create-harness-vibe-coding 0.8.7 → 0.8.9

package/templates/common/.opencode/agents/verifier.md

@@ -0,0 +1,37 @@
+---
+description: Use to run verification commands, inspect results, and record evidence. Final acceptance still waits for cross-review PASS and reflector PASS.
+mode: subagent
+permission:
+  edit: deny
+  task: deny
+  websearch: deny
+  webfetch: deny
+---
+
+# Verifier
+
+You are a verification agent for this project harness.
+
+Load first:
+
+- `Harness/tasks/<task-id>/PROGRESS.md` and `Harness/tasks/<task-id>/PLAN.md` when available
+- current feature doc when present
+- verification commands and acceptance criteria
+
+Rules:
+
+- Do not write code.
+- Run only declared verification commands unless asked to expand coverage.
+- If a command is unavailable, record why and suggest a manual check.
+- Mark results as pass, fail, or not run with notes.
+- Do not mark work verified without evidence.
+- Do not claim final acceptance. Verification evidence is necessary but final
+  acceptance waits for cross-review PASS and reflector PASS.
+
+Return:
+
+- commands run
+- result per command
+- acceptance criteria status
+- residual risk
+- patch-ready verification update for `PLAN.md` or feature doc

package/templates/common/.opencode/commands/wf-auto-spark.md

@@ -0,0 +1,15 @@
+---
+description: Run perpetual inspiration mode via the wf-auto-spark skill
+---
+
+# /wf-auto-spark
+
+This is a **workflow command**, not a direct command. Do not execute it as a
+static help or script command.
+
+1. Load `CLAUDE.md`, `Harness/MEMORY.md` (index only per Memory Preflight), then `Harness/README.md`.
+2. Execute per the skill adapter `.claude/skills/wf-auto-spark/SKILL.md` (mirror: `.agents/skills/wf-auto-spark/SKILL.md`).
+3. Do not duplicate the workflow here. The skill adapter and `Harness/WF-AUTO-SPARK.md` are authoritative.
+
+If this runtime cannot invoke the skill directly, read
+`.claude/skills/wf-auto-spark/SKILL.md` and follow it in place.

package/templates/common/.opencode/commands/wf-auto.md

@@ -0,0 +1,15 @@
+---
+description: Run perpetual adaptive auto-optimization via the wf-auto skill
+---
+
+# /wf-auto
+
+This is a **workflow command**, not a direct command. Do not execute it as a
+static help or script command.
+
+1. Load `CLAUDE.md`, `Harness/MEMORY.md` (index only per Memory Preflight), then `Harness/README.md`.
+2. Execute per the skill adapter `.claude/skills/wf-auto/SKILL.md` (mirror: `.agents/skills/wf-auto/SKILL.md`).
+3. Do not duplicate the workflow here. The skill adapter and `Harness/WF-AUTO.md` are authoritative.
+
+If this runtime cannot invoke the skill directly, read
+`.claude/skills/wf-auto/SKILL.md` and follow it in place.

package/templates/common/.opencode/commands/wf-help.md

@@ -0,0 +1,27 @@
+---
+description: Show the Harness WF command table
+---
+# /wf-help
+
+Return this help table directly. Do not invoke a skill, do not start WF mode,
+do not dispatch agents, and do not edit files.
+
+| Command | Type | Usage | Purpose |
+| --- | --- | --- | --- |
+| `/wf-help` | direct command | `/wf-help` | Show this command table. |
+| `/wf <task>` | workflow skill | `/wf fix failing login flow` | Tiered WF: WF-Light (low-risk, planner/test/verifier), WF-Standard (multi-file, compact ACs), WF-Full (high-risk/cross-layer, full role chain). |
+| `/wf-max <task>` | workflow skill | `/wf-max refactor auth module` | WF-Max-Useful default (fan-out only where independent), WF-Max-Strict override (unconditional fan-out). |
+| `/wf-auto` | workflow skill | `/wf-auto` | Perpetual adaptive auto-optimization using project evidence, dynamic probes, risk obligations, evidence ledger, and confirmation-based exhaustion. |
+| `/wf-auto-spark` | workflow skill | `/wf-auto-spark` | Perpetual inspiration mode with roadmap anchoring and external spark search. |
+| `/wf-review <focus>` | workflow skill | `/wf-review security and test coverage` | Cross-model peer review through the other CLI; use for second opinions and risk checks. |
+| `/wf-learn` | workflow skill | `/wf-learn` | Force context-master -> memory-master learning cycle after repeated failures or closeout. |
+| `/wf-readme <task>` | workflow skill | `/wf-readme polish quickstart` | Preserve, merge, or improve README docs without trampling existing project documentation. |
+| `/wf-update` | direct command | `/wf-update` | Check/apply Harness scaffold updates with safe file classification and conflict handling. |
+| `/wf-remove` | workflow skill | `/wf-remove` | Safely remove Harness files while preserving project/user data unless explicitly purged. |
+
+Source of truth: `Harness/README.md#Skill Commands` plus installed skills under
+`.claude/skills/` (Claude Code) or `.agents/skills/` (Codex). In OpenCode the
+same skills load from `.claude/skills/`, `.agents/skills/`, and `.opencode/skills/`.
+In OpenCode, every workflow command above is also visible as a thin command
+wrapper under `.opencode/commands/` (e.g. `/wf`, `/wf-max`); each wrapper only
+routes to the matching skill adapter and does not duplicate the workflow.

package/templates/common/.opencode/commands/wf-learn.md

@@ -0,0 +1,15 @@
+---
+description: Run the context-master -> memory-master learning cycle via the wf-learn skill
+---
+
+# /wf-learn
+
+This is a **workflow command**, not a direct command. Do not execute it as a
+static help or script command.
+
+1. Load `CLAUDE.md`, `Harness/MEMORY.md` (index only per Memory Preflight), then `Harness/README.md`.
+2. Execute per the skill adapter `.claude/skills/wf-learn/SKILL.md` (mirror: `.agents/skills/wf-learn/SKILL.md`).
+3. Do not duplicate the workflow here. The skill adapter and `Harness/MEMORY_PROTOCOL.md` are authoritative.
+
+If this runtime cannot invoke the skill directly, read
+`.claude/skills/wf-learn/SKILL.md` and follow it in place.

package/templates/common/.opencode/commands/wf-max.md

@@ -0,0 +1,15 @@
+---
+description: Run the WF-MAX maximum-safe-parallelism workflow via the wf-max skill
+---
+
+# /wf-max
+
+This is a **workflow command**, not a direct command. Do not execute it as a
+static help or script command.
+
+1. Load `CLAUDE.md`, `Harness/MEMORY.md` (index only per Memory Preflight), then `Harness/README.md`.
+2. Execute per the skill adapter `.claude/skills/wf-max/SKILL.md` (mirror: `.agents/skills/wf-max/SKILL.md`).
+3. Do not duplicate the workflow here. The skill adapter and `Harness/WF-MAX.md` are authoritative.
+
+If this runtime cannot invoke the skill directly, read
+`.claude/skills/wf-max/SKILL.md` and follow it in place.

package/templates/common/.opencode/commands/wf-readme.md

@@ -0,0 +1,15 @@
+---
+description: Run the README preservation and improvement workflow via the wf-readme skill
+---
+
+# /wf-readme
+
+This is a **workflow command**, not a direct command. Do not execute it as a
+static help or script command.
+
+1. Load `CLAUDE.md`, `Harness/MEMORY.md` (index only per Memory Preflight), then `Harness/README.md`.
+2. Execute per the skill adapter `.claude/skills/wf-readme/SKILL.md` (mirror: `.agents/skills/wf-readme/SKILL.md`).
+3. Do not duplicate the workflow here. The skill adapter and the project root \`README.md\` ownership rules are authoritative.
+
+If this runtime cannot invoke the skill directly, read
+`.claude/skills/wf-readme/SKILL.md` and follow it in place.

package/templates/common/.opencode/commands/wf-remove.md

@@ -0,0 +1,15 @@
+---
+description: Run safe harness removal via the wf-remove skill
+---
+
+# /wf-remove
+
+This is a **workflow command**, not a direct command. Do not execute it as a
+static help or script command.
+
+1. Load `CLAUDE.md`, `Harness/MEMORY.md` (index only per Memory Preflight), then `Harness/README.md`.
+2. Execute per the skill adapter `.claude/skills/wf-remove/SKILL.md` (mirror: `.agents/skills/wf-remove/SKILL.md`).
+3. Do not duplicate the workflow here. The skill adapter and `Harness/scripts/wf-remove.mjs` are authoritative.
+
+If this runtime cannot invoke the skill directly, read
+`.claude/skills/wf-remove/SKILL.md` and follow it in place.

package/templates/common/.opencode/commands/wf-review.md

@@ -0,0 +1,15 @@
+---
+description: Run cross-model peer review via the wf-review skill
+---
+
+# /wf-review
+
+This is a **workflow command**, not a direct command. Do not execute it as a
+static help or script command.
+
+1. Load `CLAUDE.md`, `Harness/MEMORY.md` (index only per Memory Preflight), then `Harness/README.md`.
+2. Execute per the skill adapter `.claude/skills/wf-review/SKILL.md` (mirror: `.agents/skills/wf-review/SKILL.md`).
+3. Do not duplicate the workflow here. The skill adapter and the wf-review cross-model contract are authoritative.
+
+If this runtime cannot invoke the skill directly, read
+`.claude/skills/wf-review/SKILL.md` and follow it in place.

package/templates/common/.opencode/commands/wf-update.md

@@ -0,0 +1,24 @@
+# /wf-update
+
+Run the Harness update checker script. Do not invoke a skill or start WF mode.
+
+## Flow
+
+1. Run `node Harness/scripts/wf-update-check.mjs --json` and use the `agent` block as the action plan.
+2. Preserve all PRESERVE files. Never overwrite user task, memory, research, README, package, or architecture files.
+3. If `agent.safeApplyCommand` is present, run it to apply SAFE/NEW files first.
+4. For conflicts, compare local with `templateHint` or `remoteUrl`, decide merge/keep-local/overwrite, and record via `--accept-local`, `--accept-merged`, or `--accept-template`.
+5. Run `node Harness/scripts/wf-update-check.mjs --finalize` after all conflicts resolved.
+6. After update, run `node Harness/scripts/validate-harness.mjs` and `node Harness/scripts/scan-clean.mjs`.
+
+Codex users without a direct command surface: use `$wf-update` (skill path) or `node Harness/scripts/wf-update-check.mjs`.
+
+## Recovery
+
+If the script reports `Harness/.harness-version not found` or the update checker script itself is missing (`Harness/scripts/wf-update-check.mjs`), the Harness install predates version-tracking. Recover by regenerating missing infrastructure without overwriting user files:
+
+```
+npx create-harness-vibe-coding@latest <project-name> . -y --on-conflict skip
+```
+
+This creates missing Harness files while preserving CLAUDE.md, README.md, tasks, memory, research, and all user data. After recovery, re-run the update check.

package/templates/common/.opencode/commands/wf.md

@@ -0,0 +1,15 @@
+---
+description: Run the tiered WF workflow (WF-Light/Standard/Full) via the wf skill
+---
+
+# /wf
+
+This is a **workflow command**, not a direct command. Do not execute it as a
+static help or script command.
+
+1. Load `CLAUDE.md`, `Harness/MEMORY.md` (index only per Memory Preflight), then `Harness/README.md`.
+2. Execute per the skill adapter `.claude/skills/wf/SKILL.md` (mirror: `.agents/skills/wf/SKILL.md`).
+3. Do not duplicate the workflow here. The skill adapter and `Harness/WF.md` are authoritative.
+
+If this runtime cannot invoke the skill directly, read
+`.claude/skills/wf/SKILL.md` and follow it in place.

package/templates/common/.opencode/plugins/harness-wf-status.mjs

@@ -0,0 +1,135 @@
+import { existsSync, mkdirSync, readFileSync, rmSync, writeFileSync } from 'node:fs';
+import { spawnSync } from 'node:child_process';
+import { dirname, resolve } from 'node:path';
+
+const WF_COMMANDS = new Map([
+  ['wf', 'WF'],
+  ['wf-max', 'WF-MAX'],
+  ['wf-auto', 'WF-AUTO'],
+  ['wf-auto-spark', 'WF-AUTO-SPARK'],
+  ['wf-review', 'WF-REVIEW'],
+  ['wf-learn', 'WF-LEARN'],
+  ['wf-readme', 'WF-README'],
+  ['wf-remove', 'WF-REMOVE'],
+  ['wf-browser', 'WF-BROWSER'],
+]);
+
+function commandName(value) {
+  return String(value || '').trim().replace(/^\/+/, '').split(/\s+/)[0];
+}
+
+function runtimeDir(root) {
+  return resolve(root, 'Harness', '.runtime');
+}
+
+function modePath(root) {
+  return resolve(runtimeDir(root), 'current-mode.json');
+}
+
+function writeMode(root, mode, sessionID) {
+  mkdirSync(runtimeDir(root), { recursive: true });
+  writeFileSync(modePath(root), JSON.stringify({
+    active: true,
+    mode,
+    sessionID,
+    startedAt: new Date().toISOString(),
+    surface: 'opencode',
+  }, null, 2) + '\n', 'utf-8');
+}
+
+function readMode(root) {
+  try {
+    return JSON.parse(readFileSync(modePath(root), 'utf-8'));
+  } catch {
+    return null;
+  }
+}
+
+function clearMode(root) {
+  try {
+    rmSync(modePath(root), { force: true });
+  } catch {
+    // Best effort only.
+  }
+}
+
+function runUpdatePrompt(root, prompt) {
+  const script = resolve(root, 'Harness', 'scripts', 'wf-auto-update-prompt.mjs');
+  if (!existsSync(script)) return null;
+  const result = spawnSync(process.execPath, [script, '--format', 'json'], {
+    cwd: root,
+    input: JSON.stringify({
+      cwd: root,
+      hook_event_name: 'chat.message',
+      prompt,
+    }),
+    encoding: 'utf-8',
+    timeout: 35000,
+  });
+  if (result.error || !result.stdout?.trim()) return null;
+  try {
+    return JSON.parse(result.stdout);
+  } catch {
+    return null;
+  }
+}
+
+function textFromParts(parts) {
+  return (parts || [])
+    .filter(part => part?.type === 'text' && typeof part.text === 'string')
+    .map(part => part.text)
+    .join('\n');
+}
+
+async function showToast(client, directory, body) {
+  try {
+    await client.tui.showToast({
+      body,
+      query: { directory },
+    });
+  } catch {
+    // TUI may not be attached, for example during non-interactive runs.
+  }
+}
+
+export const HarnessWfStatusPlugin = async ({ client, directory, worktree }) => {
+  const root = worktree || directory || process.cwd();
+
+  return {
+    'chat.message': async (_input, output) => {
+      const update = runUpdatePrompt(root, textFromParts(output.parts));
+      if (!update?.message) return;
+      await showToast(client, root, {
+        title: 'Harness update available',
+        message: update.message,
+        variant: 'warning',
+        duration: 12000,
+      });
+    },
+
+    'command.execute.before': async (input) => {
+      const mode = WF_COMMANDS.get(commandName(input.command));
+      if (!mode) return;
+      writeMode(root, mode, input.sessionID);
+      await showToast(client, root, {
+        title: 'Harness',
+        message: `${mode} mode on`,
+        variant: 'info',
+        duration: 8000,
+      });
+    },
+
+    event: async ({ event }) => {
+      if (event.type !== 'session.idle') return;
+      const mode = readMode(root);
+      if (!mode?.active) return;
+      clearMode(root);
+      await showToast(client, root, {
+        title: 'Harness',
+        message: `${mode.mode} mode cleared`,
+        variant: 'success',
+        duration: 5000,
+      });
+    },
+  };
+};

package/templates/common/AGENTS.md

@@ -1,32 +1,5 @@
 # AGENTS.md
 
-Entry point for coding agents. This project uses the Harness scaffold - a 0-1 product workflow contract.
+Codex compatibility entry. Do not put workflow rules, role rules, command tables, or Harness routing here.
 
-## Startup
-
-Read `CLAUDE.md` first, then `Harness/MEMORY.md`, then `Harness/README.md`.
-Do not bulk-read `Harness/`. Let `Harness/README.md#Load By Task` route you.
-
-## WF-MAX Role Contract (READ FIRST)
-
-`/wf-max` activates WF-MAX global mode. Top-level orchestrator is **CEO** - reads, plans, dispatches. Delegated Workers follow dispatch packet (writeSet, forbidden, verification). **Global mode != every agent is CEO.**
-Closeout still requires reviewer cross-review, verifier evidence, and reflector PASS before final acceptance.
-
-| ALLOWED (W0 CEO) | FORBIDDEN (always on source) |
-|---|---|
-| Read Harness docs, CLAUDE.md | Edit / Write / MultiEdit |
-| Grep/Glob for scoping | Bash (except `ls`/`dir`/`tree`/`git`) |
-| Agent spawn (ONE message) | Deep source reads -> delegate to Worker |
-| Write PLAN.md / PROGRESS.md | Sequential spawn (AP6) |
-
-**Tempted to edit source? STOP. Spawn a Worker with explicit writeSet.**
-
-## Key Commands
-
-| Command | Purpose |
-|---------|---------|
-| `/wf-help` | Direct help table for all Harness WF commands |
-| `/wf-max [task]` | WF strict superset: complete role chain plus maximum parallelism (CEO -> Manager -> Worker, current runtime subagents first, cross-CLI overflow) |
-| `/wf-review [focus]` | Cross-model peer review (use OTHER CLI) |
-| `/wf <task>` | Standard workflow mode |
-| `/wf-auto` | Perpetual auto-optimization |
+Read `CLAUDE.md` and follow it as the single source of startup, routing, workflow, and safety instructions. If this file conflicts with `CLAUDE.md`, `CLAUDE.md` wins.

package/templates/common/CLAUDE.md

@@ -1,89 +1,115 @@
-# CLAUDE.md
-
-This repository dogfoods the generated Harness scaffold. Scaffold source files live under `templates/common/` and `templates/optional/`; generated dogfood runtime files live under root `Harness/` and `.claude/`.
-
-## 1. Harness Binding & Startup
-
-- If `Harness/` exists, this repository is governed by the Harness contract. Treat these files as mandatory operating instructions, not optional references.
-- Every session: load `Harness/MEMORY.md` first, then `Harness/README.md`.
-- If `Harness/SETUP.md` exists, follow it before normal project work; it is the install/bootstrap contract and may be deleted after setup is complete.
-
-### 1a. WF-MAX Role Contract (ACTIVE ONLY when /wf-max invoked)
-
-`/wf-max` active -> top-level orchestrator is **CEO**. Delegated Workers follow dispatch packet, edit only assigned writeSet. **Global mode != every agent is CEO.** There is no runtime hook enforcement; role/writeSet compliance is enforced by dispatch packets, review, validation, and durable task evidence.
-
-| ALLOWED (W0 CEO) | FORBIDDEN (always on source) |
-|---|---|
-| Read Harness docs, CLAUDE.md | Edit / Write / MultiEdit |
-| Grep/Glob for scoping | Bash (except `ls`/`dir`/`tree`/`git`) |
-| Agent spawn (ONE message) | Deep source reads -> delegate to Worker |
-| Write PLAN.md / PROGRESS.md | Sequential spawn (AP6) |
-
-**Tempted to edit source? STOP. Spawn a Worker with explicit writeSet.**
-
-- `Harness/MEMORY.md` is the memory/resource router: agents, skills, durable memories, and cross-session lessons. Follow its registrations when selecting agents/skills or recording memory.
-- `Harness/README.md` is the task router. For every request, check `Harness/README.md#Load By Task` and `Harness/README.md#Skill Commands`; invoke via `/wf-*` skills or `$wf-*` skills.
-- `Harness/PROGRESS.md` is the global task index. Load at session start to see active task and task history.
-- If work spans more than one step, create a task capsule from `Harness/tasks/_template/` and update `Harness/tasks/<task-id>/PROGRESS.md`.
-- Keep task records compact: PLAN holds goal, decisions, scope, risks; PROGRESS holds status/next, changes, verification. Link logs or outputs instead of pasting them.
-- Subagents are readers and reporters. Only the main agent writes to `Harness/tasks/<task-id>/PROGRESS.md` and `Harness/tasks/<task-id>/PLAN.md`.
-- Invoke multi-agent work via `subagent-orchestrator` and `Harness/subagents.md`. Update harness via `/wf-update` (see `.claude/skills/wf-update/SKILL.md`).
-- For memory writing, dispatch `memory-master`. For context analysis, dispatch `context-master`.
-- Never bulk-read `Harness/`; route through `Harness/README.md` and `Harness/MEMORY.md`.
-- Scaffold source files live under `templates/common/` and `templates/optional/`; generated dogfood runtime files live under root `Harness/` and `.claude/`.
-
-## 2. Think Before Coding
-
-- You must have **>=95% confidence** in user intent before writing implementation code.
-- If confidence is below 95%, stop and ask up to 3 blocking questions.
-- If multiple valid approaches exist and the choice affects architecture, scope, stack, or user-facing behavior, present trade-offs instead of picking silently.
+# CLAUDE.md
+
+This repository dogfoods the generated Harness scaffold. Scaffold source files live under `templates/common/` and `templates/optional/`; generated dogfood runtime files live under root `Harness/` and `.claude/`.
+
+## 1. Harness Binding & Startup
+
+If `Harness/` exists, this repository is governed by the Harness contract.
+
+At session start, after loading `CLAUDE.md`, read `Harness/memory/startup-hints.md` (L2 lightweight digest, 5-10 hints). This is NOT loading `Harness/MEMORY.md`, `Harness/README.md`, or PROGRESS — it is a minimal startup hint file only.
+
+Use **direct mode** for simple, single-step, low-risk requests: commit, push, one-line fix, file read, code question, git log, git status, or similar small operations.
+
+In direct mode, do not load the full Harness router. Inspect only the files needed for the task and execute directly.
+
+Complex work may use direct planning, task capsules, tests, and subagents without entering WF. WF mode is explicit only: the user must type `/wf`, `$wf`, `/skills wf`, `/wf-max`, `$wf-max`, `/skills wf-max`, `/wf-auto`, `$wf-auto`, `/skills wf-auto`, `/wf-auto-spark`, `$wf-auto-spark`, or `/skills wf-auto-spark` to enter WF. No other phrasing, complexity heuristic, or inferred intent triggers WF.
+
+`/wf-help` and `/wf-update` are **direct commands** — do NOT load `Harness/MEMORY.md`, do NOT enter WF, do NOT invoke a skill. Execute them immediately as static help / script commands respectively.
+
+For actual workflow commands (`/wf`, `/wf-max`, `/wf-auto`, `/wf-review`, `/wf-learn`, `/wf-readme`, `/wf-remove`, `/wf-browser`, `/wf-auto-spark`), load `Harness/MEMORY.md` first, then `Harness/README.md`.
+
+### Active Task Resume
+
+If the user says "continue", "resume", "last task", "current task", "status", "where were we", or similar resume language, or the current work is not a simple direct task:
+
+1. Read `Harness/PROGRESS.md` → find Active Task.
+2. If Active Task exists, read `Harness/tasks/<active-task>/STATE.json` first.
+3. Read `Harness/tasks/<active-task>/PROGRESS.md`.
+4. Read `Harness/tasks/<active-task>/PLAN.md` only if decisions or scope need review.
+5. From STATE.json, recover: phase, gate, tier, ready/running/blocked/done queues, activeQuestion, nextAction.
+6. Do NOT bulk-read `Harness/tasks/` to find context. Use the active pointer.
+7. Direct simple tasks may skip STATE/PLAN/PROGRESS unless the user says "continue"/"resume".
+
+See `Harness/WF-STATE.md` for the full state machine contract. Completed/abandoned tasks are archived to `Harness/tasks/_archive/` per `Harness/TASK_ARCHIVE.md`.
+
+Use **/wf** for multi-step work that needs structured coordination. Use **/wf-max** for maximum-parallelism with CEO/Manager/Worker decomposition. See `Harness/WF.md` for tier selection (WF-Light, WF-Standard, WF-Full) and `Harness/WF-MAX.md` for fan-out rules (WF-Max-Useful, WF-Max-Strict).
+
+`Harness/SETUP.md` is a bootstrap-only document: it exists only while the harness install is not yet finalized. If it exists, finish the bootstrap it describes once, then delete or archive it. Installed projects must not keep `Harness/SETUP.md` in the startup path, and normal sessions must not route through it.
+
+### 1a. WF-MAX Role Contract
+
+This section is active only when `/wf-max` is invoked.
+
+In `/wf-max`, the top-level agent is the **CEO**. The CEO owns task framing, decomposition, dispatch, review coordination, and task evidence.
+
+The CEO must not edit source files directly. Source edits must be delegated to Workers through dispatch packets with explicit boundaries.
+
+Each Worker dispatch must define: role, objective, allowed writeSet, forbidden files/actions, required verification, and expected return evidence.
+
+Workers may edit only inside their assigned writeSet. Reviewers and verifiers must be independent from the Worker whose output they evaluate.
+
+Detailed WF-MAX role rules live in `Harness/WF-KERNEL.md`, `Harness/WF-MAX.md`, and `Harness/subagents.md`.
+
+## 2. Think Before Coding
+
+- You must have **>=95% confidence** in user intent before writing implementation code.
+- If confidence is below 95%, stop and ask up to 3 blocking questions.
+- If multiple valid approaches exist and the choice affects architecture, scope, stack, or user-facing behavior, present trade-offs instead of picking silently.
 - State assumptions before implementation and record only durable assumptions, decisions, blockers, handoffs, and verification evidence in `Harness/tasks/<task-id>/PLAN.md`.
-- If something is unclear, stop. Name what is unclear and ask instead of guessing.
-- Before asserting a fact about the codebase, read the file that proves it. If you cannot cite the file and line, do not assert.
-
-## 3. Simplicity First
-
-- No features beyond what was asked.
-- No abstractions for single-use code.
-- No unrequested flexibility, configurability, or speculative error handling.
-- Use explicit interfaces or state models only when they protect a real boundary, clarify ownership, or make verification/recovery simpler.
-- If a simpler approach exists, say so and prefer the smallest change that satisfies the request.
-- If the solution is growing faster than the problem, reduce scope before coding more.
-
-## 4. Surgical Changes
-
-- Touch only files and lines required by the task.
-- Do not improve adjacent code, comments, formatting, or architecture unless it is required for the task.
-- Match existing style even when you would choose a different style in a new project.
-- Clean up imports, variables, functions, and files made unused by your own changes; do not delete pre-existing dead code unless asked.
-- Keep every changed line traceable to the user's request.
-
-## 5. Goal-Driven Execution
-
-- Define verifiable success criteria before implementation.
-- For bugs, reproduce the failure or document why reproduction is impossible before fixing.
-- For multi-step work, keep `Harness/tasks/<task-id>/PROGRESS.md` and `Harness/tasks/<task-id>/PLAN.md` current. The main agent is the only state committer; subagents return suggestions only.
-- State assumptions before implementation and record durable assumptions, decisions, blockers, handoffs, and verification evidence in `Harness/tasks/<task-id>/PLAN.md`.
-- Every task needs a test, build check, validator run, or recorded manual check.
-- Do not claim web/UI acceptance without real-browser evidence from Chrome DevTools, CDP, Playwright, or documented manual browser checks.
-- Do not place project build scripts, git conventions, run commands, or release process in this file. Put them in `README.md`.
-- Do not place code architecture here. Put architecture in `Harness/architecture.md` or the current feature doc.
-- If this file has accumulated unrelated project notes, pause and propose moving them to the right place: `README.md` for development operations, `Harness/architecture.md` for architecture, `Harness/WF.md` or `Harness/workflows/` for workflow rules.
-
-## 6. Memory & Self-Learning
-
-- `Harness/MEMORY.md` is the resource index. Detailed durable memory lives in `Harness/memory/`.
-- **Tool reflection trigger**: record a lightweight reflection when the same tool/use pattern fails 3+ times, or when a better command pattern/environment fix is found. Write it newest-first in `Harness/memory/tool-usage-reflections.md`.
-- **User correction trigger**: record a lightweight preference/correction when the user asks to remember it, or when the user corrects the same assumption/pattern 2+ times. Write it newest-first in `Harness/memory/user-corrections-preferences.md`.
-- **Agent lesson trigger**: record reusable lessons from review/debug loops in `Harness/memory/agent-lessons-patterns.md` when they would prevent recurrence.
-- **WF auto-trigger**: before WF closeout, dispatch `context-master` then `memory-master` (or use `/wf-learn`). The old "3x same failure" auto-trigger is unreliable - make this a mandatory closeout gate.
-- **Context threshold trigger**: when context approaches ~85% of the window, dispatch `context-master` to analyze and write a non-blocking compression suggestion to `Harness/tasks/<task-id>/PROGRESS.md#Heartbeat`.
-- **Closeout trigger**: during WF closeout, dispatch `context-master` to extract durable knowledge, then `memory-master` to consolidate into `Harness/memory/*`.
-- Never record secrets, credentials, tokens, or private data in memory.
-
-## 7. Mode Constraints
-
-- Never call `EnterPlanMode` - delegate planning to `planner` subagents (see `Harness/WF.md`).
-- Never write code directly in `/wf` or `/wf-max` CEO mode - delegate all implementation to Workers via dispatch packets with explicit writeSet.
-- **WF-MAX three-layer architecture**: global mode (`wf-max`) != agent role (`ceo|manager|worker|verifier|reviewer|reflector`). Workers follow dispatch packet (writeSet, forbidden, verification). Missing role/writeSet means the controller must not proceed with source edits.
-- **Enforcement**: `.claude/settings.json` denies `EnterPlanMode` via the `deny` list. WF-MAX role/writeSet compliance is not hook-enforced; it is maintained through dispatch packets, independent review, validation evidence, and the task capsule. Role contract is in [Section 1a](#1a-wf-max-role-contract-active-only-when-wf-max-invoked) - read it first.
+- If something is unclear, stop. Name what is unclear and ask instead of guessing.
+- Before asserting a fact about the codebase, read the file that proves it. If you cannot cite the file and line, do not assert.
+
+## 3. Simplicity First
+
+- No features beyond what was asked.
+- No abstractions for single-use code.
+- No unrequested flexibility, configurability, or speculative error handling.
+- Use explicit interfaces or state models only when they protect a real boundary, clarify ownership, or make verification/recovery simpler.
+- If a simpler approach exists, say so and prefer the smallest change that satisfies the request.
+- If the solution is growing faster than the problem, reduce scope before coding more.
+
+## 4. Surgical Changes
+
+- Touch only files and lines required by the task.
+- Do not improve adjacent code, comments, formatting, or architecture unless it is required for the task.
+- Match existing style even when you would choose a different style in a new project.
+- Clean up imports, variables, functions, and files made unused by your own changes; do not delete pre-existing dead code unless asked.
+- Keep every changed line traceable to the user's request.
+
+## 5. Goal-Driven Execution
+
+- Define verifiable success criteria before implementation.
+- For bugs, reproduce the failure or document why reproduction is impossible before fixing.
+- For multi-step work, keep `Harness/tasks/<task-id>/PROGRESS.md` and `Harness/tasks/<task-id>/PLAN.md` current. Only the controller or task-scribe writes task state; subagents return suggestions only.
+- State assumptions before implementation and record only durable assumptions, decisions, blockers, handoffs, and verification evidence in `Harness/tasks/<task-id>/PLAN.md`.
+- Every task needs a test, build check, validator run, or recorded manual check.
+- Do not claim web/UI acceptance without real-browser evidence from Chrome DevTools, CDP, Playwright, or documented manual browser checks.
+- Do not place project build scripts, git conventions, run commands, or release process in this file. Put them in `README.md`.
+- Do not place code architecture here. Put architecture in `Harness/architecture.md` or the current feature doc.
+- If this file has accumulated unrelated project notes, pause and propose moving them to the right place: `README.md` for development operations, `Harness/architecture.md` for architecture, `Harness/WF.md` or `Harness/workflows/` for workflow rules.
+
+## 5a. Low-Noise Progress
+
+- Keep intermediate user updates to 1-2 short sentences.
+- Do not recap the plan, paste logs, or narrate obvious file reads between steps.
+- Save full detail for the final response: changed files, verification results, risks, and commit hash when relevant.
+- For long-running work, report only meaningful phase changes, blockers, failed commands, or user decisions needed.
+
+## 6. Memory & Self-Learning
+
+`Harness/MEMORY.md` is the memory and resource router. Detailed durable memory lives under `Harness/memory/`.
+
+Do not write memory directly unless the selected workflow allows it. For workflow closeout, use the registered context and memory workflow to extract durable lessons, decisions, corrections, and reusable patterns.
+
+Keep memory compact, durable, and reusable. Do not record transient logs, raw command output, speculative notes, or information that belongs in task-local PLAN.md / PROGRESS.md.
+
+Never record secrets, credentials, tokens, or private data in memory.
+
+## 7. Mode Constraints
+
+- Never call `EnterPlanMode`. Delegate planning to `planner` subagents (see `Harness/WF.md`).
+- In `/wf` or `/wf-max`, follow the selected workflow role contract instead of improvising execution flow.
+- In `/wf-max`, the CEO must not edit source files directly. Implementation must be delegated to Workers with explicit writeSet boundaries.
+- If a Worker dispatch is missing role, objective, writeSet, forbidden scope, or verification requirements, the controller must not proceed with source edits.
+
+Keep CLAUDE.md as a thin routing and global-behavior file. Put detailed workflows in `Harness/WF.md` or `Harness/workflows/`, subagent rules in `Harness/subagents.md`, architecture in `Harness/architecture.md`, and project operations in `README.md`.

package/templates/common/Harness/ACCEPTANCE_PROTOCOL.md

@@ -27,8 +27,8 @@ Mode differences are organizational only:
 
 | Mode | Organization | Same Acceptance Flow |
 | --- | --- | --- |
-| `/wf` / `$wf` | Complete role chain | yes |
-| `/wf-max` / `$wf-max` | Complete role chain plus CEO -> Manager -> Worker fan-out | yes |
+| `/wf` / `$wf` | WF-KERNEL tier selection (WF-Light / WF-Standard / WF-Full); WF-Full uses the complete role chain | yes |
+| `/wf-max` / `$wf-max` | WF kernel plus CEO -> Manager -> Worker fan-out; WF-Max-Useful by default, WF-Max-Strict only on explicit strict request | yes |
 | `/wf-auto` / `$wf-auto` | Repeating optimization loop | yes, per cycle |
 
 ## Gates