What You Get
hatch3r ships a full agentic setup out of the box. During hatch3r init, you choose a content profile (Minimal, Standard, Full, or Custom) that determines which items are installed. Here's everything available in the Full profile.
| Category | Count | Highlights |
|---|---|---|
| Agents | 29 | Code reviewer, lint-fixer, dependency auditor, implementer (sub-agentic), fixer, researcher, architect, DevOps, handoff loader / preparer, nine quality-vector specialists (UI, UX, security, reliability, testability, scalability, performance, maintainability, enhancability), and more |
| Skills | 53 | Bug fix, feature implementation, issue workflow, release, incident response, context health, cost tracking, handoff prepare / resume, recipes, API spec, CI pipeline, migration, customization, board lifecycle, ad-hoc orchestration scaffold, 5 standalone CLI-tool skills + a 24-tool cli-toolbox, and more |
| Rules | 65 | Code standards, testing, API design, observability, theming, i18n, security patterns, agent orchestration, fan-out discipline, right-sizing, deep context, handoff readiness, and more |
| Commands | 30 | Board management, planning (feature, bug, refactor, test), workflow, quick-change, bug-pipeline, revision, debug, healthcheck, security-audit, onboard, benchmark, handoff (prepare/resume/list/complete/prune), 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) |
Counts above mirror
governance/inventory.json— the single source of truth, regenerated bynpm run inventoryand drift-checked in CI (Cycle 7 H10). If a number here disagrees withinventory.json,inventory.jsonis authoritative.
:::tip Content profiles
The Standard profile (recommended) includes core, planning, implementation, review, devops, and maintenance content — everything most projects need. The Minimal profile installs only core-tagged items for a lean setup. Use hatch3r config to add or remove items after init.
:::
Agents
Specialized agents that handle distinct responsibilities in your development workflow.
| Agent | Tags | Description |
|---|---|---|
| implementer | core, implementation | Focused implementation agent for single sub-issues, receives context from orchestrator |
| reviewer | core, review | Senior reviewer -- correctness, security, privacy, performance, accessibility |
| researcher | core, planning | Deep investigation sub-agent used by planning commands |
| fixer | core, implementation | Targeted fixes for reviewer findings in the review loop |
| testability | review, testing, floor:content-quality | Testability specialist -- per-feature test-class mandate, real-deal-first testing, coverage thresholds, AI feature eval coverage |
| lint-fixer | core, implementation | Code quality enforcer -- ESLint, Prettier, TypeScript strict, dead code removal |
| learnings-loader | core, maintenance | Load and apply project learnings from the knowledge base |
| context-rules | core, maintenance | Dynamic context rule generation from project patterns |
| architect | planning | Architecture design, trade-off analysis, ADR production |
| docs-writer | maintenance | Technical writer -- specs, ADRs, glossary, process docs |
| dependency-auditor | maintenance, security | Supply chain analyst -- CVE scanning, upgrade paths, lockfile integrity |
| security | review, security, floor:security | Security specialist -- OAuth 2.1 / OIDC / DPoP / WebAuthn, supply-chain integrity (SBOM, provenance, SHA-pin, cosign), OWASP ASI controls |
| ci-watcher | devops | CI/CD specialist -- monitors GitHub Actions, reads failure logs |
| devops | devops | CI/CD and deployment operations specialist |
| a11y-auditor | review, a11y | Accessibility specialist -- WCAG AA compliance, ARIA, color contrast |
| perf-profiler | review, performance | Performance engineer -- runtime profiling, bundle size, benchmarks |
...and 14 more, including the nine quality-vector specialists. See the full Agents reference.
Skills
On-demand instruction bundles for specific tasks. Skills are loaded when agents need them.
| Skill | Description |
|---|---|
| feature | End-to-end feature implementation as a vertical slice |
| bug-fix | Root cause diagnosis, minimal fix, regression test |
| refactor | Internal quality improvement without behavior change |
| release | Semantic versioning, changelog, tagging, deploy verification |
| issue-workflow | 8-step GitHub issue workflow with sub-agent delegation |
| pr-creation | PR conventions, branch naming, self-review checklist |
| incident-response | Triage, mitigation, root cause analysis, post-mortem |
...and 36 more. See the full Skills reference.
Rules
Persistent coding standards and conventions always available to agents.
| Rule | Description |
|---|---|
| code-standards | TypeScript strict, naming conventions, function/file limits |
| testing | Deterministic, isolated, fast tests with clear naming |
| api-design | Versioning, validation, error responses, auth, CORS, pagination |
| security-patterns | Input validation, output encoding, auth, OWASP alignment |
| git-conventions | Branch naming, commit messages, merge strategy |
| deep-context | Deep context retrieval and codebase understanding for AI agents |
| agent-orchestration | Agent delegation patterns and multi-agent coordination protocols |
...and 47 more. See the full Rules reference.
Commands
Workflows invoked inside your coding tool or via CLI.
| Command | Description |
|---|---|
| board-init | Create/connect a GitHub Projects V2 board |
| board-fill | Parse todo.md into GitHub issues with dependency analysis |
| board-pickup | Auto-pick next issue, delegate to sub-agents, create PR |
| project-spec | Generate project documentation from a vision |
| feature-plan | Plan a single feature with parallel researchers |
| test-plan | Plan a test strategy (coverage targets, strategy matrix, prioritized cases) with parallel researchers |
| release | Cut a versioned release with changelog |
...and 16 more. See the full Commands reference.