create-harness-vibe-coding 0.2.0 → 0.3.0

package/templates/common/docs/harness/subagents.md

@@ -4,7 +4,7 @@ Purpose: coordinate subagents for speed without losing control of scope, evidenc
 
 Use this file when work needs multiple roles, parallel reading, independent review, broad context, repeated failures, or `/wf`.
 
-project files are the only durable communication channel; chat/subagent transcript state is non-authoritative. Important assumptions, decisions, blockers, evidence, and handoffs must be written to `Harness/PLAN.md`, the current feature doc, `Harness/MEMORY.md`, or `Harness/memory/*` as appropriate.
+project files are the only durable communication channel; chat/subagent transcript state is non-authoritative. Important assumptions, decisions, blockers, evidence, and handoffs must be written to `Harness/tasks/<task-id>/PROGRESS.md` and `Harness/tasks/<task-id>/PLAN.md`, the current feature doc, `Harness/MEMORY.md`, or `Harness/memory/*` as appropriate.
 
 ## Source Attribution
 
@@ -28,12 +28,52 @@ The main agent is the controller. It owns:
 - intent confidence and user questions
 - task decomposition
 - read/write set boundaries
-- dispatch table in `Harness/PLAN.md`
+- dispatch table in `Harness/tasks/<task-id>/PLAN.md#Subagent Dispatch`
 - integration of returned summaries
 - final verification and closeout
 
 Subagents provide bounded work. They do not own final scope, architecture, release claims, or user-facing decisions.
 
+## Built-in Agent Roster
+
+Use the installed roster under `.claude/agents/` before inventing ad hoc roles.
+
+| Agent | Default Use |
+| --- | --- |
+| `planner` | decompose goals, map unknowns, define success criteria and write sets |
+| `researcher` | local/external ecosystem context, comparable projects, current facts |
+| `docs-researcher` | official docs, SDK/API behavior, browser/tool constraints |
+| `architect` | boundaries, interface decoupling, state ownership, data flow, migration risk |
+| `test-writer` | failing tests, manual check contracts, browser/API evidence plan |
+| `implementer` | bounded code or doc changes after the second plan |
+| `reviewer` | spec compliance, code quality, maintainability, security, missing tests |
+| `debugger` | reproduced failures, root cause isolation, smallest safe fix |
+| `verifier` | command execution, real browser/API checks, final evidence |
+| `memory-master` | write/consolidate memory entries, dedup, cross-project extraction; dispatched on repeated failures, user corrections, and WF closeout |
+| `context-master` | analyze context usage, recommend compression at ~85% window, extract durable session knowledge during closeout |
+
+## WF Default Fan-Out
+
+Explicit `/wf`, `wf mode`, `workflow mode`, or `wk mode` requires at least 3 distinct agents from `.claude/agents/` before second planning.
+
+Default starter set:
+
+- `planner` for decomposition and local map
+- `architect` for boundaries, interfaces, and state impact
+- `researcher` or `docs-researcher` depending whether the unknowns are project/ecosystem facts or official tool/API behavior
+
+Then add phase-specific agents:
+
+- `test-writer` before implementation
+- `implementer` for the serial write lane
+- `reviewer` for spec and code-quality gates
+- `debugger` after a reproduced verification failure
+- `verifier` for final command/browser/API evidence
+- `context-master` before closeout for knowledge extraction
+- `memory-master` after repeated failures and during closeout for consolidation
+
+The default decision ratio is a 7:3 collaboration bias: choose multi-agent collaboration for substantial or uncertain work about 70% of the time; choose solo mode only for clearly local, low-risk work that is not explicitly in WF/WK mode.
+
 ## Efficiency Ladder
 
 Choose the cheapest coordination level that is safe.
@@ -46,13 +86,13 @@ Choose the cheapest coordination level that is safe.
 | Serial build lane | normal feature or fix | test-writer -> implementer -> reviewers -> verifier |
 | Isolated lanes | disjoint write sets or competing approaches | separate worktrees, then review and merge |
 
-Default: at most three active subagents. More agents increase coordination cost and conflict risk.
+Default for automatic WF triggers: 3-5 active read-only agents before second planning. For explicit WF/WK mode, never use the solo pass unless subagents are unavailable; use bounded role passes as the recorded fallback.
 
 ## WF Orchestration Shape
 
 ```text
 controller intake
--> parallel explorer/researcher/docs-researcher/architect passes
+-> parallel planner/researcher/docs-researcher/architect subagents
 -> controller synthesis
 -> second plan with dependencies and write sets
 -> test-writer
@@ -91,8 +131,9 @@ Do not make a subagent rediscover the entire project or read the whole harness.
 - Read-only agents may run in parallel.
 - Writing agents run serially unless write sets are disjoint and the controller has chosen an isolated worktree.
 - Reviewers may run in parallel after implementation, but spec compliance is evaluated before code-quality approval.
-- Do not let two agents edit `Harness/PLAN.md`, `Harness/MEMORY.md`, or `Harness/memory/*` concurrently. The controller writes durable state.
-- If two agents disagree, the controller records the conflict in `Harness/PLAN.md` and chooses the smallest reversible next step.
+- Subagents are readers and reporters. They return findings and PLAN patch suggestions. Only the controller (main agent) commits state changes to task files.
+- Do not let two agents edit `Harness/tasks/<task-id>/PROGRESS.md`, `Harness/tasks/<task-id>/PLAN.md`, `Harness/MEMORY.md`, or `Harness/memory/*` concurrently. The controller writes durable state.
+- If two agents disagree, the controller records the conflict in `Harness/tasks/<task-id>/PLAN.md` and chooses the smallest reversible next step.
 
 ## Review Gates
 
@@ -108,7 +149,7 @@ If either reviewer finds issues, the implementer or debugger fixes them and the
 | Status | Controller Action |
 | --- | --- |
 | `DONE` | start review gates |
-| `DONE_WITH_CONCERNS` | read concerns, decide whether to address before review, record in `PLAN.md` |
+| `DONE_WITH_CONCERNS` | read concerns, decide whether to address before review, record in `Harness/tasks/<task-id>/PROGRESS.md` |
 | `NEEDS_CONTEXT` | provide only missing context and re-dispatch |
 | `BLOCKED` | change something: add context, split task, upgrade reasoning, use debugger, or ask user |
 
@@ -117,14 +158,14 @@ Never retry the same failed prompt unchanged.
 ## Failure Recovery
 
 - First failed verification: record evidence, dispatch debugger with the smallest reproduced failure.
-- Second same-class failure: narrow scope, update `PLAN.md#Heartbeat`, and add a reviewer before another fix.
+- Second same-class failure: narrow scope, update `Harness/tasks/<task-id>/PROGRESS.md#Heartbeat`, and add a reviewer before another fix.
 - Third same-class failure: stop blind fixes. Present evidence-backed options to the user.
 
 The recovery loop must preserve the same evidence standard as the main workflow: real commands, real browser/API checks when applicable, and recorded logs or artifacts.
 
 ## Synthesis Output
 
-After subagents return, the controller writes one synthesis into `Harness/PLAN.md`:
+After subagents return, the controller writes one synthesis into `Harness/tasks/<task-id>/PLAN.md`:
 
 ```text
 Agents used:

package/templates/common/docs/research/README.md

@@ -6,7 +6,7 @@ Purpose: guide agent research. Record conclusions in [research-results.md](resea
 
 Use this before PRD, stack choice, external API use, public dependency choice, pricing/legal/security assumptions, or any fact likely to change.
 
-Skip only when the task is local, narrow, and fully answerable from existing project files. Record the skip reason in `Harness/PLAN.md`.
+Skip only when the task is local, narrow, and fully answerable from existing project files. Record the skip reason in `Harness/tasks/<task-id>/PROGRESS.md`.
 
 ## Research Agent
 
@@ -21,7 +21,7 @@ Built-in agents:
 - `.claude/agents/researcher.md`: product, market, open-source, dependency, pricing, policy, and ecosystem research.
 - `.claude/agents/docs-researcher.md`: official docs, API, SDK, config, limits, errors, and examples verification.
 
-For multi-agent research plus build work, create the dispatch table in `Harness/PLAN.md` and follow `Harness/dispatch.md`.
+For multi-agent research plus build work, create the dispatch table in `Harness/tasks/<task-id>/PLAN.md` and follow `Harness/dispatch.md`.
 
 Research Agent input:
 
@@ -104,7 +104,7 @@ Use these patterns when turning research into PRD or feature docs:
 
 ## Write Target
 
-- Research process, queries, and limitations: this file or `Harness/PLAN.md`.
+- Research process, queries, and limitations: this file or `Harness/tasks/<task-id>/PROGRESS.md`.
 - Final research decisions: [research-results.md](research-results.md).
 - Product scope: [PRD.md](PRD.md).
 - Architecture consequences: `Harness/architecture.md` and `Harness/domain/ports.md`.

package/templates/common/docs/tasks/_template/ARTIFACTS.md

@@ -0,0 +1,3 @@
+# {{TASK_ID}} — Artifacts
+
+Optional: screenshots, logs, API responses, links. Create only when evidence is too large for this task's PLAN.md verification table.

package/templates/common/docs/tasks/_template/NOTES.md

@@ -0,0 +1,3 @@
+# {{TASK_ID}} — Notes
+
+Optional: exploration notes, design alternatives, research leads. Create only when notes are too long for this task's PLAN.md.

package/templates/common/docs/tasks/_template/PLAN.md

@@ -0,0 +1,40 @@
+# {{TASK_ID}} — PLAN
+
+Task-level implementation plan and evidence. Main agent writes after second planning; implementer reads before coding.
+
+## Goal
+
+## Acceptance Criteria
+
+- [ ]
+
+## Scope
+
+Allowed write set:
+- 
+
+Forbidden:
+- 
+
+## Loaded Context
+
+- 
+
+## Subagent Dispatch
+
+| Agent | Mode | Read Set | Write Set | Status |
+|-------|------|----------|-----------|--------|
+
+## Subagent Synthesis
+
+Agents used:
+Findings accepted:
+Findings rejected:
+Conflicts:
+Decisions:
+Residual risk:
+
+## Verification
+
+| Check | Result | Notes |
+|-------|--------|-------|

package/templates/common/docs/tasks/_template/PROGRESS.md

@@ -0,0 +1,29 @@
+# {{TASK_ID}} — PROGRESS
+
+Task-level progress and heartbeat. Main agent updates; subagents read only.
+
+## Current Goal
+
+## Phase
+
+Current: Intake
+
+## Heartbeat
+
+Last beat:
+Current phase: Intake
+Current blocker: none
+Next beat trigger:
+Failure count: 0
+Recovery action: none
+
+## Tasks
+
+| # | Task | Owner | Verify | Status |
+|---|------|-------|--------|--------|
+| 1 | Define goal and scope | main agent | recorded above | Pending |
+
+## Agent Handoffs
+
+| Agent | Role | Context Pack | Result |
+|-------|------|-------------|--------|

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

@@ -25,6 +25,8 @@ const commonAgents = [
   'debugger',
   'reviewer',
   'verifier',
+  'memory-master',
+  'context-master',
 ];
 
 const commonSkills = [
@@ -34,6 +36,7 @@ const commonSkills = [
   'harness-context',
   'harness-build-loop',
   'wf-mode',
+  'wf-update',
   'subagent-orchestrator',
   'readme-optimizer',
 ];
@@ -57,6 +60,7 @@ const required = [
   ...commonAgents.map(agent => `.claude/agents/${agent}.md`),
   ...commonSkills.map(skill => `.claude/skills/${skill}/SKILL.md`),
   'Harness/README.md',
+  'Harness/PROGRESS.md',
   'Harness/PLAN.md',
   'Harness/lifecycle.md',
   'Harness/subagents.md',
@@ -72,10 +76,13 @@ const required = [
   'Harness/research/research-results.md',
   'Harness/research/PRD.md',
   'Harness/domain/ports.md',
+  '.claude/skills/wf-update/SKILL.md',
+  '.claude/commands/update.md',
+  'Harness/.harness-version',
 ];
 
 const projectFacts = [
-  'Harness/PLAN.md',
+  'Harness/PROGRESS.md',
   'Harness/research/PRD.md',
   'Harness/research/research-results.md',
   'Harness/architecture.md',
@@ -93,6 +100,8 @@ const contextPacks = [
   'Reviewer:',
   'Debugger:',
   'Verifier:',
+  'Memory Master:',
+  'Context Master:',
 ];
 
 const durableCommunicationDocs = [
@@ -181,6 +190,37 @@ for (const rel of required) {
   }
 }
 
+// Task capsule template files
+const taskTemplateDir = path.join(root, 'Harness', 'tasks', '_template');
+if (!fs.existsSync(taskTemplateDir)) {
+  errors.push('missing directory: Harness/tasks/_template/');
+} else {
+  for (const f of ['PROGRESS.md', 'PLAN.md']) {
+    if (!fs.existsSync(path.join(taskTemplateDir, f))) {
+      errors.push(`missing task template file: Harness/tasks/_template/${f}`);
+    }
+  }
+}
+
+// Cross-reference: DONE files in task PLAN.md must exist on disk
+const taskDirs = fs.existsSync(path.join(root, 'Harness', 'tasks'))
+  ? fs.readdirSync(path.join(root, 'Harness', 'tasks'), { withFileTypes: true })
+      .filter(e => e.isDirectory() && e.name !== '_template')
+      .map(e => e.name)
+  : [];
+for (const taskDir of taskDirs) {
+  const planPath = `Harness/tasks/${taskDir}/PLAN.md`;
+  const planText = read(planPath);
+  if (!planText) continue;
+  const donePattern = /`([^`]+\.(?:md|mjs|js|ts|json|html|css))`[^\n]*DONE/gi;
+  for (const match of planText.matchAll(donePattern)) {
+    const claimedFile = match[1];
+    if (!fs.existsSync(path.join(root, claimedFile))) {
+      errors.push(`${planPath} claims '${claimedFile}' is DONE but file does not exist`);
+    }
+  }
+}
+
 if (fs.existsSync(path.join(root, 'Harness/research/scaffolds.md'))) {
   errors.push('legacy research file should be renamed: Harness/research/scaffolds.md -> Harness/research/research-results.md');
 }
@@ -218,17 +258,26 @@ requireText('CLAUDE.md', 'Harness/MEMORY.md` is the memory/resource router', 'me
 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/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');
 for (const heading of ['## 2. Think Before Coding', '## 3. Simplicity First', '## 4. Surgical Changes', '## 5. Goal-Driven Execution']) {
   requireText('CLAUDE.md', heading, `Karpathy-style rule heading: ${heading}`);
 }
 
+// Root PROGRESS.md structure check
+const progress = read('Harness/PROGRESS.md');
+if (progress) {
+  for (const heading of ['## Active Task', '## Task Index', '## Cross-Task Decisions']) {
+    if (!progress.includes(heading)) errors.push(`Harness/PROGRESS.md missing heading: ${heading}`);
+  }
+}
+
+// Legacy PLAN.md deprecation check (it exists as stub, no longer requires active task headings)
 const plan = read('Harness/PLAN.md');
 if (plan) {
-  for (const heading of ['## Current Goal', '## Phase', '## Heartbeat', '## Success Criteria', '## Loaded Context', '## Tasks', '## Parallel Dispatch', '## Subagent Synthesis', '## Verification']) {
-    if (!plan.includes(heading)) errors.push(`Harness/PLAN.md missing heading: ${heading}`);
-  }
-  for (const marker of ['Next beat trigger', 'Recovery action']) {
-    if (!plan.includes(marker)) errors.push(`Harness/PLAN.md missing heartbeat marker: ${marker}`);
+  if (!plan.includes('DEPRECATED')) {
+    errors.push('Harness/PLAN.md should be a deprecation stub; see Harness/PROGRESS.md');
   }
 }
 
@@ -349,13 +398,25 @@ for (const agent of commonAgents) {
 }
 
 requireText('Harness/extension.md', 'Skills should extend the harness');
-requireText('Harness/agent-workflow.md', 'Harness/PLAN.md');
+requireText('Harness/agent-workflow.md', 'Harness/tasks/<task-id>/PROGRESS.md');
 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 mode`, `workflow mode`, or `wk mode` MUST spawn at least 3 distinct subagents', 'explicit WF/WK subagent minimum');
+requireText('Harness/WF.md', '.claude/agents/', 'WF built-in agent roster path');
+requireText('Harness/WF.md', '7:3 collaboration bias', 'WF collaboration bias');
+requireText('Harness/WF.md', 'Harness/tasks/', 'WF task directory reference');
+requireText('Harness/README.md', '`/wf`, `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/harness-router/SKILL.md', '`/wf`, `wf mode`, `workflow mode`, `wk mode`', 'harness-router WF/WK aliases');
 requireText('.claude/skills/wf-mode/SKILL.md', 'Harness/WF.md', 'wf-mode loads WF document');
 requireText('.claude/skills/wf-mode/SKILL.md', 'Harness/subagents.md', 'wf-mode loads subagent orchestration');
+requireText('.claude/skills/wf-mode/SKILL.md', 'wk mode', 'wf-mode wk alias');
+requireText('.claude/skills/wf-mode/SKILL.md', 'spawn at least 3 distinct subagents from `.claude/agents/`', 'wf-mode subagent minimum');
 requireText('.claude/skills/subagent-orchestrator/SKILL.md', 'Harness/subagents.md', 'subagent-orchestrator loads subagents doc');
+requireText('.claude/skills/subagent-orchestrator/SKILL.md', '.claude/agents/', 'subagent-orchestrator built-in agent roster path');
+requireText('.claude/skills/subagent-orchestrator/SKILL.md', '`workflow mode`, `wk mode`', 'subagent-orchestrator WF/WK aliases');
 requireText('.claude/skills/harness-context/SKILL.md', 'Harness/subagents.md', 'harness-context loads subagents doc');
 requireText('.claude/skills/readme-optimizer/SKILL.md', 'README.md', 'readme-optimizer loads README');
 requireText('.claude/skills/readme-optimizer/SKILL.md', 'Harness/architecture.md', 'readme-optimizer links architecture docs');
@@ -363,8 +424,18 @@ requireText('Harness/subagents.md', '## Source Attribution', 'subagent source at
 requireText('Harness/subagents.md', 'npx skills find', 'find-skills discovery attribution');
 requireText('Harness/subagents.md', 'superpowers:dispatching-parallel-agents', 'parallel-agent source attribution');
 requireText('Harness/subagents.md', 'superpowers:subagent-driven-development', 'subagent-driven source attribution');
+requireText('Harness/subagents.md', '## Built-in Agent Roster', 'built-in agent roster');
+requireText('Harness/subagents.md', '## WF Default Fan-Out', 'WF default fan-out');
+requireText('Harness/subagents.md', '7:3 collaboration bias', 'subagent collaboration bias');
+requireText('Harness/subagents.md', 'parallel planner/researcher/docs-researcher/architect subagents', 'WF roster orchestration shape');
 requireText('Harness/subagents.md', '## Efficiency Ladder', 'subagent efficiency ladder');
 requireText('Harness/subagents.md', '## Review Gates', 'subagent review gates');
+requireText('Harness/architecture.md', '## 2. Interface Decoupling', 'architecture interface decoupling');
+requireText('Harness/architecture.md', '## 3. State Design', 'architecture state design');
+requireText('Harness/architecture.md', 'Avoid speculative abstraction', 'anti-overengineering architecture rule');
+requireText('CLAUDE.md', 'Use explicit interfaces or state models only when they protect a real boundary', 'CLAUDE interface/state simplicity rule');
+requireText('CLAUDE.md', '/wf update', 'wf update startup instruction');
+requireText('Harness/README.md', 'Need harness update', 'update routing row');
 
 if (errors.length) {
   console.error(`Harness validation failed${strict ? ' (strict)' : ''}:`);