Merge branch 'main' into garrytan/team-supabase-store

Resolved 4 conflicts:
- scripts/gen-skill-docs.ts: kept ARTIFACT_SETUP + added main's new
  resolvers (SPEC_REVIEW_LOOP, DESIGN_SKETCH, BENEFITS_FROM,
  CODEX_REVIEW_STEP). Updated codex review-log to use new paths.
- ship/SKILL.md.tmpl: adopted {{CODEX_REVIEW_STEP}} macro from main
- test/skill-e2e.test.ts: added main's new E2E tests (office-hours
  spec review, plan-ceo benefits-from) + kept our E2E isolation cleanup

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

test/helpers/codex-session-runner.ts

@@ -0,0 +1,282 @@
+/**
+ * Codex CLI subprocess runner for skill E2E testing.
+ *
+ * Spawns `codex exec` as a completely independent process, parses its JSONL
+ * output, and returns structured results. Follows the same pattern as
+ * session-runner.ts but adapted for the Codex CLI.
+ *
+ * Key differences from Claude session-runner:
+ * - Uses `codex exec` instead of `claude -p`
+ * - Output is JSONL with different event types (item.completed, turn.completed, thread.started)
+ * - Uses `--json` flag instead of `--output-format stream-json`
+ * - Needs temp HOME with skill installed at ~/.codex/skills/{skillName}/SKILL.md
+ */
+
+import * as fs from 'fs';
+import * as path from 'path';
+import * as os from 'os';
+
+// --- Interfaces ---
+
+export interface CodexResult {
+  output: string;           // Full agent message text
+  reasoning: string[];      // [codex thinking] blocks
+  toolCalls: string[];      // [codex ran] commands
+  tokens: number;           // Total tokens used
+  exitCode: number;         // Process exit code
+  durationMs: number;       // Wall clock time
+  sessionId: string | null; // Thread ID for session continuity
+  rawLines: string[];       // Raw JSONL lines for debugging
+}
+
+// --- JSONL parser (ported from Python in codex/SKILL.md.tmpl) ---
+
+export interface ParsedCodexJSONL {
+  output: string;
+  reasoning: string[];
+  toolCalls: string[];
+  tokens: number;
+  sessionId: string | null;
+}
+
+/**
+ * Parse an array of JSONL lines from `codex exec --json` into structured data.
+ * Pure function — no I/O, no side effects.
+ *
+ * Handles these Codex event types:
+ * - thread.started → extract thread_id (session ID)
+ * - item.completed → extract reasoning, agent_message, command_execution
+ * - turn.completed → extract token usage
+ */
+export function parseCodexJSONL(lines: string[]): ParsedCodexJSONL {
+  const outputParts: string[] = [];
+  const reasoning: string[] = [];
+  const toolCalls: string[] = [];
+  let tokens = 0;
+  let sessionId: string | null = null;
+
+  for (const line of lines) {
+    if (!line.trim()) continue;
+    try {
+      const obj = JSON.parse(line);
+      const t = obj.type || '';
+
+      if (t === 'thread.started') {
+        const tid = obj.thread_id || '';
+        if (tid) sessionId = tid;
+      } else if (t === 'item.completed' && obj.item) {
+        const item = obj.item;
+        const itype = item.type || '';
+        const text = item.text || '';
+
+        if (itype === 'reasoning' && text) {
+          reasoning.push(text);
+        } else if (itype === 'agent_message' && text) {
+          outputParts.push(text);
+        } else if (itype === 'command_execution') {
+          const cmd = item.command || '';
+          if (cmd) toolCalls.push(cmd);
+        }
+      } else if (t === 'turn.completed') {
+        const usage = obj.usage || {};
+        const turnTokens = (usage.input_tokens || 0) + (usage.output_tokens || 0);
+        tokens += turnTokens;
+      }
+    } catch { /* skip malformed lines */ }
+  }
+
+  return {
+    output: outputParts.join('\n'),
+    reasoning,
+    toolCalls,
+    tokens,
+    sessionId,
+  };
+}
+
+// --- Skill installation helper ---
+
+/**
+ * Install a SKILL.md into a temp HOME directory for Codex to discover.
+ * Creates ~/.codex/skills/{skillName}/SKILL.md in the temp HOME.
+ *
+ * Returns the temp HOME path. Caller is responsible for cleanup.
+ */
+export function installSkillToTempHome(
+  skillDir: string,
+  skillName: string,
+  tempHome?: string,
+): string {
+  const home = tempHome || fs.mkdtempSync(path.join(os.tmpdir(), 'codex-e2e-'));
+  const destDir = path.join(home, '.codex', 'skills', skillName);
+  fs.mkdirSync(destDir, { recursive: true });
+
+  const srcSkill = path.join(skillDir, 'SKILL.md');
+  if (fs.existsSync(srcSkill)) {
+    fs.copyFileSync(srcSkill, path.join(destDir, 'SKILL.md'));
+  }
+
+  return home;
+}
+
+// --- Main runner ---
+
+/**
+ * Run a Codex skill via `codex exec` and return structured results.
+ *
+ * Spawns codex in a temp HOME with the skill installed, parses JSONL output,
+ * and returns a CodexResult. Skips gracefully if codex binary is not found.
+ */
+export async function runCodexSkill(opts: {
+  skillDir: string;         // Path to skill directory containing SKILL.md
+  prompt: string;           // What to ask Codex to do with the skill
+  timeoutMs?: number;       // Default 300000 (5 min)
+  cwd?: string;             // Working directory
+  skillName?: string;       // Skill name for installation (default: dirname)
+  sandbox?: string;         // Sandbox mode (default: 'read-only')
+}): Promise<CodexResult> {
+  const {
+    skillDir,
+    prompt,
+    timeoutMs = 300_000,
+    cwd,
+    skillName,
+    sandbox = 'read-only',
+  } = opts;
+
+  const startTime = Date.now();
+  const name = skillName || path.basename(skillDir) || 'gstack';
+
+  // Check if codex binary exists
+  const whichResult = Bun.spawnSync(['which', 'codex']);
+  if (whichResult.exitCode !== 0) {
+    return {
+      output: 'SKIP: codex binary not found',
+      reasoning: [],
+      toolCalls: [],
+      tokens: 0,
+      exitCode: -1,
+      durationMs: Date.now() - startTime,
+      sessionId: null,
+      rawLines: [],
+    };
+  }
+
+  // Set up temp HOME with skill installed
+  const tempHome = fs.mkdtempSync(path.join(os.tmpdir(), 'codex-e2e-'));
+  const realHome = os.homedir();
+
+  try {
+    installSkillToTempHome(skillDir, name, tempHome);
+
+    // Symlink real Codex auth config so codex can authenticate from temp HOME.
+    // Codex stores auth in ~/.codex/ — we need the config but not the skills
+    // (we install our own test skills above).
+    const realCodexConfig = path.join(realHome, '.codex');
+    const tempCodexDir = path.join(tempHome, '.codex');
+    if (fs.existsSync(realCodexConfig)) {
+      // Copy auth-related files from real ~/.codex/ into temp ~/.codex/
+      // (skills/ is already set up by installSkillToTempHome)
+      const entries = fs.readdirSync(realCodexConfig);
+      for (const entry of entries) {
+        if (entry === 'skills') continue; // don't clobber our test skills
+        const src = path.join(realCodexConfig, entry);
+        const dst = path.join(tempCodexDir, entry);
+        if (!fs.existsSync(dst)) {
+          fs.cpSync(src, dst, { recursive: true });
+        }
+      }
+    }
+
+    // Build codex exec command
+    const args = ['exec', prompt, '--json', '-s', sandbox];
+
+    // Spawn codex with temp HOME so it discovers our installed skill
+    const proc = Bun.spawn(['codex', ...args], {
+      cwd: cwd || skillDir,
+      stdout: 'pipe',
+      stderr: 'pipe',
+      env: {
+        ...process.env,
+        HOME: tempHome,
+      },
+    });
+
+    // Race against timeout
+    let timedOut = false;
+    const timeoutId = setTimeout(() => {
+      timedOut = true;
+      proc.kill();
+    }, timeoutMs);
+
+    // Stream and collect JSONL from stdout
+    const collectedLines: string[] = [];
+    const stderrPromise = new Response(proc.stderr).text();
+
+    const reader = proc.stdout.getReader();
+    const decoder = new TextDecoder();
+    let buf = '';
+
+    try {
+      while (true) {
+        const { done, value } = await reader.read();
+        if (done) break;
+        buf += decoder.decode(value, { stream: true });
+        const lines = buf.split('\n');
+        buf = lines.pop() || '';
+        for (const line of lines) {
+          if (!line.trim()) continue;
+          collectedLines.push(line);
+
+          // Real-time progress to stderr
+          try {
+            const event = JSON.parse(line);
+            if (event.type === 'item.completed' && event.item) {
+              const item = event.item;
+              if (item.type === 'command_execution' && item.command) {
+                const elapsed = Math.round((Date.now() - startTime) / 1000);
+                process.stderr.write(`  [codex ${elapsed}s] ran: ${item.command.slice(0, 100)}\n`);
+              } else if (item.type === 'agent_message' && item.text) {
+                const elapsed = Math.round((Date.now() - startTime) / 1000);
+                process.stderr.write(`  [codex ${elapsed}s] message: ${item.text.slice(0, 100)}\n`);
+              }
+            }
+          } catch { /* skip — parseCodexJSONL will handle it later */ }
+        }
+      }
+    } catch { /* stream read error — fall through to exit code handling */ }
+
+    // Flush remaining buffer
+    if (buf.trim()) {
+      collectedLines.push(buf);
+    }
+
+    const stderr = await stderrPromise;
+    const exitCode = await proc.exited;
+    clearTimeout(timeoutId);
+
+    const durationMs = Date.now() - startTime;
+
+    // Parse all collected JSONL lines
+    const parsed = parseCodexJSONL(collectedLines);
+
+    // Log stderr if non-empty (may contain auth errors, etc.)
+    if (stderr.trim()) {
+      process.stderr.write(`  [codex stderr] ${stderr.trim().slice(0, 200)}\n`);
+    }
+
+    return {
+      output: parsed.output,
+      reasoning: parsed.reasoning,
+      toolCalls: parsed.toolCalls,
+      tokens: parsed.tokens,
+      exitCode: timedOut ? 124 : exitCode,
+      durationMs,
+      sessionId: parsed.sessionId,
+      rawLines: collectedLines,
+    };
+  } finally {
+    // Clean up temp HOME
+    try { fs.rmSync(tempHome, { recursive: true, force: true }); } catch { /* non-fatal */ }
+  }
+}

test/helpers/gemini-session-runner.test.ts

@@ -0,0 +1,104 @@
+import { describe, test, expect } from 'bun:test';
+import { parseGeminiJSONL } from './gemini-session-runner';
+
+// Fixture: actual Gemini CLI stream-json output with tool use
+const FIXTURE_LINES = [
+  '{"type":"init","timestamp":"2026-03-20T15:14:46.455Z","session_id":"test-session-123","model":"auto-gemini-3"}',
+  '{"type":"message","timestamp":"2026-03-20T15:14:46.456Z","role":"user","content":"list the files"}',
+  '{"type":"message","timestamp":"2026-03-20T15:14:49.650Z","role":"assistant","content":"I will list the files.","delta":true}',
+  '{"type":"tool_use","timestamp":"2026-03-20T15:14:49.690Z","tool_name":"run_shell_command","tool_id":"cmd_1","parameters":{"command":"ls"}}',
+  '{"type":"tool_result","timestamp":"2026-03-20T15:14:49.931Z","tool_id":"cmd_1","status":"success","output":"file1.ts\\nfile2.ts"}',
+  '{"type":"message","timestamp":"2026-03-20T15:14:51.945Z","role":"assistant","content":"Here are the files.","delta":true}',
+  '{"type":"result","timestamp":"2026-03-20T15:14:52.030Z","status":"success","stats":{"total_tokens":27147,"input_tokens":26928,"output_tokens":87,"cached":0,"duration_ms":5575,"tool_calls":1}}',
+];
+
+describe('parseGeminiJSONL', () => {
+  test('extracts session ID from init event', () => {
+    const parsed = parseGeminiJSONL(FIXTURE_LINES);
+    expect(parsed.sessionId).toBe('test-session-123');
+  });
+
+  test('concatenates assistant message deltas into output', () => {
+    const parsed = parseGeminiJSONL(FIXTURE_LINES);
+    expect(parsed.output).toBe('I will list the files.Here are the files.');
+  });
+
+  test('ignores user messages', () => {
+    const lines = [
+      '{"type":"message","role":"user","content":"this should be ignored"}',
+      '{"type":"message","role":"assistant","content":"this should be kept","delta":true}',
+    ];
+    const parsed = parseGeminiJSONL(lines);
+    expect(parsed.output).toBe('this should be kept');
+  });
+
+  test('extracts tool names from tool_use events', () => {
+    const parsed = parseGeminiJSONL(FIXTURE_LINES);
+    expect(parsed.toolCalls).toHaveLength(1);
+    expect(parsed.toolCalls[0]).toBe('run_shell_command');
+  });
+
+  test('extracts total tokens from result stats', () => {
+    const parsed = parseGeminiJSONL(FIXTURE_LINES);
+    expect(parsed.tokens).toBe(27147);
+  });
+
+  test('skips malformed lines without throwing', () => {
+    const lines = [
+      '{"type":"init","session_id":"ok"}',
+      'this is not json',
+      '{"type":"message","role":"assistant","content":"hello","delta":true}',
+      '{incomplete json',
+      '{"type":"result","status":"success","stats":{"total_tokens":100}}',
+    ];
+    const parsed = parseGeminiJSONL(lines);
+    expect(parsed.sessionId).toBe('ok');
+    expect(parsed.output).toBe('hello');
+    expect(parsed.tokens).toBe(100);
+  });
+
+  test('skips empty and whitespace-only lines', () => {
+    const lines = [
+      '',
+      '  ',
+      '{"type":"init","session_id":"s1"}',
+      '\t',
+      '{"type":"result","status":"success","stats":{"total_tokens":50}}',
+    ];
+    const parsed = parseGeminiJSONL(lines);
+    expect(parsed.sessionId).toBe('s1');
+    expect(parsed.tokens).toBe(50);
+  });
+
+  test('handles empty input', () => {
+    const parsed = parseGeminiJSONL([]);
+    expect(parsed.output).toBe('');
+    expect(parsed.toolCalls).toHaveLength(0);
+    expect(parsed.tokens).toBe(0);
+    expect(parsed.sessionId).toBeNull();
+  });
+
+  test('handles missing fields gracefully', () => {
+    const lines = [
+      '{"type":"init"}',                              // no session_id
+      '{"type":"message","role":"assistant"}',         // no content
+      '{"type":"tool_use"}',                           // no tool_name
+      '{"type":"result","status":"success"}',          // no stats
+    ];
+    const parsed = parseGeminiJSONL(lines);
+    expect(parsed.sessionId).toBeNull();
+    expect(parsed.output).toBe('');
+    expect(parsed.toolCalls).toHaveLength(0);
+    expect(parsed.tokens).toBe(0);
+  });
+
+  test('handles multiple tool_use events', () => {
+    const lines = [
+      '{"type":"tool_use","tool_name":"run_shell_command","tool_id":"cmd_1","parameters":{"command":"ls"}}',
+      '{"type":"tool_use","tool_name":"read_file","tool_id":"cmd_2","parameters":{"path":"foo.ts"}}',
+      '{"type":"tool_use","tool_name":"run_shell_command","tool_id":"cmd_3","parameters":{"command":"cat bar.ts"}}',
+    ];
+    const parsed = parseGeminiJSONL(lines);
+    expect(parsed.toolCalls).toEqual(['run_shell_command', 'read_file', 'run_shell_command']);
+  });
+});

test/helpers/gemini-session-runner.ts

@@ -0,0 +1,201 @@
+/**
+ * Gemini CLI subprocess runner for skill E2E testing.
+ *
+ * Spawns `gemini -p` as an independent process, parses its stream-json
+ * output, and returns structured results. Follows the same pattern as
+ * codex-session-runner.ts but adapted for the Gemini CLI.
+ *
+ * Key differences from Codex session-runner:
+ * - Uses `gemini -p` instead of `codex exec`
+ * - Output is NDJSON with event types: init, message, tool_use, tool_result, result
+ * - Uses `--output-format stream-json --yolo` instead of `--json -s read-only`
+ * - No temp HOME needed — Gemini discovers skills from `.agents/skills/` in cwd
+ * - Message events are streamed with `delta: true` — must concatenate
+ */
+
+import * as path from 'path';
+
+// --- Interfaces ---
+
+export interface GeminiResult {
+  output: string;           // Full assistant message text (concatenated deltas)
+  toolCalls: string[];      // Tool names from tool_use events
+  tokens: number;           // Total tokens used
+  exitCode: number;         // Process exit code
+  durationMs: number;       // Wall clock time
+  sessionId: string | null; // Session ID from init event
+  rawLines: string[];       // Raw JSONL lines for debugging
+}
+
+// --- JSONL parser ---
+
+export interface ParsedGeminiJSONL {
+  output: string;
+  toolCalls: string[];
+  tokens: number;
+  sessionId: string | null;
+}
+
+/**
+ * Parse an array of JSONL lines from `gemini -p --output-format stream-json`.
+ * Pure function — no I/O, no side effects.
+ *
+ * Handles these Gemini event types:
+ * - init → extract session_id
+ * - message (role=assistant, delta=true) → concatenate content into output
+ * - tool_use → extract tool_name
+ * - tool_result → logged but not extracted
+ * - result → extract token usage from stats
+ */
+export function parseGeminiJSONL(lines: string[]): ParsedGeminiJSONL {
+  const outputParts: string[] = [];
+  const toolCalls: string[] = [];
+  let tokens = 0;
+  let sessionId: string | null = null;
+
+  for (const line of lines) {
+    if (!line.trim()) continue;
+    try {
+      const obj = JSON.parse(line);
+      const t = obj.type || '';
+
+      if (t === 'init') {
+        const sid = obj.session_id || '';
+        if (sid) sessionId = sid;
+      } else if (t === 'message') {
+        if (obj.role === 'assistant' && obj.content) {
+          outputParts.push(obj.content);
+        }
+      } else if (t === 'tool_use') {
+        const name = obj.tool_name || '';
+        if (name) toolCalls.push(name);
+      } else if (t === 'result') {
+        const stats = obj.stats || {};
+        tokens = (stats.total_tokens || 0);
+      }
+    } catch { /* skip malformed lines */ }
+  }
+
+  return {
+    output: outputParts.join(''),
+    toolCalls,
+    tokens,
+    sessionId,
+  };
+}
+
+// --- Main runner ---
+
+/**
+ * Run a prompt via `gemini -p` and return structured results.
+ *
+ * Spawns gemini with stream-json output, parses JSONL events,
+ * and returns a GeminiResult. Skips gracefully if gemini binary is not found.
+ */
+export async function runGeminiSkill(opts: {
+  prompt: string;           // What to ask Gemini
+  timeoutMs?: number;       // Default 300000 (5 min)
+  cwd?: string;             // Working directory (where .agents/skills/ lives)
+}): Promise<GeminiResult> {
+  const {
+    prompt,
+    timeoutMs = 300_000,
+    cwd,
+  } = opts;
+
+  const startTime = Date.now();
+
+  // Check if gemini binary exists
+  const whichResult = Bun.spawnSync(['which', 'gemini']);
+  if (whichResult.exitCode !== 0) {
+    return {
+      output: 'SKIP: gemini binary not found',
+      toolCalls: [],
+      tokens: 0,
+      exitCode: -1,
+      durationMs: Date.now() - startTime,
+      sessionId: null,
+      rawLines: [],
+    };
+  }
+
+  // Build gemini command
+  const args = ['-p', prompt, '--output-format', 'stream-json', '--yolo'];
+
+  // Spawn gemini — uses real HOME for auth, cwd for skill discovery
+  const proc = Bun.spawn(['gemini', ...args], {
+    cwd: cwd || process.cwd(),
+    stdout: 'pipe',
+    stderr: 'pipe',
+  });
+
+  // Race against timeout
+  let timedOut = false;
+  const timeoutId = setTimeout(() => {
+    timedOut = true;
+    proc.kill();
+  }, timeoutMs);
+
+  // Stream and collect JSONL from stdout
+  const collectedLines: string[] = [];
+  const stderrPromise = new Response(proc.stderr).text();
+
+  const reader = proc.stdout.getReader();
+  const decoder = new TextDecoder();
+  let buf = '';
+
+  try {
+    while (true) {
+      const { done, value } = await reader.read();
+      if (done) break;
+      buf += decoder.decode(value, { stream: true });
+      const lines = buf.split('\n');
+      buf = lines.pop() || '';
+      for (const line of lines) {
+        if (!line.trim()) continue;
+        collectedLines.push(line);
+
+        // Real-time progress to stderr
+        try {
+          const event = JSON.parse(line);
+          if (event.type === 'tool_use' && event.tool_name) {
+            const elapsed = Math.round((Date.now() - startTime) / 1000);
+            process.stderr.write(`  [gemini ${elapsed}s] tool: ${event.tool_name}\n`);
+          } else if (event.type === 'message' && event.role === 'assistant' && event.content) {
+            const elapsed = Math.round((Date.now() - startTime) / 1000);
+            process.stderr.write(`  [gemini ${elapsed}s] message: ${event.content.slice(0, 100)}\n`);
+          }
+        } catch { /* skip — parseGeminiJSONL will handle it later */ }
+      }
+    }
+  } catch { /* stream read error — fall through to exit code handling */ }
+
+  // Flush remaining buffer
+  if (buf.trim()) {
+    collectedLines.push(buf);
+  }
+
+  const stderr = await stderrPromise;
+  const exitCode = await proc.exited;
+  clearTimeout(timeoutId);
+
+  const durationMs = Date.now() - startTime;
+
+  // Parse all collected JSONL lines
+  const parsed = parseGeminiJSONL(collectedLines);
+
+  // Log stderr if non-empty (may contain auth errors, etc.)
+  if (stderr.trim()) {
+    process.stderr.write(`  [gemini stderr] ${stderr.trim().slice(0, 200)}\n`);
+  }
+
+  return {
+    output: parsed.output,
+    toolCalls: parsed.toolCalls,
+    tokens: parsed.tokens,
+    exitCode: timedOut ? 124 : exitCode,
+    durationMs,
+    sessionId: parsed.sessionId,
+    rawLines: collectedLines,
+  };
+}

test/helpers/touchfiles.ts

@@ -57,9 +57,13 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
   'review-base-branch':       ['review/**'],
   'review-design-lite':       ['review/**', 'test/fixtures/review-eval-design-slop.*'],
 
+  // Office Hours
+  'office-hours-spec-review':  ['office-hours/**', 'scripts/gen-skill-docs.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-eng-review':           ['plan-eng-review/**'],
   'plan-eng-review-artifact':  ['plan-eng-review/**'],
 
@@ -73,9 +77,17 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
   // Document-release
   'document-release': ['document-release/**'],
 
-  // Codex
+  // Codex (Claude E2E — tests /codex skill via Claude)
   'codex-review': ['codex/**'],
 
+  // Codex E2E (tests skills via Codex CLI)
+  'codex-discover-skill':  ['codex/**', '.agents/skills/**', 'test/helpers/codex-session-runner.ts'],
+  'codex-review-findings': ['review/**', '.agents/skills/gstack-review/**', 'codex/**', 'test/helpers/codex-session-runner.ts'],
+
+  // Gemini E2E (tests skills via Gemini CLI)
+  'gemini-discover-skill':  ['.agents/skills/**', 'test/helpers/gemini-session-runner.ts'],
+  'gemini-review-findings': ['review/**', '.agents/skills/gstack-review/**', 'test/helpers/gemini-session-runner.ts'],
+
   // QA bootstrap
   'qa-bootstrap': ['qa/**', 'browse/src/**', 'ship/**'],
 
@@ -136,6 +148,10 @@ export const LLM_JUDGE_TOUCHFILES: Record<string, string[]> = {
   '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'],
 
+  // 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'],
+
   // Other skills
   'retro/SKILL.md instructions':          ['retro/SKILL.md', 'retro/SKILL.md.tmpl'],
   'qa-only/SKILL.md workflow':            ['qa-only/SKILL.md', 'qa-only/SKILL.md.tmpl'],
@@ -147,6 +163,8 @@ export const LLM_JUDGE_TOUCHFILES: Record<string, string[]> = {
  */
 export const GLOBAL_TOUCHFILES = [
   'test/helpers/session-runner.ts',
+  'test/helpers/codex-session-runner.ts',
+  'test/helpers/gemini-session-runner.ts',
   'test/helpers/eval-store.ts',
   'test/helpers/llm-judge.ts',
   'scripts/gen-skill-docs.ts',