qa/SKILL.md health rubric':        ['qa/sections/**', 'qa/SKILL.md', 'qa/SKILL.md.tmpl'],
-  'qa/SKILL.md anti-refusal':         ['qa/sections/**', 'qa/SKILL.md', 'qa/SKILL.md.tmpl', 'qa-only/SKILL.md', 'qa-only/SKILL.md.tmpl'],
-  'cross-skill greptile consistency': ['review/SKILL.md', 'review/SKILL.md.tmpl', 'ship/SKILL.md', 'ship/SKILL.md.tmpl', 'review/greptile-triage.md', 'retro/SKILL.md', 'retro/SKILL.md.tmpl'],
-  'baseline score pinning':           ['browse/sections/**', 'SKILL.md', 'SKILL.md.tmpl', 'test/fixtures/eval-baselines.json'],
+  'command reference table':          ['browse/sections/**', 'SKILL.md', 'SKILL.md.tmpl', 'browse/src/commands.ts', 'test/skill-llm-eval.test.ts'],
+  'snapshot flags reference':         ['browse/sections/**', 'SKILL.md', 'SKILL.md.tmpl', 'browse/src/snapshot.ts', 'test/skill-llm-eval.test.ts'],
+  'browse/SKILL.md reference':        ['browse/sections/**', 'browse/SKILL.md', 'browse/SKILL.md.tmpl', 'browse/src/**', 'test/skill-llm-eval.test.ts'],
+  'setup block':                      ['SKILL.md', 'SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
+  'regression vs baseline':           ['browse/sections/**', 'SKILL.md', 'SKILL.md.tmpl', 'browse/src/commands.ts', 'test/fixtures/eval-baselines.json', 'test/skill-llm-eval.test.ts'],
+  'qa/SKILL.md workflow':             ['qa/sections/**', 'qa/SKILL.md', 'qa/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
+  'qa/SKILL.md health rubric':        ['qa/sections/**', 'qa/SKILL.md', 'qa/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
+  'qa/SKILL.md anti-refusal':         ['qa/sections/**', 'qa/SKILL.md', 'qa/SKILL.md.tmpl', 'qa-only/SKILL.md', 'qa-only/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
+  'cross-skill greptile consistency': ['review/SKILL.md', 'review/SKILL.md.tmpl', 'ship/SKILL.md', 'ship/SKILL.md.tmpl', 'review/greptile-triage.md', 'retro/SKILL.md', 'retro/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
+  'baseline score pinning':           ['browse/sections/**', 'SKILL.md', 'SKILL.md.tmpl', 'test/fixtures/eval-baselines.json', 'test/skill-llm-eval.test.ts'],
 
   // Ship & Release
-  'ship/SKILL.md workflow':               ['ship/SKILL.md', 'ship/SKILL.md.tmpl'],
-  'document-release/SKILL.md workflow':   ['document-release/SKILL.md', 'document-release/SKILL.md.tmpl'],
+  'ship/SKILL.md workflow':               ['ship/SKILL.md', 'ship/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
+  'document-release/SKILL.md workflow':   ['document-release/SKILL.md', 'document-release/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
 
   // Plan Reviews
-  'plan-ceo-review/SKILL.md modes':       ['plan-ceo-review/SKILL.md', 'plan-ceo-review/SKILL.md.tmpl'],
-  'plan-eng-review/SKILL.md sections':    ['plan-eng-review/SKILL.md', 'plan-eng-review/SKILL.md.tmpl'],
+  'plan-ceo-review/SKILL.md modes':       ['plan-ceo-review/SKILL.md', 'plan-ceo-review/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
+  'plan-eng-review/SKILL.md sections':    ['plan-eng-review/SKILL.md', 'plan-eng-review/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
 
   // /spec authored-spec quality (paid LLM-judge — periodic-tier).
-  'plan-design-review/SKILL.md passes':   ['plan-design-review/SKILL.md', 'plan-design-review/SKILL.md.tmpl'],
+  'plan-design-review/SKILL.md passes':   ['plan-design-review/SKILL.md', 'plan-design-review/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
 
   // Design skills
-  'design-review/SKILL.md fix loop':      ['design-review/SKILL.md', 'design-review/SKILL.md.tmpl'],
-  'design-consultation/SKILL.md research': ['design-consultation/SKILL.md', 'design-consultation/SKILL.md.tmpl'],
+  'design-review/SKILL.md fix loop':      ['design-review/SKILL.md', 'design-review/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
+  'design-consultation/SKILL.md research': ['design-consultation/SKILL.md', 'design-consultation/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
 
   // Office Hours
   'office-hours/SKILL.md spec review':    ['office-hours/SKILL.md', 'office-hours/SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
   'office-hours/SKILL.md design sketch':  ['office-hours/SKILL.md', 'office-hours/SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
 
   // Deploy skills
-  'land-and-deploy/SKILL.md workflow':    ['land-and-deploy/SKILL.md', 'land-and-deploy/SKILL.md.tmpl', 'land-and-deploy/sections/**'],
-  'canary/SKILL.md monitoring loop':      ['canary/SKILL.md', 'canary/SKILL.md.tmpl'],
-  'benchmark/SKILL.md perf collection':   ['benchmark/SKILL.md', 'benchmark/SKILL.md.tmpl'],
-  'setup-deploy/SKILL.md platform setup': ['setup-deploy/SKILL.md', 'setup-deploy/SKILL.md.tmpl'],
+  'land-and-deploy/SKILL.md workflow':    ['land-and-deploy/SKILL.md', 'land-and-deploy/SKILL.md.tmpl', 'land-and-deploy/sections/**', 'test/skill-llm-eval.test.ts'],
+  'canary/SKILL.md monitoring loop':      ['canary/SKILL.md', 'canary/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
+  'benchmark/SKILL.md perf collection':   ['benchmark/SKILL.md', 'benchmark/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
+  'setup-deploy/SKILL.md platform setup': ['setup-deploy/SKILL.md', 'setup-deploy/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
 
   // Other skills
-  'retro/SKILL.md instructions':          ['retro/sections/**', 'retro/SKILL.md', 'retro/SKILL.md.tmpl'],
-  'qa-only/SKILL.md workflow':            ['qa-only/SKILL.md', 'qa-only/SKILL.md.tmpl'],
-  'gstack-upgrade/SKILL.md upgrade flow': ['gstack-upgrade/SKILL.md', 'gstack-upgrade/SKILL.md.tmpl'],
+  'retro/SKILL.md instructions':          ['retro/sections/**', 'retro/SKILL.md', 'retro/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
+  'qa-only/SKILL.md workflow':            ['qa-only/SKILL.md', 'qa-only/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
+  'gstack-upgrade/SKILL.md upgrade flow': ['gstack-upgrade/SKILL.md', 'gstack-upgrade/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
 
   // Voice directive
-  'voice directive tone':                 ['scripts/resolvers/preamble.ts', 'review/SKILL.md', 'review/SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
+  'voice directive tone':                 ['scripts/resolvers/preamble.ts', 'review/SKILL.md', 'review/SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-llm-eval.test.ts'],
 };
 
 /**