create-harness-vibe-coding 0.8.3 → 0.8.5

package/templates/common/SETUP.md

@@ -8,14 +8,14 @@ This scaffold is a 0-1 product harness:
 
 - short agent entry files
 - dynamic docs router
-- PRD, research protocol, architecture, ports, data-flow, state templates
+- Mini PRD, acceptance protocol, UI/API contracts, research protocol, architecture, ports, data-flow, state templates
 - active `Harness/PROGRESS.md`
 - `Harness/MEMORY.md` plus a `Harness/memory/` folder for durable self-learning, user corrections, and tool reflections
 - built-in common agents
 - subagent orchestration and context-loading protocol
 - skill-style dynamic loaders in `.claude/skills/` for Claude Code and `.agents/skills/` for Codex
 - lightweight harness validator
-- test/review/feedback loop
+- acceptance/test/review/debug/memory loop
 
 It does not guess your stack or business domain. The agent MUST detect or ask, then install the right ECC rules for the project.
 
@@ -26,7 +26,7 @@ Start Claude Code or Codex, then say:
 ```text
 Read Harness/SETUP.md. Bootstrap this project as a 0-1 product harness.
 Use Harness/README.md as the router. Keep context small.
-First clarify the idea, then create PRD, research, architecture, Harness/PROGRESS.md and the first per-task plan, and the first vertical-slice task.
+First clarify the idea, then create Mini PRD, acceptance criteria, UI/API contracts, test plan, research, architecture, Harness/PROGRESS.md, the first per-task plan, and the first vertical-slice task.
 ```
 
 ## Required Bootstrap Sequence
@@ -34,16 +34,19 @@ First clarify the idea, then create PRD, research, architecture, Harness/PROGRES
 Claude must follow this order:
 
 0. **ECC Stack Configuration** — Detect the project's tech stack. If the repo is empty or has no stack markers (`package.json`, `go.mod`, `pyproject.toml`, `Cargo.toml`, `Gemfile`, `composer.json`, `build.gradle`, etc.), ask the user: "What's your tech stack? (language/framework)" Then install the matching ECC rule sets from `~/.claude/rules/ecc/`. See `Harness/ECC-GUIDE.md` for the stack→rules mapping. Minimum: always install `common/`. Verify with `ls .claude/rules/ecc/`.
-1. Read `CLAUDE.md`, `Harness/MEMORY.md`, `Harness/README.md`, and `Harness/lifecycle.md`. Load `Harness/memory/*` only when the router or memory trigger applies.
-2. Ask up to 3 blocking product questions. If not blocked, record assumptions in `Harness/tasks/<task-id>/PLAN.md`.
-3. Fill `Harness/research/PRD.md` with MVP, non-goals, and acceptance criteria.
-4. Read `Harness/research/README.md`, then fill `Harness/research/research-results.md` with adopted/rejected research choices.
-5. Fill `Harness/architecture.md`.
-6. Create a task capsule from `Harness/tasks/_template/` and fill the first vertical-slice plan in `Harness/tasks/<task-id>/PLAN.md`.
-7. Use `Harness/subagents.md`, `Harness/context-loading.md`, and `Harness/dispatch.md` when explicit WF/WK mode or any spawned subagents are involved.
-9. Implement only after a failing test or manual verification step is defined.
-10. Run `node Harness/scripts/validate-harness.mjs --strict`.
-11. Record final verification and next feedback step in `Harness/tasks/<task-id>/PROGRESS.md`. If repeated tool failures, repeated user corrections, or reusable review/debug lessons appeared, record the concise reflection in the relevant `Harness/memory/` file.
+1. Read `CLAUDE.md`, `Harness/MEMORY.md`, `Harness/README.md`, `Harness/lifecycle.md`, and `Harness/ACCEPTANCE_PROTOCOL.md`. Load `Harness/memory/*` only when the router or memory trigger applies.
+2. Ask up to 3 blocking product questions. If not blocked, record assumptions in `Harness/tasks/<task-id>/PLAN.md`.
+3. Fill `Harness/research/PRD.md` or the first task PLAN with Mini PRD fields: goal, scope, non-scope, user flow, UI elements, API behavior, acceptance criteria, and verification commands.
+4. Read `Harness/research/README.md`, then fill `Harness/research/research-results.md` with adopted/rejected research choices.
+5. Create AC IDs, UI/API contract tables, and a test plan before implementation. Use `Harness/templates/*` when helpful.
+6. Fill `Harness/architecture.md`.
+7. Create a task capsule from `Harness/tasks/_template/` and fill the first vertical-slice plan in `Harness/tasks/<task-id>/PLAN.md`.
+8. Use `Harness/AGENT_ISOLATION.md`, `Harness/subagents.md`, `Harness/context-loading.md`, and `Harness/dispatch.md` when explicit WF/WK mode or any spawned subagents are involved.
+9. Implement only after PRD-GATE, AC-GATE, CONTRACT-GATE, and TEST-GATE pass.
+10. Independently validate with an AC-by-AC result matrix; use `Harness/HARNESS_BRIDGE.md` for browser/API/CDP flows.
+11. For `/wf-auto` or memory scenario hints, read `Harness/WF-AUTO.md` and `Harness/MEMORY_PROTOCOL.md`; do not enable a background runner by default. The only allowed runtime hook is the optional `/wf-auto` bounded tick hook.
+11. Run `node Harness/scripts/validate-harness.mjs --strict`.
+12. Record final verification and next feedback step in `Harness/tasks/<task-id>/PROGRESS.md`. If repeated tool failures, repeated user corrections, or reusable review/debug lessons appeared, record the concise reflection in the relevant `Harness/memory/` file.
 
 ## Install or Upgrade Path
 
@@ -61,7 +64,7 @@ When adding this harness to a project that already has source code, docs, CI, or
 1. Get the machine-readable install report first with `npx create-harness-vibe-coding@latest <project-name> <target-dir> -y --dry-run --on-conflict skip --json`. Use `scan.markers` and `agent.aiMergeRequired` instead of hand-written root probes for install decisions. Do manual project-fact reading only after the script has created missing Harness files.
 2. Record discovered facts and open questions in `Harness/tasks/<task-id>/PROGRESS.md` before changing harness docs.
 3. Fill `Harness/research/PRD.md`, `Harness/research/research-results.md`, `Harness/architecture.md` from observed project facts plus explicit user input.
-4. Existing configuration is project fact. Do not overwrite `CLAUDE.md`, `AGENTS.md`, `.claude/`, `.agents/`, `.codex/`, `.gitignore`, settings, hooks, package files, CI, docs routers, workflow docs, or installed skills/plugins/rules unless the user explicitly approves that exact overwrite.
+4. Existing configuration is project fact. Do not overwrite `CLAUDE.md`, `AGENTS.md`, `.claude/`, `.agents/`, `.codex/`, `.gitignore`, settings, package files, CI, docs routers, workflow docs, or installed skills/plugins/rules unless the user explicitly approves that exact overwrite.
 5. When a harness file conflicts with an existing file, preserve the existing file and register any missing harness guidance manually using `Harness/extension.md`.
 6. Run `node Harness/scripts/validate-harness.mjs --strict` after project-fact placeholders have been resolved or intentionally recorded as open. Use the non-strict validator only for early structural checks.
 
@@ -174,8 +177,9 @@ Each template doc contains `{{PLACEHOLDER}}` markers. Below is what every placeh
 - `{{MUST_1..3}}`: concrete, testable MVP items (checkbox form)
 - `{{NON_GOAL_1..3}}`: explicitly out-of-scope items
 - `{{USER_ROLE}}`, `{{SCENARIO}}`, `{{FREQUENCY}}`, `{{PAIN}}`: one row per user type
-- `{{ACCEPTANCE_1..3}}`: verifiable project-level acceptance criteria
-- `{{DIMENSION}}`, `{{TARGET}}`, `{{MEASUREMENT}}`: non-functional requirements (perf, security, etc.)
+- `AC-001..003`: verifiable project-level acceptance criteria written as Given/When/Then summaries
+- UI/API contract requirements: stable selectors, endpoint contracts, state changes, and evidence methods for relevant AC IDs
+- `{{DIMENSION}}`, `{{TARGET}}`, `{{MEASUREMENT}}`: non-functional requirements (perf, security, etc.)
 
 **`Harness/research/research-results.md`** — Tech decisions. Research before filling:
 - Use `Harness/research/README.md` as the research protocol.
@@ -210,7 +214,7 @@ False confidence is worse than a question. If you catch yourself thinking "this
 
 ## How to Find Proper Skills
 
-After the architecture stage reveals your stack, inspect existing `.claude/skills/`, `.agents/skills/`, plugins, hooks, and custom rules before recommending anything. Skills teach Claude Code and Codex domain-specific patterns, testing conventions, and design rules, but duplicate skills create routing noise.
+After the architecture stage reveals your stack, inspect existing `.claude/skills/`, `.agents/skills/`, plugins, and custom rules before recommending anything. Skills teach Claude Code and Codex domain-specific patterns, testing conventions, and design rules, but duplicate skills create routing noise.
 
 **Built-in route**: invoke the `/find-skills` skill (or say "help me find skills for X"). Examples:
 
@@ -239,13 +243,13 @@ ECC and Superpowers overlap ~80% in topic coverage but serve different purposes:
 | | ECC Rules | Superpowers Skills |
 |---|------|------|
 | **Role** | Coding STANDARD (what to enforce) | Coding GUIDE (how to execute) |
-| **Enforcement** | Hooks (PreToolUse/PostToolUse), validator | Agent self-discipline |
+| **Enforcement** | Validator plus documented command evidence | Agent self-discipline |
 | **Scope** | Universal + per-language (TS/Python/Go/...) | Universal (no language specifics) |
 | **TDD** | `testing.md`: coverage ≥80%, AAA pattern | `test-driven-development`: red-green-refactor workflow |
 | **Code Review** | `code-review.md`: severity levels, checklist | `requesting-code-review`: dispatch reviewer subagent |
 | **Subagents** | `subagents.md` + `dispatch.md`: role packs, write sets | `subagent-driven-development`: two-stage review after each task |
 | **Verification** | `testing.md` + `agent-workflow.md`: evidence before claims | `verification-before-completion`: verification before claiming done |
-| **Unique** | Design quality, performance budgets, security CSP, per-language idioms, hooks | Brainstorming, git worktrees |
+| **Unique** | Design quality, performance budgets, security CSP, per-language idioms | Brainstorming, git worktrees |
 
 **Installation rule:**
 1. **ECC is mandatory.** Install `common/` + stack-specific rules during bootstrap step 0. See `Harness/ECC-GUIDE.md`.
@@ -267,7 +271,7 @@ This scaffold includes built-in harness skills in `.claude/skills/*` and mirrore
 
 ## Optional Agent Assets
 
-After the product shape is known, Claude Code may also install or copy stack-specific agents, rules, and hooks into `.claude/`. Codex-discoverable workflow skills belong in `.agents/skills/`. Follow `Harness/extension.md` for every added asset.
+After the product shape is known, Claude Code may also install or copy stack-specific agents and rules into `.claude/`. Codex-discoverable workflow skills belong in `.agents/skills/`. Follow `Harness/extension.md` for every added asset.
 
 Examples:
 

package/templates/common/scripts/validate-harness.mjs

@@ -33,11 +33,12 @@ const commonAgents = [
   'review-manager',
 ];
 
-const commonSkills = [
-  'wf',
-  'wf-update',
-  'wf-max',
-  'wf-review',
+const commonSkills = [
+  'wf',
+  'tdd',
+  'wf-update',
+  'wf-max',
+  'wf-review',
   'wf-learn',
   'subagent-orchestrator',
   'wf-readme',
@@ -56,14 +57,26 @@ const required = [
   'AGENTS.md',
   'CLAUDE.md',
   'README.md',
-  'Harness/MEMORY.md',
-  'Harness/WF.md',
-  'Harness/WF-MAX.md',
-  ...memoryFiles,
-  '.codex/config.toml',
-  '.codex/hooks.json',
-  '.claude/settings.json',
-  '.claude/rules/ecc/common.md',
+  'Harness/MEMORY.md',
+  'Harness/WF.md',
+  'Harness/WF-MAX.md',
+  'Harness/ACCEPTANCE_PROTOCOL.md',
+  'Harness/AGENT_ISOLATION.md',
+  'Harness/HARNESS_BRIDGE.md',
+  'Harness/DEBUG_PROTOCOL.md',
+  'Harness/MEMORY_PROTOCOL.md',
+  'Harness/templates/PRD.template.md',
+  'Harness/templates/ACCEPTANCE.template.md',
+  'Harness/templates/UI_CONTRACT.template.md',
+  'Harness/templates/API_CONTRACT.template.md',
+  'Harness/templates/TEST_PLAN.template.md',
+  'Harness/templates/PLAYWRIGHT_SPEC.template.ts',
+  'Harness/templates/VALIDATION_REPORT.template.md',
+  ...memoryFiles,
+  '.codex/config.toml',
+  '.claude/settings.json',
+  '.claude/commands/wf-help.md',
+  '.claude/rules/ecc/common.md',
   ...commonAgents.map(agent => `.claude/agents/${agent}.md`),
   ...commonSkills.map(skill => `.claude/skills/${skill}/SKILL.md`),
   ...commonSkills.map(skill => `.agents/skills/${skill}/SKILL.md`),
@@ -78,8 +91,8 @@ const required = [
   'Harness/architecture.md',
   'Harness/research/README.md',
   'Harness/research/research-results.md',
-  'Harness/research/PRD.md',
-  'Harness/scripts/wf-update-check.mjs',
+  'Harness/research/PRD.md',
+  'Harness/scripts/wf-update-check.mjs',
   'Harness/scripts/wf-remove.mjs',
   'Harness/scripts/scan-clean.mjs',
   'Harness/.harness-version',
@@ -121,11 +134,16 @@ function read(rel) {
   return fs.existsSync(file) ? fs.readFileSync(file, 'utf8') : '';
 }
 
-function requireText(rel, text, label = text) {
-  const body = read(rel);
-  if (body && !body.includes(text)) errors.push(`${rel} missing ${label}`);
-}
-
+function requireText(rel, text, label = text) {
+  const body = read(rel);
+  if (body && !body.includes(text)) errors.push(`${rel} missing ${label}`);
+}
+
+function forbidText(rel, text, label = text) {
+  const body = read(rel);
+  if (body && body.includes(text)) errors.push(`${rel} contains forbidden ${label}`);
+}
+
 function frontmatterField(text, field) {
   const match = text.match(new RegExp(`^${field}:\\s*(.+)$`, 'm'));
   return match ? match[1].trim() : '';
@@ -209,11 +227,25 @@ function registeredWorkflowFiles(...texts) {
   return [...files].sort();
 }
 
-for (const rel of required) {
-  if (!fs.existsSync(path.join(root, rel))) {
-    errors.push(`missing required file: ${rel}`);
-  }
-}
+for (const rel of required) {
+  if (!fs.existsSync(path.join(root, rel))) {
+    errors.push(`missing required file: ${rel}`);
+  }
+}
+
+const removedHookArtifacts = [
+  'Harness/HOOK_PROTOCOL.md',
+  'Harness/scripts/wf-mode-hook.mjs',
+  'Harness/scripts/wf-statusline.sh',
+  'Harness/scripts/wf-statusline.ps1',
+  'tests/e2e-wf-hooks.test.mjs',
+];
+
+for (const rel of removedHookArtifacts) {
+  if (fs.existsSync(path.join(root, rel))) {
+    errors.push(`removed hook artifact should not exist: ${rel}`);
+  }
+}
 
 // Task capsule template files
 const taskTemplateDir = path.join(root, 'Harness', 'tasks', '_template');
@@ -285,8 +317,9 @@ requireText('CLAUDE.md', 'user corrects the same assumption/pattern 2+ times', '
 requireText('CLAUDE.md', 'If `Harness/` exists, this repository is governed by the Harness contract', 'Harness binding contract');
 requireText('CLAUDE.md', 'Harness/MEMORY.md` is the memory/resource router', 'memory/resource router');
 requireText('CLAUDE.md', 'Harness/README.md#Load By Task', 'Harness task router');
-requireText('CLAUDE.md', 'Harness/SETUP.md` exists, follow it before normal project work', 'setup bootstrap contract');
-requireText('CLAUDE.md', 'subagent-orchestrator` and `Harness/subagents.md', 'subagent orchestrator entry trigger');
+requireText('CLAUDE.md', 'Harness/SETUP.md` exists, follow it before normal project work', 'setup bootstrap contract');
+requireText('Harness/SETUP.md', 'Harness/MEMORY_PROTOCOL.md', 'setup memory protocol reference');
+requireText('CLAUDE.md', 'subagent-orchestrator` and `Harness/subagents.md', 'subagent orchestrator entry trigger');
 requireText('CLAUDE.md', 'Harness/PROGRESS.md` is the global task index', 'PROGRESS global task index');
 requireText('CLAUDE.md', 'Harness/tasks/', 'task capsule directory reference');
 requireText('CLAUDE.md', 'Subagents are readers and reporters', 'subagent state committer rule');
@@ -443,17 +476,20 @@ for (const agent of commonAgents) {
   }
 }
 
-requireText('Harness/extension.md', 'Skills should extend the harness');
-requireText('Harness/agent-workflow.md', 'Harness/tasks/<task-id>/PROGRESS.md');
-requireText('Harness/research/README.md', 'research-results.md');
+requireText('Harness/extension.md', 'Skills should extend the harness');
+requireText('Harness/agent-workflow.md', 'Harness/tasks/<task-id>/PROGRESS.md');
+requireText('Harness/agent-workflow.md', 'TDD-GUIDE.md', 'agent workflow loads TDD guide');
+requireText('Harness/agent-workflow.md', 'real user-path test', 'agent workflow real user path requirement');
+requireText('Harness/research/README.md', 'research-results.md');
 requireText('Harness/WF.md', 'Ralph-style harness loop', 'WF loop description');
 requireText('Harness/WF.md', 'Heartbeat Protocol', 'heartbeat protocol');
 requireText('Harness/WF.md', 'WF mode requires multi-subagent orchestration by default', 'WF multi-subagent default');
 requireText('Harness/WF.md', 'Explicit `/wf`, `$wf`, `wf mode`, `workflow mode`, or `wk mode` MUST use at least 3 distinct role passes', 'explicit WF/WK role-pass minimum');
 requireText('Harness/WF.md', '.claude/agents/', 'WF built-in agent roster path');
-requireText('Harness/WF.md', 'Collaboration decision tree', 'WF decision tree');
-requireText('Harness/WF.md', 'Harness/tasks/', 'WF task directory reference');
-requireText('Harness/README.md', '`wf mode`, `workflow mode`, or `wk mode`', 'WF/WK router aliases');
+requireText('Harness/WF.md', 'Collaboration decision tree', 'WF decision tree');
+requireText('Harness/WF.md', 'Harness/tasks/', 'WF task directory reference');
+requireText('Harness/WF.md', 'IMPLEMENT-GATE', 'WF implement gate naming');
+requireText('Harness/README.md', '`wf mode`, `workflow mode`, or `wk mode`', 'WF/WK router aliases');
 requireText('Harness/README.md', 'explicit WF/WK loads subagent docs immediately', 'explicit WF/WK router output');
 requireText('.claude/skills/wf/SKILL.md', 'Harness/WF.md', 'wf skill loads core WF doc');
 requireText('.agents/skills/wf/SKILL.md', 'Harness/WF.md', 'Codex wf skill loads core WF doc');
@@ -483,16 +519,76 @@ requireText('Harness/WF-MAX.md', 'agent role', 'WF-MAX agent role separation');
 requireText('Harness/WF-MAX.md', 'write-set coloring', 'WF-MAX coloring algorithm');
 requireText('Harness/WF-MAX.md', 'wave dispatch', 'WF-MAX wave dispatch');
 requireText('Harness/README.md', '/wf-max', 'wf max router alias');
-requireText('Harness/README.md', 'WF-MAX.md', 'WF-MAX router reference');
-requireText('Harness/subagents.md', 'Max parallelism', 'subagents max parallelism row');
+requireText('Harness/README.md', 'WF-MAX.md', 'WF-MAX router reference');
+requireText('Harness/README.md', 'ACCEPTANCE_PROTOCOL.md', 'acceptance protocol router reference');
+requireText('Harness/README.md', 'TDD-GUIDE.md', 'TDD guide router reference');
+requireText('Harness/ACCEPTANCE_PROTOCOL.md', 'PRD-GATE', 'acceptance PRD gate');
+requireText('Harness/ACCEPTANCE_PROTOCOL.md', 'AC-GATE', 'acceptance AC gate');
+requireText('Harness/ACCEPTANCE_PROTOCOL.md', 'Acceptance Result', 'acceptance result matrix');
+requireText('Harness/ACCEPTANCE_PROTOCOL.md', 'Syntax-only checks', 'syntax-only checks are not browser acceptance evidence');
+requireText('Harness/AGENT_ISOLATION.md', 'implementer', 'agent isolation implementer rule');
+requireText('Harness/HARNESS_BRIDGE.md', 'Network Trace Collector', 'harness bridge network trace collector');
+requireText('Harness/WF-AUTO.md', 'Intent Checkpoint', 'wf-auto intent checkpoint');
+requireText('Harness/MEMORY_PROTOCOL.md', 'Scenario Memory Hints', 'memory protocol scenario hints');
+requireText('Harness/MEMORY_PROTOCOL.md', 'WF closeout', 'memory protocol WF closeout injection row');
+requireText('Harness/MEMORY_PROTOCOL.md', 'memory-master owns writes', 'memory protocol memory write ownership');
+requireText('Harness/TDD-GUIDE.md', 'Browser/UI Acceptance TDD Gate', 'browser UI acceptance TDD gate');
+requireText('Harness/TDD-GUIDE.md', 'syntax-only', 'syntax-only acceptance prohibition');
+requireText('Harness/TDD-GUIDE.md', 'Playwright/CDP', 'Playwright/CDP acceptance requirement');
+requireText('Harness/TDD-GUIDE.md', 'AC-by-AC result matrix', 'AC-by-AC TDD evidence matrix');
+requireText('Harness/tasks/_template/PLAN.md', 'User Action / API Request', 'task template user action/API test-plan column');
+requireText('Harness/templates/TEST_PLAN.template.md', 'syntax-only checks', 'test plan template syntax-only prohibition');
+requireText('.claude/skills/tdd/SKILL.md', 'Harness/ACCEPTANCE_PROTOCOL.md', 'tdd skill loads acceptance protocol');
+requireText('.claude/skills/tdd/SKILL.md', 'Harness/HARNESS_BRIDGE.md', 'tdd skill loads harness bridge');
+requireText('.claude/skills/tdd/SKILL.md', 'No syntax-only acceptance', 'tdd skill forbids syntax-only acceptance');
+requireText('.claude/skills/wf-remove/SKILL.md', 'User-facing removal is the slash/skill command', 'wf-remove slash command is user-facing');
+requireText('.claude/skills/wf-remove/SKILL.md', 'agent-internal execution steps', 'wf-remove script commands are agent-internal');
+requireText('.claude/skills/wf-remove/SKILL.md', 'verify residual discovery folders', 'wf-remove residual discovery verification');
+requireText('.claude/agents/tdd-guide.md', 'Browser Acceptance Rules', 'tdd-guide browser acceptance rules');
+requireText('.claude/agents/tdd-guide.md', 'real user actions', 'tdd-guide real user action requirement');
+requireText('.claude/agents/test-writer.md', 'Harness/ACCEPTANCE_PROTOCOL.md', 'test-writer loads acceptance protocol');
+requireText('.claude/agents/test-writer.md', 'real user-path test', 'test-writer real user path requirement');
+requireText('.claude/agents/test-writer.md', 'network URL, method, payload', 'test-writer network assertion requirement');
+requireText('Harness/DEBUG_PROTOCOL.md', 'Layer Classification', 'debug layer classification');
+requireText('Harness/MEMORY_PROTOCOL.md', 'AC ID', 'memory AC traceability');
+requireText('Harness/subagents.md', 'Max parallelism', 'subagents max parallelism row');
 requireText('Harness/dispatch.md', 'Concurrency group', 'dispatch concurrency group field');
 requireText('Harness/dispatch.md', 'File claim', 'dispatch file claim field');
-requireText('CLAUDE.md', '/wf-max', 'wf max startup instruction');
-requireText('CLAUDE.md', 'three-layer architecture', 'CLAUDE.md three-layer role architecture');
-requireText('Harness/scripts/wf-mode-hook.mjs', 'agentRole', 'hook agentRole validation');
-requireText('Harness/scripts/wf-mode-hook.mjs', 'writeSet', 'hook writeSet enforcement');
-
-if (errors.length) {
+requireText('CLAUDE.md', '/wf-max', 'wf max startup instruction');
+requireText('.claude/commands/wf-help.md', 'Do not invoke a skill', 'wf-help direct command boundary');
+requireText('.claude/commands/wf-help.md', '| `/wf-help` |', 'wf-help command row');
+requireText('.claude/commands/wf-help.md', '| `/wf-max <task>` |', 'wf-help wf-max row');
+requireText('.claude/commands/wf-help.md', '| `/wf-auto` |', 'wf-help wf-auto row');
+requireText('.claude/commands/wf-help.md', '| `/wf-readme <task>` |', 'wf-help wf-readme row');
+requireText('Harness/README.md', '## Direct Commands', 'direct commands section');
+requireText('Harness/README.md', '.claude/commands/wf-help.md', 'wf-help router reference');
+requireText('CLAUDE.md', 'three-layer architecture', 'CLAUDE.md three-layer role architecture');
+requireText('CLAUDE.md', 'not hook-enforced', 'CLAUDE no-hook role enforcement statement');
+requireText('Harness/README.md', 'no runtime hook state', 'README no-hook runtime statement');
+requireText('Harness/WF-AUTO.md', 'WF-AUTO Hook Exception', 'wf-auto-only hook exception');
+requireText('Harness/WF-AUTO.md', 'only `/wf-auto` may use a runtime hook', 'wf-auto-only hook boundary');
+forbidText('CLAUDE.md', 'Enforced by hooks', 'WF-MAX hook enforcement claim');
+forbidText('CLAUDE.md', 'WF-MAX hooks', 'WF-MAX hook enforcement claim');
+forbidText('Harness/README.md', 'PreToolUse hook', 'WF-MAX PreToolUse hook claim');
+forbidText('Harness/README.md', 'SessionStart hook', 'WF-MAX SessionStart hook claim');
+forbidText('Harness/README.md', 'hook-managed', 'hook-managed runtime claim');
+forbidText('Harness/README.md', 'HOOK_PROTOCOL.md', 'removed hook protocol reference');
+forbidText('Harness/WF-AUTO.md', 'Hook-Assisted Long Loop', 'wf-auto hook loop section');
+forbidText('Harness/MEMORY_PROTOCOL.md', 'Hooks may', 'hook-triggered memory claim');
+forbidText('.claude/settings.json', 'wf-mode-hook.mjs', 'Claude WF hook command registration');
+forbidText('.codex/hooks.json', 'wf-mode-hook.mjs', 'Codex WF hook command registration');
+const codexHookConfig = read('.codex/hooks.json');
+const claudeSettings = read('.claude/settings.json');
+if (codexHookConfig && !codexHookConfig.includes('wf-auto')) {
+  errors.push('.codex/hooks.json may only exist for a wf-auto hook configuration');
+}
+if (claudeSettings.includes('"hooks"') && !claudeSettings.includes('wf-auto')) {
+  errors.push('.claude/settings.json hooks may only be used for wf-auto');
+}
+if (read('.codex/config.toml').includes('hooks = true') && !codexHookConfig.includes('wf-auto')) {
+  errors.push('.codex/config.toml may enable hooks only with a wf-auto hook configuration');
+}
+if (errors.length) {
   console.error(`Harness validation failed${strict ? ' (strict)' : ''}:`);
   for (const error of errors) console.error(`- ${error}`);
   process.exit(1);