{"id":45892017,"url":"https://github.com/hatch3r/hatch3r","last_synced_at":"2026-04-22T13:00:50.297Z","repository":{"id":341025494,"uuid":"1168611103","full_name":"hatch3r/hatch3r","owner":"hatch3r","description":"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 \u0026 MCP integrations for Cursor, GitHub Copilot, Claude Code, Windsurf, Amp, Codex, Gemini CLI, Cline \u0026 OpenCode.","archived":false,"fork":false,"pushed_at":"2026-04-09T14:07:52.000Z","size":7365,"stargazers_count":19,"open_issues_count":12,"forks_count":1,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-09T15:22:34.064Z","etag":null,"topics":["agentic","agents","ai","claude","cli","codex","coding-assistant","copilot","cursor","developer-tools","gemini","mcp","windsurf"],"latest_commit_sha":null,"homepage":"https://www.npmjs.com/package/hatch3r","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/hatch3r.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":"CODEOWNERS","security":"SECURITY.md","support":null,"governance":"governance/AUDIT-EXECUTE.md","roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-02-27T15:38:54.000Z","updated_at":"2026-04-01T13:38:38.000Z","dependencies_parsed_at":"2026-04-02T02:02:25.902Z","dependency_job_id":null,"html_url":"https://github.com/hatch3r/hatch3r","commit_stats":null,"previous_names":["hatch3r/hatch3r"],"tags_count":5,"template":false,"template_full_name":null,"purl":"pkg:github/hatch3r/hatch3r","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hatch3r%2Fhatch3r","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hatch3r%2Fhatch3r/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hatch3r%2Fhatch3r/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hatch3r%2Fhatch3r/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hatch3r","download_url":"https://codeload.github.com/hatch3r/hatch3r/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hatch3r%2Fhatch3r/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32016852,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-18T20:23:30.271Z","status":"online","status_checked_at":"2026-04-19T02:00:07.110Z","response_time":55,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agentic","agents","ai","claude","cli","codex","coding-assistant","copilot","cursor","developer-tools","gemini","mcp","windsurf"],"created_at":"2026-02-27T18:26:38.956Z","updated_at":"2026-04-19T18:03:01.586Z","avatar_url":"https://github.com/hatch3r.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# hatch3r\n\n[![npm version](https://img.shields.io/npm/v/hatch3r.svg)](https://www.npmjs.com/package/hatch3r)\n\n**Crack the egg. Hatch better agents.**\n\nhatch3r is an open-source CLI and Cursor plugin that installs a battle-tested, tool-agnostic agentic coding setup into any repository. One command gives you up to 16 agents, 26 skills, 26 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.\n\n## Quick Start\n\nRequires Node.js 22+.\n\n```bash\nnpx hatch3r init\n```\n\nThat'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).\n\n## What You Get\n\n| Category | Count | Highlights |\n|----------|-------|-----------|\n| **Agents** | 16 | Code reviewer, test writer, security auditor, implementer (sub-agentic), fixer, researcher, architect, DevOps, and more |\n| **Skills** | 26 | Bug fix, feature implementation, issue workflow, release, incident response, context health, cost tracking, recipes, API spec, CI pipeline, migration, customization, and more |\n| **Rules** | 26 | Code standards, testing, API design, observability, theming, i18n, security patterns, agent orchestration, deep context analysis, and more |\n| **Commands** | 34 | Board management, planning (feature, bug, refactor, test), workflow, quick-change, revision, debug, healthcheck, security-audit, cost-tracking, onboard, benchmark, customization, and more |\n| **MCP Servers** | 10 (3 default + 7 opt-in) | Playwright, Context7, Filesystem (default); GitHub, Brave Search, Sentry, Postgres, Linear, Azure DevOps, GitLab (opt-in) |\n| **Platforms** | 3 | GitHub, Azure DevOps, GitLab -- auto-detected from git remote |\n\n## Supported Tools (15 Adapters)\n\n| Tool | Output |\n|------|--------|\n| **Cursor** | `.mdc` rules, agents, skills, commands, MCP config |\n| **GitHub Copilot** | instructions, prompts, GitHub agents |\n| **Claude Code** | `CLAUDE.md`, skills, `.mcp.json` |\n| **OpenCode** | `AGENTS.md`, `opencode.json` |\n| **Windsurf** | `.windsurfrules` |\n| **Amp** | `AGENTS.md` |\n| **Codex CLI** | `AGENTS.md`, `codex.md` |\n| **Gemini CLI** | `GEMINI.md` |\n| **Cline / Roo Code** | `.clinerules` |\n| **Aider** | `CONVENTIONS.md` |\n| **Kiro** | `.kiro/steering/`, `.kiro/settings/mcp.json` |\n| **Goose** | `.goosehints` |\n| **Zed** | `.rules` |\n| **Amazon Q** | `.amazonq/rules/`, `.amazonq/mcp.json` |\n| **Antigravity** | `.antigravity/rules.md`, `.antigravity/settings.json` |\n\nPlatform is auto-detected from your git remote during `hatch3r init`. All board commands, agents, rules, and skills adapt to your selected platform.\n\n## How It Works\n\n```\n.agents/              \u003c- Canonical source (tool-agnostic)\n  ├── agents/\n  ├── skills/\n  ├── rules/\n  ├── commands/\n  ├── mcp/\n  ├── AGENTS.md\n  └── hatch.json       \u003c- Manifest\n\n.cursor/               \u003c- Generated (Cursor adapter)\n.github/               \u003c- Generated (Copilot adapter)\nCLAUDE.md              \u003c- Generated (Claude adapter)\n.windsurfrules         \u003c- Generated (Windsurf adapter)\nAGENTS.md              \u003c- Generated (OpenCode, Amp, Codex adapters)\nGEMINI.md              \u003c- Generated (Gemini adapter)\n.clinerules            \u003c- Generated (Cline adapter)\nCONVENTIONS.md         \u003c- Generated (Aider adapter)\n.kiro/                 \u003c- Generated (Kiro adapter)\n.goosehints            \u003c- Generated (Goose adapter)\n.rules                 \u003c- Generated (Zed adapter)\n.amazonq/              \u003c- Generated (Amazon Q adapter)\n.antigravity/          \u003c- Generated (Antigravity adapter)\n.worktreeinclude       \u003c- Generated (worktree isolation)\n```\n\nhatch3r keeps one source of truth in `.agents/` and generates native configuration for each tool.\n\n## Multi-Repo Workspaces\n\nhatch3r 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.\n\n```\nmy-platform/                   \u003c- Workspace root (not a git repo)\n  .agents/                     \u003c- Shared canonical source\n    workspace.json             \u003c- Workspace manifest\n    hatch.json\n    agents/\n    rules/\n    ...\n  frontend/                    \u003c- Git repo (gets its own generated files)\n    .cursor/\n    CLAUDE.md\n    ...\n  backend/                     \u003c- Git repo\n    .cursor/\n    CLAUDE.md\n    ...\n  infra/                       \u003c- Git repo\n    .cursor/\n    CLAUDE.md\n    ...\n```\n\n```bash\nnpx hatch3r init --workspace              # force workspace mode\nnpx hatch3r sync                          # cascade to all repos\nnpx hatch3r sync --repos frontend backend # sync specific repos\nnpx hatch3r sync --dry-run                # preview changes\nnpx hatch3r config                        # manage repos and sync strategy\n```\n\nContent 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.\n\n## Workflow\n\nhatch3r provides a full project lifecycle, from setup to release:\n\n1. **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).\n2. **Set up the board** -- `hatch3r-board-init` creates or connects a Projects V2 board with status fields, label taxonomy, and config writeback.\n3. **Define work** -- Create a `todo.md` at the project root (one item per line).\n4. **Fill the board** -- `hatch3r-board-fill` parses `todo.md`, classifies items, groups into epics, builds a dependency DAG, and marks issues `status:ready`.\n5. **Groom the backlog** -- `hatch3r-board-groom` surfaces stale items, priority imbalances, and decomposition candidates for selective refinement.\n6. **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.\n7. **Review cycle** -- Reviewer + fixer agents loop (max 3 iterations) until clean, then test-writer and security-auditor run final checks.\n8. **Release** -- `hatch3r-release` determines the semver bump, generates a changelog, tags, and publishes.\n\n\u003e **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`.\n\n## Commands\n\n### CLI Commands\n\n```bash\nnpx hatch3r init          # Interactive setup\nnpx hatch3r config        # Reconfigure tools, MCP servers, features, and platform\nnpx hatch3r sync          # Re-generate from canonical state\nnpx hatch3r update        # Pull latest templates (safe merge)\nnpx hatch3r status        # Check sync status between canonical and generated files\nnpx hatch3r validate      # Validate canonical .agents/ structure\nnpx hatch3r verify        # Verify file integrity checksums\nnpx hatch3r clean                 # Remove generated files (optional --reinit)\nnpx hatch3r worktree-setup \u003cpath\u003e  # Set up gitignored files in a worktree\nnpx hatch3r worktree-cleanup \u003cpath\u003e # Clean up worktree-specific files\nnpx hatch3r add \u003cpack\u003e    # Install a community pack (coming soon)\n```\n\n### Agent Commands\n\nThese commands are invoked inside your coding tool (e.g., as Cursor commands).\n\n**Board management:** `board-init`, `board-fill`, `board-groom`, `board-pickup`, `board-refresh`, `board-shared`\n\n**Planning:** `project-spec`, `codebase-map`, `roadmap`, `feature-plan`, `bug-plan`, `refactor-plan`, `migration-plan`, `test-plan`, `api-spec`\n\n**Workflow:** `workflow`, `quick-change`, `revision`, `debug`, `onboard`, `benchmark`, `hooks`, `learn`, `recipe`\n\n**Operations:** `healthcheck`, `security-audit`, `dep-audit`, `release`, `context-health`, `cost-tracking`\n\n**Customization:** `agent-customize`, `command-customize`, `skill-customize`, `rule-customize`\n\nAll 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.\n\n## MCP Configuration\n\n`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.).\n\n- **VS Code / Copilot**: Secrets are passed via the `env` object in `.vscode/mcp.json`.\n- **Cursor / Claude Code / others**: Source the file first: `set -a \u0026\u0026 source .env.mcp \u0026\u0026 set +a \u0026\u0026 cursor .`\n\nSee [MCP Setup](https://docs.hatch3r.com/docs/guides/mcp-setup) for full setup, per-server details, and PAT scope guidance.\n\n## Platform Agentic Workflows\n\nhatch3r includes a complete board management system supporting GitHub, Azure DevOps, and GitLab. Configure in `hatch.json`:\n\n```json\n{\n  \"board\": {\n    \"owner\": \"my-org\",\n    \"repo\": \"my-repo\",\n    \"projectNumber\": 1,\n    \"areas\": [\"area:frontend\", \"area:backend\", \"area:infra\"]\n  },\n  \"models\": {\n    \"default\": \"opus\",\n    \"agents\": { \"hatch3r-lint-fixer\": \"sonnet\" }\n  }\n}\n```\n\n## Sub-Agentic Architecture\n\n- **Four-phase pipeline** -- Research, Implement, Review Loop (reviewer + fixer, max 3 iterations), Final Quality (testing + security)\n- **Implementer agent** -- Receives a single sub-issue, delivers code + tests, reports back\n- **Fixer agent** -- Takes reviewer findings and implements targeted fixes\n- **Issue workflow skill** -- 8-step structured workflow with parallel sub-agent delegation for epics\n- **Tooling hierarchy** -- Project docs \u003e Codebase search \u003e Library docs (Context7) \u003e Web research\n\n## Content Profiles\n\nDuring `hatch3r init`, you choose a content profile:\n\n| Profile | What's included | Best for |\n|---------|----------------|----------|\n| **Minimal** | Core agents and workflows only (`core` tag) | Quick setup, minimal footprint |\n| **Standard** (recommended) | Full development lifecycle without niche audits | Most projects |\n| **Full** | Everything including board management and all audits | Large teams, full coverage |\n| **Custom** | Choose exactly what you need | Fine-grained control |\n\nContent is tagged with workflow, context, and domain tags. After init, use `hatch3r config` to add or remove individual content items.\n\n## Customization\n\nhatch3r separates managed from custom files:\n\n- `hatch3r-*` files are managed by hatch3r and fully replaced on update\n- Files without the prefix are your customizations and are never touched\n- All hatch3r-generated markdown files use managed blocks (`\u003c!-- HATCH3R:BEGIN --\u003e` / `\u003c!-- HATCH3R:END --\u003e`). 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.\n\n## Model Selection\n\nConfigure 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 \u003e manifest per-agent \u003e agent frontmatter \u003e manifest default.\n\nSee [Model Selection](https://docs.hatch3r.com/docs/guides/model-selection) for the full guide.\n\n## Cursor Plugin\n\nhatch3r 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`.\n\n## Documentation\n\nFull documentation is available at [docs.hatch3r.com](https://docs.hatch3r.com).\n\n- [Vision](governance/VISION.md) -- Framework north-star vision and principles\n- [MCP Setup](https://docs.hatch3r.com/docs/guides/mcp-setup) -- Connecting MCP servers and managing secrets\n- [Adapter Capability Matrix](https://docs.hatch3r.com/docs/reference/adapter-capability-matrix) -- Per-tool support and output paths\n- [Agent Teams](https://docs.hatch3r.com/docs/guides/agent-teams) -- Multi-agent team coordination and delegation patterns\n- [Model Selection](https://docs.hatch3r.com/docs/guides/model-selection) -- Configuring AI models per agent\n- [Agentic Process](https://docs.hatch3r.com/docs/guides/agentic-process) -- Visual diagrams of init flow, board workflow, and agent orchestration\n- [Troubleshooting](https://docs.hatch3r.com/docs/troubleshooting) -- Common issues and solutions\n- [Changelog](CHANGELOG.md) -- Release history\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhatch3r%2Fhatch3r","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhatch3r%2Fhatch3r","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhatch3r%2Fhatch3r/lists"}