본문으로 건너뛰기
TakoAPI
스킬로 돌아가기
—아직 평가 없음
내 평가

요약

Production-ready spec driven development setup for AI coding agents in any repo with one command. Pre-configured with 11 agents, 22 skills, 18 rules, 25 commands & MCP integrations for Cursor, GitHub Copilot, Claude Code, Windsurf, Amp, Codex, Gemini CLI, Cline & OpenCode.

설명

# hatch3r

[![npm version](https://img.shields.io/npm/v/hatch3r.svg)](https://www.npmjs.com/package/hatch3r)

**Crack the egg. Hatch better agents.**

hatch3r is an open-source CLI and Cursor plugin that installs a battle-tested, tool-agnostic agentic coding setup into any repository. Ship Ready as of Cycle 8 (audit score 83.74/100, 0 Critical findings, 15 platform adapters wired, 19-domain governance audit cycle operational). One command gives you up to 16 agents, 26 skills, 27 rules, 34 commands, and MCP integrations -- optimized for your coding tool of choice. Selective init installs only what you need based on your project type and team size. (Authoritative counts: [`governance/inventory.json`](governance/inventory.json), regenerated by `npm run inventory`.)

## Quick Start

Requires Node.js 22+.

```bash
npx hatch3r init
```

That's it. hatch3r detects your repo, asks about your project context (greenfield/brownfield, solo/team), lets you choose a content profile (minimal/standard/full/custom), and generates everything. The platform (GitHub, Azure DevOps, or GitLab) is auto-detected from your git remote. Run into issues? See [Troubleshooting](https://docs.hatch3r.com/docs/troubleshooting).

## What You Get

| Category | Count | Highlights |
|----------|-------|-----------|
| **Agents** | 16 | Code reviewer, test writer, security auditor, implementer (sub-agentic), fixer, researcher, architect, DevOps, and more |
| **Skills** | 26 | Bug fix, feature implementation, issue workflow, release, incident response, context health, cost tracking, recipes, API spec, CI pipeline, migration, customization, and more |
| **Rules** | 27 | Code standards, testing, API design, observability, theming, i18n, security patterns, agent orchestration, deep context analysis, and more |
| **Commands** | 34 | Board management, planning (feature, bug, refactor, test), workflow, quick-change, revision, debug, healthcheck, security-audit, cost-tracking, onboard, benchmark, customization, and more |
| **MCP Servers** | 10 (3 default + 7 opt-in) | Playwright, Context7, Filesystem (default); GitHub, Brave Search, Sentry, Postgres, Linear, Azure DevOps, GitLab (opt-in) |
| **Platforms** | 3 | GitHub, Azure DevOps, GitLab -- auto-detected from git remote |

## Supported Tools (15 Adapters)

| Tool | Output |
|------|--------|
| **Cursor** | `.mdc` rules, agents, skills, commands, MCP config |
| **GitHub Copilot** | instructions, prompts, GitHub agents |
| **Claude Code** | `CLAUDE.md`, skills, `.mcp.json` |
| **OpenCode** | `AGENTS.md`, `opencode.json` |
| **Windsurf** | `.windsurfrules` |
| **Amp** | `AGENTS.md` |
| **Codex CLI** | `AGENTS.md`, `codex.md` |
| **Gemini CLI** | `GEMINI.md` |
| **Cline / Roo Code** | `.clinerules` |
| **Aider** | `CONVENTIONS.md` |
| **Kiro** | `.kiro/steering/`, `.kiro/settings/mcp.json` |
| **Goose** | `.goosehints` |
| **Zed** | `.rules` |
| **Amazon Q** | `.amazonq/rules/`, `.amazonq/mcp.json` |
| **Antigravity** | `.antigravity/rules.md`, `.antigravity/settings.json` |

Platform is auto-detected from your git remote during `hatch3r init`. All board commands, agents, rules, and skills adapt to your selected platform.

## How It Works

```
.agents/              <- Canonical source (tool-agnostic)
  ├── agents/
  ├── skills/
  ├── rules/
  ├── commands/
  ├── mcp/
  ├── AGENTS.md
  └── hatch.json       <- Manifest

.cursor/               <- Generated (Cursor adapter)
.github/               <- Generated (Copilot adapter)
CLAUDE.md              <- Generated (Claude adapter)
.windsurfrules         <- Generated (Windsurf adapter)
AGENTS.md              <- Generated (OpenCode, Amp, Codex adapters)
GEMINI.md              <- Generated (Gemini adapter)
.clinerules            <- Generated (Cline adapter)
CONVENTIONS.md         <- Generated (Aider adapter)
.kiro/                 <- Generated (Kiro adapter)
.goosehints            <- Generated (Goose adapter)
.rules                 <- Generated (Zed adapter)
.amazonq/              <- Generated (Amazon Q adapter)
.antigravity/          <- Generated (Antigravity adapter)
.worktreeinclude       <- Generated (worktree isolation)
```

hatch3r keeps one source of truth in `.agents/` and generates native configuration for each tool.

## Multi-Repo Workspaces

hatch3r can manage multiple git repos from a single workspace root. Run `hatch3r init` in a non-git directory containing git subdirectories and it auto-detects the workspace layout.

```
my-platform/                   <- Workspace root (not a git repo)
  .agents/                     <- Shared canonical source
    workspace.json             <- Workspace manifest
    hatch.json
    agents/
    rules/
    ...
  frontend/                    <- Git repo (gets its own generated files)
    .cursor/
    CLAUDE.md
    ...
  backend/                     <- Git repo
    .cursor/
    CLAUDE.md
    ...
  infra/                       <- Git repo
    .cursor/
    CLAUDE.md
    ...
```

```bash
npx hatch3r init --workspace              # force workspace mode
npx hatch3r sync                          # cascade to all repos
npx hatch3r sync --repos frontend backend # sync specific repos
npx hatch3r sync --dry-run                # preview changes
npx hatch3r config                        # manage repos and sync strategy
```

Content flows from workspace defaults into each sub-repo with optional per-repo overrides (tools, features, include/exclude content). Sub-repos receive independent copies, not symlinks. See the [Workspace guide](https://docs.hatch3r.com/docs/guides/workspace) for full details.

## Workflow

hatch3r provides a full project lifecycle, from setup to release:

1. **Initialize** -- `npx hatch3r init` detects your repo and platform, asks about context and profile, generates agents/skills/rules/commands/MCP. For headless CI, pass `--yes` with optional flags. See [agentic process diagrams](https://docs.hatch3r.com/docs/guides/agentic-process).
2. **Set up the board** -- `hatch3r-board-init` creates or connects a Projects V2 board with status fields, label taxonomy, and config writeback.
3. **Define work** -- Create a `todo.md` at the project root (one item per line).
4. **Fill the board** -- `hatch3r-board-fill` parses `todo.md`, classifies items, groups into epics, builds a dependency DAG, and marks issues `status:ready`.
5. **Groom the backlog** -- `hatch3r-board-groom` surfaces stale items, priority imbalances, and decomposition candidates for selective refinement.
6. **Pick up work** -- `hatch3r-board-pickup` auto-selects the next issue by dependency order and priority, creates a branch, delegates implementation, and opens a PR.
7. **Review cycle** -- Reviewer + fixer agents loop (max 3 iterations) until clean, then test-writer and security-auditor run final checks.
8. **Release** -- `hatch3r-release` determines the semver bump, generates a changelog, tags, and publishes.

> **After init:** For greenfield, run `hatch3r-project-spec` then `hatch3r-roadmap`. For brownfield, run `hatch3r-codebase-map`. For a single feature, run `hatch3r-feature-plan`. For small changes, run `hatch3r-quick-change`.

## Commands

### CLI Commands

```bash
npx hatch3r init          # Interactive setup
npx hatch3r config        # Reconfigure tools, MCP servers, features, and platform
npx hatch3r sync          # Re-generate from canonical state
npx hatch3r update        # Pull latest templates (safe merge)
npx hatch3r status        # Check sync status between canonical and generated files
npx hatch3r validate      # Validate canonical .agents/ structure
npx hatch3r verify        # Verify file integrity checksums
npx hatch3r clean                 # Remove generated files (optional --reinit)
npx hatch3r worktree-setup <path>  # Set up gitignored files in a worktree
npx hatch3r worktree-cleanup <path> # Clean up worktree-specific files
npx hatch3r add <pack>    # Install a community pack (coming soon)
```

### Agent Commands

These commands are invoked inside your coding tool (e.g., as Cursor commands).

**Board management:** `board-init`, `board-fill`, `board-groom`, `board-pickup`, `board-refresh`, `board-shared`

**Planning:** `project-spec`, `codebase-map`, `roadmap`, `feature-plan`, `bug-plan`, `refactor-plan`, `migration-plan`, `test-plan`, `api-spec`

**Workflow:** `workflow`, `quick-change`, `revision`, `debug`, `onboard`, `benchmark`, `hooks`, `learn`, `recipe`

**Operations:** `healthcheck`, `security-audit`, `dep-audit`, `release`, `context-health`, `cost-tracking`

**Customization:** `agent-customize`, `command-customize`, `skill-customize`, `rule-customize`

All commands are prefixed with `hatch3r-` (e.g., `hatch3r-board-fill`). See the [CLI Commands reference](https://docs.hatch3r.com/docs/reference/commands/cli-commands) and [Agent Commands reference](https://docs.hatch3r.com/docs/reference/commands/agent-commands) for full details.

## MCP Configuration

`hatch3r init` creates a `.env.mcp` file with required environment variables for your selected MCP servers (gitignored by default). MCP config is written to the tool-appropriate location (`.cursor/mcp.json`, `.mcp.json`, `.vscode/mcp.json`, etc.).

- **VS Code / Copilot**: Secrets are passed via the `env` object in `.vscode/mcp.json`.
- **Cursor / Claude Code / others**: Source the file first: `set -a && source .env.mcp && set +a && cursor .`

See [MCP Setup](https://docs.hatch3r.com/docs/guides/mcp-setup) for full setup, per-server details, and PAT scope guidance.

## Platform Agentic Workflows

hatch3r includes a complete board management system supporting GitHub, Azure DevOps, and GitLab. Configure in `hatch.json`:

```json
{
  "board": {
    "owner": "my-org",
    "repo": "my-repo",
    "projectNumber": 1,
    "areas": ["area:frontend", "area:backend", "area:infra"]
  },
  "models": {
    "default": "opus",
    "agents": { "hatch3r-lint-fixer": "sonnet" }
  }
}
```

## Sub-Agentic Architecture

- **Four-phase pipeline** -- Research, Implement, Review Loop (reviewer + fixer, max 3 iterations), Final Quality (testing + security)
- **Implementer agent** -- Receives a single sub-issue, delivers code + tests, reports back
- **Fixer agent** -- Takes reviewer findings and implements targeted fixes
- **Issue workflow skill** -- 8-step structured workflow with parallel sub-agent delegation for epics
- **Tooling hierarchy** -- Project docs > Codebase search > Library docs (Context7) > Web research

## Content Profiles

During `hatch3r init`, you choose a content profile:

| Profile | What's included | Best for |
|---------|----------------|----------|
| **Minimal** | Core agents and workflows only (`core` tag) | Quick setup, minimal footprint |
| **Standard** (recommended) | Full development lifecycle without niche audits | Most projects |
| **Full** | Everything including board management and all audits | Large teams, full coverage |
| **Custom** | Choose exactly what you need | Fine-grained control |

Content is tagged with workflow, context, and domain tags. After init, use `hatch3r config` to add or remove individual content items.

## How hatch3r differs from Ruler

Ruler (`@intellectronica/ruler`) is the closest architectural analogue to hatch3r -- both distribute from a single canonical source to multiple AI coding tools. Ruler's model is simpler per-adapter emission of markdown rules only. hatch3r ships a deeper content model, integrity surface, and governance system:

| Dimension | hatch3r | Ruler |
|-----------|---------|-------|
| Tool targets | 15 native adapters generating tool-specific primitives (Cursor `.mdc` frontmatter, Claude Code skills + hooks, Kiro steering, Copilot prompts) | 32 rule-distribution targets (markdown rules only; no tool-specific feature utilization) |
| Canonical content model | 6 artifact types (agents, skills, rules, commands, hooks, MCP servers) plus board workflows and learning loop, indexed in `hatch.json` | 1 artifact type (rules) |
| Managed blocks | `<!-- HATCH3R:BEGIN -->` / `<!-- HATCH3R:END -->` markers on every bridge file preserve user content across updates (`src/merge/managedBlocks.ts`) | Full-file replacement semantics |
| Integrity manifest | SHA-256 per-file + manifest-level checksum in `hatch.json`; safe merge via temp file + atomic rename (`src/merge/safeWrite.ts`, `src/integrity/index.ts`) | None |
| Governance audit cycle | 19-domain audit cycle with 106 sub-agents, 4-wave execution, closed-loop PRD evolution (`governance/AUDIT.md`, `governance/AUDIT-EXECUTE.md`) | None |
| Supply-chain provenance | npm OIDC trusted publishing + `--provenance` attestations via `.github/workflows/release.yml` (SLSA-level provenance) | Not published with OIDC trusted publishing |
| Security | OWASP Agentic Top 10 coverage via `src/pipeline/agentToolAllowlist.ts` + `src/pipeline/mcpDescriptionScan.ts` + `src/pipeline/promptGuard.ts` (500KB input / 1MB output limits) | Rule distribution only |

See [governance/COMPETITIVE-ANALYSIS.md](governance/COMPETITIVE-ANALYSIS.md) section 4 (Feature Comparison) for the full matrix.

## Customization

hatch3r separates managed from custom files:

- `hatch3r-*` files are managed by hatch3r and fully replaced on update
- Files without the prefix are your customizations and are never touched
- All hatch3r-generated markdown files use managed blocks (`<!-- HATCH3R:BEGIN -->` / `<!-- HATCH3R:END -->`). Content outside these markers is preserved. Bridge files are emitted by 15 adapters: Cursor, Claude, Copilot, Cline, Codex, Gemini, Windsurf, Amp, OpenCode, Aider, Kiro, Goose, Zed, Amazon Q, Antigravity.

## Model Selection

Configure preferred AI models per agent via `hatch.json` (global default and per-agent overrides), canonical agent frontmatter, or `.hatch3r/agents/{id}.customize.yaml`. Resolution order: customization file > manifest per-agent > agent frontmatter > manifest default.

See [Model Selection](https://docs.hatch3r.com/docs/guides/model-selection) for the full guide.

## Cursor Plugin

hatch3r is also available as a [Cursor plugin](https://cursor.com/marketplace). Enable it for instant access to all rules, skills, agents, and commands without running `init`.

## Documentation

Full documentation is available at [docs.hatch3r.com](https://docs.hatch3r.com).

- [Vision](governance/VISION.md) -- Framework north-star vision and principles
- [MCP Setup](https://docs.hatch3r.com/docs/guides/mcp-setup) -- Connecting MCP servers and managing secrets
- [Adapter Capability Matrix](https://docs.hatch3r.com/docs/reference/adapter-capability-matrix) -- Per-tool support and output paths
- [Agent Teams](https://docs.hatch3r.com/docs/guides/agent-teams) -- Multi-agent team coordination and delegation patterns
- [Model Selection](https://docs.hatch3r.com/docs/guides/model-selection) -- Configuring AI models per agent
- [Agentic Process](https://docs.hatch3r.com/docs/guides/agentic-process) -- Visual diagrams of init flow, board workflow, and agent orchestration
- [Troubleshooting](https://docs.hatch3r.com/docs/troubleshooting) -- Common issues and solutions
- [Changelog](CHANGELOG.md) -- Release history

## License

MIT

설치

https://github.com/hatch3r/hatch3r에서 스킬을 설치해줘

이 스킬은 ClawHub 레지스트리에 게시되지 않았습니다. 프롬프트를 코딩 에이전트(Claude Code, Cursor, Codex)에 붙여넣으면 소스 저장소에서 바로 스킬을 설치합니다.

저장소 열기

링크