By qwerfunch
Multi-agent development harness for Claude Code. Your AI has speed; we give it direction — through living specs and focused specialist agents.
Auto-wire mechanism · idempotency · participation · consumption spec for the four work-lifecycle ceremonies: **Kickoff · Q&A File-Drop · Design Review · Retrospective**.
Agent-routing operational spec: **conflict resolution · skip policy · feature-context inline payload · routing transparency · parallel-dispatch safety**.
Bounded autonomous loop driver — natural-language goal → researcher → planner → feature-author → execute loop, with explicit halt at every commit boundary (BR-015). Stage 1 (F-118) ships Goal primitives + read-only --status; Stage 2 (F-119) ships the full loop body.
Install the harness-boot plugin into the current project — scaffold .harness/ + wire CLAUDE.md. Run once per project. Enter via natural language or a 3-option menu.
Per-feature TDD lifecycle manager — activate · record gate result · gather evidence · transition to done (F-004). In Phase 1 the actual gate execution is on you (or CI); this command tracks the result.
The sub-agents the harness-boot plugin ships to Claude Code. Each
Accessibility auditor — cross-checks ux-architect, visual-designer, audio-designer, and frontend-engineer outputs against WCAG 2.2 and writes `.harness/_workspace/a11y/report.md`. **Read-only** — never modifies a file (same CQS principle as reviewer). Returns PASS/WARN/BLOCK; sends fixes back to the owning agent.
Auditory experience designer — produces a sound-cue catalog · volume/mix · silence policy · audio branding to `.harness/_workspace/design/audio.yaml`. Conditional summon: only when a feature has `ui_surface.has_audio: true`. Built-in standards: Earcon / Auditory Icon theory, ITU-R BS.1770 loudness, WCAG 2.2 SC 1.4.2 (audio control). Not music production (no DAW work) — only in-product interaction sounds.
Server / service / DB specialist — owns APIs, persistence, domain logic, and event pipelines. Built-in standards include Twelve-Factor App, Domain-Driven Design, REST/GraphQL, idempotency, and database normalization. Summoned for features where `features[].ui_surface.present=false`, or for pure service/domain logic. Migrations and schema changes pair with software-engineer.
UI implementation specialist — reads visual-designer's tokens.yaml + components.yaml and ux-architect's flows.md, then builds framework-neutral web/mobile/desktop components. Built-in standards: Component-Driven Development, Web Vitals, mobile-first, CSP. Summoned only when `features[].ui_surface.present=true`. Doesn't reverse-edit design outputs — if tokens or flows have an issue, kicks them back to the owning agent.
Convert a feature idea into a complete `features[]` entry for `.harness/spec.yaml` — auto-detects shape (UI / sensitive / performance / pure-domain), sizes acceptance criteria to project mode, and emits a paste-ready block for both spec.yaml mirrors. Use only on harness-boot projects (presence of `.harness/spec.yaml`).
기획 문서(plan.md 등) 또는 아키텍처 문서(architecture.md 등)를 harness-boot 의 `.harness/spec.yaml` (v2.3.8 스키마)로 변환할 때 사용. 사용자가 "기획을 스펙으로", "plan.md를 spec.yaml로", "설계문서 변환", "스펙 채우기" 등을 요청하는 경우 트리거. 변환은 정보 손실을 최소화하고 🔒 구조 / 🗒 자유텍스트 경계를 엄격히 준수하며, 담을 수 없는 덩어리는 `unrepresentable.md` 로 분리한다. 도메인별 세부 체크는 `adapters/` 하위의 도메인 어댑터로 위임.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Your AI has speed. We give it direction.
harness-boot is a multi-agent development harness for Claude Code. Where most AI tools add capability, we add focus.
A loose horse runs fast in every direction. A harnessed horse runs fast toward something.
You ──▶ ① Convert ──▶ ② Evolve ──▶ ③ Focus ──▶ ④ Collaborate ──▶ ⑤ Unify ──▶ Result
(the context) (the docs) (the rules) (the experts) (two commands)
| # | Strength | How it works | What you get |
|---|---|---|---|
| 1 | Convert | Plain-language ideas convert into an intermediate language — structured specs that every AI agent can act on directly | Same context for every agent — less guessing, sharper output |
| 2 | Evolve | Edit one place, the rest stays in sync; mismatches surface automatically; your manual tweaks survive | Design docs are always current — no manual upkeep |
| 3 | Focus | Each agent works inside its lane; completion criteria are enforced by the system, not by trust | AIs stay on the work that's theirs |
| 4 | Collaborate | Role-specialized agents follow set procedures; every decision and disagreement is recorded | Blind spots get covered, every step is traceable |
| 5 | Unify | Two slash commands. Talk to it in plain English; see the plan before anything runs | Almost nothing to memorize |
Plain language / plan.md / existing code
│
▼
┌──────────────────────────────────────────┐
│ spec.yaml (single source of truth) │
│ ├─ Ideas — vision · users │
│ └─ Rules — features · decisions │
└──────────┬─────────────────┬─────────────┘
│ │
Auto-derived Expert collaboration
│ │
▼ ▼
┌────────────────┐ ┌──────────────────────┐
│ domain.md │ │ orchestrator │
│ architecture │ │ ├─ Planning │
│ events.log │ │ ├─ Design │
│ chapters/ │ │ ├─ Implementation │
│ drift detector │ │ ├─ QA · Integration │
└────────────────┘ │ └─ Audit (read-only)│
│ + ceremonies │
└──────────────────────┘
│
▼
/harness-boot:work
(no args = dashboard · words = intent)
In Claude Code:
/plugin marketplace add qwerfunch/harness-boot
/plugin install harness-boot@harness-boot
cd my-new-project
Pick the entry point that fits — both feed into the same harness:
# A. From a one-line idea
/harness-boot:init "a simple to-do app"
# B. From an existing planning doc (plan.md, design notes, a sketch)
/harness-boot:init plan.md
Then drive every feature through the lifecycle:
/harness-boot:work
If it takes more than 5 minutes, open an issue. We'll fix it.
Use this when you want to run from a local clone — for contributors, forks, or offline setups. The repo's .claude-plugin/marketplace.json makes any clone act as a self-hosted marketplace.
Note: harness-boot is not listed in the official Claude Code marketplace yet — the
qwerfunch/harness-bootform above resolves to this GitHub repo directly.
git clone https://github.com/qwerfunch/harness-boot.git
cd harness-boot
Then in Claude Code (use the absolute path of the clone):
/plugin marketplace add /absolute/path/to/harness-boot
/plugin install harness-boot@harness-boot
To update later, git pull in the clone and run /plugin marketplace update harness-boot.
Append whatever you'd normally say after /harness-boot:work. Short keywords and full sentences both work.
Reference implementation of the Ironclad standard — multi-agent dev harness for Claude Code.
npx claudepluginhub qwerfunch/harness-boot --plugin harness-bootComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.