agenthood weekly downloads statistics

Agenthood

A full AI engineering team that earns every merge.

20 specialized AI agents — architect, reviewer, security expert, DevOps engineer, strategist, operator, and more — each a portable Markdown skill file any agent runtime can load into any project, plus a TypeScript runtime that runs them autonomously across your whole software lifecycle. No lock-in. Just drop them in.

They have opinions about your PR descriptions. They will not merge your branch if your commit says fix stuff. They are not polite about it. And they show their work: every run leaves a tamper-evident decision and provenance trail.

---

The Oath

I commit with intention. I branch with purpose. I review with honesty. I ship with confidence. I never push to main.

---

How it works

Each agent is a single .md file that describes a role, its responsibilities, standards, and how it communicates. Load one or all of them into Claude Code, Copilot, Gemini CLI, or any runtime that supports skill files. Hand them a task, or run them autonomously via the TypeScript CLI — end to end, with human checkpoints where it matters.

1. Install the Society — npm install --save-dev agenthood && npx agenthood init (or npx skills add fworks-tech/agenthood via skills.sh)
2. Load into your runtime — point Claude Code, Copilot, or your agent framework at the skills directory
3. Invoke any agent — ask the Reviewer to check your PR, ask the Auditor to scan your auth flow. They know their role. They have standards.
4. Run them autonomously — agenthood run the-scribe "write a commit message" executes a member as a real LLM agent; chain them for full-lifecycle work

Every member run records one decision and one provenance entry in .agenthood/decisions/ and .agenthood/provenance/ — a tamper-evident hash chain you can audit. See ADR-015.

Beyond the 20 members, skills/ ships 41 utility skills — specialist capability files (docker, kubernetes, jira, postgres, redis, and more) that any agent runtime activates on task match. See the Academy utility skills guide.

---

Meet the team

Every role a real software team needs — available as a skill file with impeccable standards.

	Agent	Role
✍️	The Scribe	Commits, PRs, changelogs
🏗️	The Architect	System design, ADRs, tech decisions
🛠️	The Builder	Coding, implementation, refactoring, validation
🔍	The Reviewer	Code review, standards enforcement
🧪	The Tester	TDD, coverage, edge cases
🐛	The Debugger	Error triage, root cause analysis
🔒	The Auditor	Security, vulnerability scanning, dependency audit
📦	The Herald	Releases, versioning, changelogs
📝	The Librarian	Documentation, API references
🚪	The Doorman	Validation, branch protection, health checks
🔮	The Oracle	Institutional knowledge, authoring templates
🌐	The Envoy	Cross-provider translation, convention validation
👁️	The Sentinel	Integrity, cross-member contradiction detection
⚖️	The Warden	Code health, complexity enforcement
🧭	The Steward	Context economy, provider cache strategies
🚦	The Mediator	First-in-line intent routing, handoff sequencing
🎯	The Strategist	Goal refinement, requirement discovery
🩺	The Operator	Runtime health, deployments, rollback
👁️	The Inspector	Visual-reasoning benchmarking, pixel analysis
📬	The Mailman	Message delivery, scheduling, cross-posting

---

Getting started

Option A — Drop into any AI runtime

npm install --save-dev agenthood
npx agenthood init       # interactive setup (~2 minutes)
npx agenthood check      # verify everything is in place

Members are loaded as context by your existing AI assistant. Works with Claude Code, Copilot, Gemini CLI, Cursor, OpenCode, or any skill-file runtime.

Option B — Run agents autonomously

Execute members as real LLM agents that reason, act, and remember across sessions.…