create-harness-vibe-coding 0.8.0 → 0.8.2

package/templates/common/Harness/dispatch.md

@@ -11,56 +11,36 @@ Use when work needs parallel reading, independent review, cross-layer analysis,
 - Main agent owns the final decision, integration, and verification.
 - 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.
-- Prefer three or fewer active agents (WF mode overrides this; see [WF.md](WF.md)).
+- Agent count: default (non-WF) ≤3 active agents; `/wf` requires ≥3 distinct subagents from `.claude/agents/` before second plan; `/wf max` removes the cap entirely (governed by span formula in WF-MAX.md). See [WF.md](WF.md) and [WF-MAX.md](WF-MAX.md) for the authoritative rules.
 - Read-only agents may run in parallel.
 - Writing agents run serially unless write sets are disjoint.
 - Use a worktree when two agents may touch overlapping files or long-running branches.
 - Only summaries enter main context. Load named files directly when details are needed.
 - Subagents read task files, return findings and PLAN patch suggestions. Only the main agent commits changes to PROGRESS.md and PLAN.md.
 
-## Dispatch Loop
+## Scope
 
-```text
-Goal
--> Fill task PROGRESS.md and PLAN.md
--> Apply subagents.md efficiency ladder
--> Run parallel read-only agents
--> Main agent integrates findings
--> Test Writer defines failing test or manual check
--> Implementer makes bounded change
--> Reviewer checks diff
--> Verifier records evidence
--> Main agent updates task files and closes or iterates
-```
-
-## Modes
-
-| Mode | Use When | Constraint |
-| --- | --- | --- |
-| Parallel Read | research, exploration, architecture review, docs/API check | no writes |
-| Serial Write | tests, implementation, docs sync | one writer at a time |
-| Isolated Worktree | overlapping write sets or competing approaches | merge only after review |
+`agent-workflow.md` owns the build/review loop. `subagents.md` owns orchestration strategy and agent roster. This file owns the dispatch input and subagent handoff formats.
 
-## Common Agents
+## Agent Roster
 
 | Agent | Mode | Purpose |
 | --- | --- | --- |
-| `planner` | Parallel Read | split goal into tasks, dependencies, write sets |
-| Explorer Pass | Parallel Read | bounded read-only exploration when no dedicated agent is needed |
-| `researcher` | Parallel Read | product, market, ecosystem, dependency research |
-| `docs-researcher` | Parallel Read | official docs, API, SDK, version, limits |
-| `architect` | Parallel Read | layer boundaries, ports, data flow, state impact |
-| `test-writer` | Serial Write | failing test or manual verification plan |
-| `implementer` | Serial Write | minimal change inside declared write set |
-| `debugger` | Serial Write | smallest fix for a reproduced failure |
-| `reviewer` | Parallel Read | diff review, risks, missing tests |
-| `verifier` | Parallel Read | run checks and record evidence |
-| `memory-master` | Serial Write | write/consolidate memory entries, dedup, cross-project extraction |
-| `context-master` | Parallel Read | analyze context usage, recommend compression, extract session knowledge |
-| `explore-manager` | Parallel Read | WF-MAX W0: spawn 5-10 researchers, synthesize, report to CEO |
-| `architect-manager` | Parallel Read | WF-MAX W1: spawn 3 architects, synthesize interface contracts |
-| `implement-manager` | Serial Write | WF-MAX W2: spawn implementers (one file_claim each), merge results |
-| `review-manager` | Parallel Read | WF-MAX W2R: spawn 3-4 reviewers, deduplicate, classify severity |
+| `planner` | Read | split goal into tasks, dependencies, write sets |
+| `researcher` | Read | product, market, ecosystem, dependency research |
+| `docs-researcher` | Read | official docs, API, SDK, version, limits |
+| `architect` | Read | layer boundaries, ports, data flow, state impact |
+| `test-writer` | Write | failing test or manual verification plan |
+| `implementer` | Write | minimal change inside declared write set |
+| `debugger` | Write | smallest fix for a reproduced failure |
+| `reviewer` | Read | diff review, risks, missing tests |
+| `verifier` | Read | run checks and record evidence |
+| `memory-master` | Write | write/consolidate memory entries |
+| `context-master` | Read | analyze context, recommend compression |
+| `explore-manager` | Read | WF-MAX W0: spawn researchers, synthesize |
+| `architect-manager` | Read | WF-MAX W1: spawn architects, synthesize |
+| `implement-manager` | Write | WF-MAX W2: spawn implementers |
+| `review-manager` | Read | WF-MAX W2R: spawn reviewers, deduplicate |
 
 ## Dispatch Rules
 
@@ -71,7 +51,24 @@ Goal
 - If docs, tests, and code disagree, stop implementation and record the conflict in `Harness/tasks/<task-id>/PROGRESS.md`.
 - In /wf max, file claims must respect WF-MAX.md leaf condition: no split below 50 avgLines, no split when files ≤ span×2.
 
-## Handoff Format
+## Dispatch Input (Controller → Subagent)
+
+The controller MUST include these fields in the subagent's dispatch packet.
+Without them, the subagent has no way to know which rules or contracts to load.
+
+```text
+Role:               <installed agent name or bounded role, e.g. planner, implementer-fe, reviewer, memory-master>
+Task:               <one-sentence goal>
+ECC:                <which ECC rules to load, e.g. web/design-quality.md, python/fastapi.md. See context-loading.md#ecc-rules-per-role>
+Skills:             <which skills to activate, e.g. react-review, tdd-guide>
+API contract:       <path to api/openapi.yaml, if frontend↔backend task. Omit if N/A>
+Read set:           <files and directories the subagent may read>
+Write set:          <files the subagent may modify. "none" = read-only>
+Forbidden:          <commands, paths, or patterns the subagent must not touch>
+Verification:       <commands to run after implementation, e.g. npm test>
+```
+
+## Handoff Format (Subagent → Controller)
 
 Subagents return summaries in this shape:
 
@@ -79,6 +76,9 @@ Subagents return summaries in this shape:
 Agent:
 Task:
 Mode:
+ECC loaded:         <which ECC rule files were actually loaded. Should match dispatch ECC field.>
+Skills active:      <which skills were active. Should match dispatch Skills field.>
+API contract:       <path to contract file used, if applicable>
 Files read:
 Files changed:
 Findings:

package/templates/common/Harness/subagents.md

@@ -111,33 +111,19 @@ Use this shape for `/wf`, long tasks, multi-file changes, architecture work, mig
 /wf max orchestration shape:
 controller intake
 -> wave 0: max-parallel exploration (4-14 read-only agents)
--> controller synthesis: dependency graph + write-set coloring
--> wave 1: N parallel implementers (disjoint file claims)
--> wave 1 review: parallel spec/code/security reviewers
--> wave 2+: dependent implementers (if any)
+-> E-GATE: Exploration Gate — all questions answered, findings synthesized (per WF-MAX.md)
+-> wave 1: architecture — 3 parallel architects → boundary decisions + interface contract
+-> D-GATE: Write Decomposition Gate — Dispatch Table + Self-Audit for write-set (MANDATORY, per WF-MAX.md)
+-> wave 2: N parallel implementers (disjoint file claims, ALL spawned in ONE message)
+-> wave 2 review: parallel spec/code/security reviewers
+-> wave 3+: dependent implementers (if any; re-run D-GATE if write-set changed)
 -> integration verifier
 -> closeout with evidence
 ```
 
 ## Dispatch Pack
 
-Every subagent dispatch must be self-contained:
-
-```text
-Role:
-Goal:
-Mode: read-only | write
-Read set:
-Write set:
-Forbidden scope:
-Injected docs:
-Dependencies:
-Expected evidence:
-Stop condition:
-Return format:
-```
-
-Do not make a subagent rediscover the entire project or read the whole harness. Inject only the docs selected by `Harness/README.md` and `Harness/context-loading.md`.
+Use the canonical dispatch input and handoff format in `Harness/dispatch.md`. Every subagent dispatch must be self-contained — inject only the docs selected by `Harness/README.md` and `Harness/context-loading.md`.
 
 ## Parallelism Rules
 

package/templates/common/Harness/tasks/_template/NAMING.md

@@ -0,0 +1,47 @@
+# Task Naming Convention
+
+## Format
+
+```
+task-<verb>-<noun>[-detail]
+```
+
+All task directories MUST have the `task-` prefix. This distinguishes tasks from system directories at a glance.
+
+## Rules
+
+| Rule | Example ✓ | Example ✗ |
+|------|-----------|-----------|
+| `task-` prefix required | `task-fix-ceo-inheritance` | `fix-ceo-inheritance` |
+| kebab-case (lowercase, hyphens) | `task-fix-ceo-inheritance` | `task-fix_ceo_inheritance` |
+| Verb-first after prefix | `task-add-goal-persistence` | `task-goal-persistence-add` |
+| 2-5 words after prefix, ≤46 total chars | `task-refactor-hook-role` | `task-refactor-the-entire-hook-role-model` |
+| No abbreviations unless domain-standard | `task-fix-auth-middleware` | `task-fx-ath-mdw` |
+
+## Reserved Names
+
+| Name | Purpose |
+|------|---------|
+| `_template` | Task capsule template (never a real task) |
+| `auto` | Auto-mode capsule (shared by `/wf-auto` and `/wf-auto-spark`) |
+
+## Task ID Lifecycle
+
+1. Created by copying `_template/` → `task-<verb>-<noun>/`
+2. Directory name IS the task ID — used in `Harness/PROGRESS.md`, hooks, dispatch packets
+3. Directory archived (not renamed) when task completes
+4. Task ID is immutable after creation (changing it breaks cross-references)
+5. Existing tasks without `task-` prefix are grandfathered — rename is optional but recommended
+
+## Examples
+
+```
+task-add-dark-mode-support
+task-fix-auth-token-expiry
+task-update-harness-lifecycle-docs
+task-remove-legacy-config-files
+task-refactor-agent-dispatch-model
+task-migrate-to-esm-imports
+task-audit-security-headers
+task-benchmark-wf-max-throughput
+```

package/templates/common/MEMORY.md

@@ -1,30 +1,30 @@
-# MEMORY.md - create-harness-vibe-coding Project Resource Index
-
-> The project fact source is reached via `CLAUDE.md -> Harness/README.md`. This file persists cross-session context: resource index, user preferences, tool usage standards.
-> Detailed memory lives in `Harness/memory/`. Keep entries short, newest first, and free of secrets.
-
-## Agents (Sub-agents)
-
-- [researcher](../.claude/agents/researcher.md) — product, market, open-source, dependency, pricing, policy, and ecosystem research.
-- [docs-researcher](../.claude/agents/docs-researcher.md) — official docs, API, SDK, config, limits, errors, and examples verification.
-- [planner](../.claude/agents/planner.md) — task split, dependencies, write sets, and dispatch table.
-- [architect](../.claude/agents/architect.md) — boundaries, ports, data-flow, and state impact.
-- [test-writer](../.claude/agents/test-writer.md) — failing tests or manual verification before implementation.
-- [implementer](../.claude/agents/implementer.md) — bounded implementation inside declared write set.
-- [debugger](../.claude/agents/debugger.md) — smallest fix for a reproduced failure.
-- [reviewer](../.claude/agents/reviewer.md) — read-only diff review and closeout risk.
-- [verifier](../.claude/agents/verifier.md) — verification commands and evidence.
-- [memory-master](../.claude/agents/memory-master.md) — memory writing, dedup, consolidation, and cross-project knowledge extraction.
-- [context-master](../.claude/agents/context-master.md) — context analysis, compression alerts, and session knowledge extraction for memory-master.
-- [explore-manager](../.claude/agents/explore-manager.md) — WF-MAX W0 exploration: spawn 5-10 read-only researchers, synthesize, report to CEO.
-- [architect-manager](../.claude/agents/architect-manager.md) — WF-MAX W1 architecture: spawn 3 architects, synthesize interface contracts, report to CEO.
-- [implement-manager](../.claude/agents/implement-manager.md) — WF-MAX W2 implementation: spawn 5-7 implementers (one file_claim each), merge, report to CEO.
-- [review-manager](../.claude/agents/review-manager.md) — WF-MAX W2R review: spawn 3-4 reviewers (spec/code/security/perf), deduplicate, classify severity, report to CEO.
-
-Stack-specific agents can be added after the product shape is known.
-
-## Skills (Workflows)
-
+# MEMORY.md - create-harness-vibe-coding Project Resource Index
+
+> The project fact source is reached via `CLAUDE.md -> Harness/README.md`. This file persists cross-session context: resource index, user preferences, tool usage standards.
+> Detailed memory lives in `Harness/memory/`. Keep entries short, newest first, and free of secrets.
+
+## Agents (Sub-agents)
+
+- [researcher](../.claude/agents/researcher.md) — product, market, open-source, dependency, pricing, policy, and ecosystem research.
+- [docs-researcher](../.claude/agents/docs-researcher.md) — official docs, API, SDK, config, limits, errors, and examples verification.
+- [planner](../.claude/agents/planner.md) — task split, dependencies, write sets, and dispatch table.
+- [architect](../.claude/agents/architect.md) — boundaries, ports, data-flow, and state impact.
+- [test-writer](../.claude/agents/test-writer.md) — failing tests or manual verification before implementation.
+- [implementer](../.claude/agents/implementer.md) — bounded implementation inside declared write set.
+- [debugger](../.claude/agents/debugger.md) — smallest fix for a reproduced failure.
+- [reviewer](../.claude/agents/reviewer.md) — read-only diff review and closeout risk.
+- [verifier](../.claude/agents/verifier.md) — verification commands and evidence.
+- [memory-master](../.claude/agents/memory-master.md) — memory writing, dedup, consolidation, and cross-project knowledge extraction.
+- [context-master](../.claude/agents/context-master.md) — context analysis, compression alerts, and session knowledge extraction for memory-master.
+- [explore-manager](../.claude/agents/explore-manager.md) — WF-MAX W0 exploration: spawn 5-10 read-only researchers, synthesize, report to CEO.
+- [architect-manager](../.claude/agents/architect-manager.md) — WF-MAX W1 architecture: spawn 3 architects, synthesize interface contracts, report to CEO.
+- [implement-manager](../.claude/agents/implement-manager.md) — WF-MAX W2 implementation: spawn 5-7 implementers (one file_claim each), merge, report to CEO.
+- [review-manager](../.claude/agents/review-manager.md) — WF-MAX W2R review: spawn 3-4 reviewers (spec/code/security/perf), deduplicate, classify severity, report to CEO.
+
+Stack-specific agents can be added after the product shape is known.
+
+## Skills (Workflows)
+
 - [WF Mode](WF.md) — long-task workflow: exploration, second plan, implementation, review, verification, heartbeat, and recovery loop.
 - [wf](../.claude/skills/wf/SKILL.md) — Claude Code WF skill command; mirrored for Codex at `../.agents/skills/wf/SKILL.md`.
 - [subagent-orchestrator](../.claude/skills/subagent-orchestrator/SKILL.md) — controller-led subagent orchestration, parallel read-only passes, review gates, and recovery handoffs.
@@ -33,45 +33,52 @@ Stack-specific agents can be added after the product shape is known.
 - [wf-update](../.claude/skills/wf-update/SKILL.md) — GitHub-based incremental harness update, checksum comparison, and safe in-place updates.
 - [wf-learn](../.claude/skills/wf-learn/SKILL.md) — force memory learning cycle: context-master -> memory-master -> project + global memory.
 - [wf-max](../.claude/skills/wf-max/SKILL.md) — maximum-parallelism workflow: write-set coloring, wave dispatch, parallel review per dimension.
+- [wf-auto](../.claude/skills/wf-auto/SKILL.md) — perpetual auto-optimization: 8-angle internal scan, intent checkpoints, evidence ledger.
+- [wf-auto-spark](../.claude/skills/wf-auto-spark/SKILL.md) — perpetual inspiration mode: external spark search, long-term roadmap with staged milestones, ≤50% deviation guard.
+- [tdd](../.claude/skills/tdd/SKILL.md) — test-driven development: red-green-refactor, ≥80% coverage gate, enforces tests-first methodology.
 	- [wf-remove](../.claude/skills/wf-remove/SKILL.md) — Safely remove Harness framework files (SAFE/MODIFIED/USER classes), auto-prune empty directories, backup option.
 
 Codex repo-skill mirrors live under `../.agents/skills/` with the same skill names.
-
-Stack-specific skills can be added after the product shape is known.
-
-## Rules (Harness Constraints)
-
-Located under `.claude/rules/ecc/`, auto-loaded by the CC engine:
-
-- [common.md](../.claude/rules/ecc/common.md) — universal harness constraints for context loading, verification, subagents, and security (alwaysApply: true)
-- Language-specific rules pending Claude Code initialization (e.g. python.md, typescript.md, etc.)
-
-## Harness (Runtime)
-
-- [Docs router](README.md)
-- [WF mode](WF.md)
-- [WF Max mode](WF-MAX.md)
-- [0-1 lifecycle](lifecycle.md)
-- [Research protocol](research/README.md)
-- [Context loading protocol](context-loading.md)
-- [Dispatch protocol](dispatch.md)
-- [Subagent orchestration](subagents.md)
-- [Extension contract](extension.md)
-- [Architecture docs](architecture.md)
-- [Agent workflow](agent-workflow.md)
-- [Harness validator](scripts/validate-harness.mjs)
-- [Version file](.harness-version)
-
-## Memory Folder
-
-- [Tool usage/reflections](memory/tool-usage-reflections.md) - repeated tool failures, better command patterns, environment-specific fixes.
-- [User corrections/preferences](memory/user-corrections-preferences.md) - repeated user corrections, durable preferences, common-sense course corrections.
-- [Agent lessons/patterns](memory/agent-lessons-patterns.md) - reusable lessons from review, debugging, validation, and handoff loops.
-
-Write to the memory folder when the guidance should survive chat context loss:
-
-- Use `memory/tool-usage-reflections.md` when the same tool/use pattern fails 3+ times, a better command pattern is found, or an environment-specific fix should be reused.
-- Use `memory/user-corrections-preferences.md` when the user explicitly asks to remember a preference, or the user corrects the same assumption/pattern 2+ times.
-- Use `memory/agent-lessons-patterns.md` when a review/debug loop yields a reusable lesson or regression guard.
-- Use this file for the resource index and routing pointers, not long-form lessons.
-- Never record secrets, credentials, tokens, or private data. If a memory is ambiguous, ask before writing.
+
+Stack-specific skills can be added after the product shape is known.
+
+- [browser-e2e](workflows/browser-e2e.md)
+
+Stack-specific skills can be added after the product shape is known.
+
+## Rules (Harness Constraints)
+
+Located under `.claude/rules/ecc/`, auto-loaded by the CC engine:
+
+- [common.md](../.claude/rules/ecc/common.md) — universal harness constraints for context loading, verification, subagents, and security (alwaysApply: true)
+- Language-specific rules pending Claude Code initialization (e.g. python.md, typescript.md, etc.)
+
+## Harness (Runtime)
+
+- [Docs router](README.md)
+- [WF mode](WF.md)
+- [WF Max mode](WF-MAX.md)
+- [0-1 lifecycle](lifecycle.md)
+- [Research protocol](research/README.md)
+- [Context loading protocol](context-loading.md)
+- [Dispatch protocol](dispatch.md)
+- [Subagent orchestration](subagents.md)
+- [Extension contract](extension.md)
+- [Architecture docs](architecture.md)
+- [Agent workflow](agent-workflow.md)
+- [Harness validator](scripts/validate-harness.mjs)
+- [Version file](.harness-version)
+
+## Memory Folder
+
+- [Tool usage/reflections](memory/tool-usage-reflections.md) - repeated tool failures, better command patterns, environment-specific fixes.
+- [User corrections/preferences](memory/user-corrections-preferences.md) - repeated user corrections, durable preferences, common-sense course corrections.
+- [Agent lessons/patterns](memory/agent-lessons-patterns.md) - reusable lessons from review, debugging, validation, and handoff loops.
+
+Write to the memory folder when the guidance should survive chat context loss:
+
+- Use `memory/tool-usage-reflections.md` when the same tool/use pattern fails 3+ times, a better command pattern is found, or an environment-specific fix should be reused.
+- Use `memory/user-corrections-preferences.md` when the user explicitly asks to remember a preference, or the user corrects the same assumption/pattern 2+ times.
+- Use `memory/agent-lessons-patterns.md` when a review/debug loop yields a reusable lesson or regression guard.
+- Use this file for the resource index and routing pointers, not long-form lessons.
+- Never record secrets, credentials, tokens, or private data. If a memory is ambiguous, ask before writing.