Open source · AI dev tools
A full AI engineering team
as plain Markdown files.
14 specialized AI agents — architect, reviewer, security expert, DevOps engineer, and more — each a single Markdown skill file any agent runtime can load into any project. No lock-in. No configuration. Just drop them in.
14
Specialized agents
Any
Agent runtime
Zero
Tolerance for “fix stuff” commits
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, Cursor, or any runtime that supports skill files.
01
Install the Society
One command: npx skills add fworks-tech/agenthood — or clone the repo directly.
02
Load into your runtime
Point Claude Code, Cursor, or your agent framework at the skills directory.
03
Invoke any agent
Ask the Reviewer to check your PR. Ask Security to audit your auth flow. They know their role.
Meet the team
Every role a real software team needs — available as a skill file with impeccable standards.
🏗️
Architect
System design, ADRs, tech decisions
⚙️
Engineer
Implementation, refactoring, code quality
🔍
Reviewer
PR reviews, standards enforcement
🧪
Tester
Test strategy, coverage, edge cases
🔒
Security
Vulnerability scanning, threat modeling
🚀
DevOps
CI/CD, infra, deployment pipelines
📝
Docs Writer
READMEs, changelogs, API docs
📊
Data Engineer
Schemas, migrations, query optimization
🎨
UX Auditor
Accessibility, usability, design consistency
📋
PM
Tickets, priorities, sprint planning
🚨
On-call
Incident triage, root cause analysis
🎓
Mentor
Code explanations, onboarding, learning paths
💳
Debt Tracker
Tech debt inventory and payoff plans
📦
Release Manager
Versioning, release notes, changelog
Your project deserves a full team.
Open source. No sign-up. Works with any agent runtime.
Get started on GitHub →