My Claude Devteam 🤖 Agent Open source
An engineering team in a box for Claude Code: role-based agents plus safety and quality hooks
- GitHub stars
- 269
- Stars this week
- –
- Forks
- 61
- Licence
- MIT
- Last push
- 2026-04-18
- Maintainer
- NYCU-Chung
/plugin marketplace add NYCU-Chung/my-claude-devteamThird-party subagents & agents run with your permissions. Read the source before installing, and prefer pinned versions.
Works with
About My Claude Devteam
What it does
My Claude Devteam is a Claude Code plugin that sets up a team of role-based subagents plus a set of automation hooks. The idea is to split work the way an engineering team does. A planner breaks larger tasks into written task prompts. Engineers implement the changes, a critic reviews them, and specialists handle debugging, database work, migrations and security checks. Each agent has its own tool permissions. The agents also share a strict working style: finish every task, back every claim with file and line references, and never skip a checklist item.
What is inside
- Twelve agents: planner, fullstack-engineer, refactor-specialist, migration-engineer, frontend-designer, critic, vuln-verifier, debugger, db-expert, onboarder, tool-expert and web-researcher
- Fifteen hooks: blocking commits that contain debugger statements or hardcoded secrets, blocking force pushes and direct commits to protected branches, warnings on large files, running tests after edits, cost tracking, audit logs and session summaries
- Methodology files: optional CLAUDE.md versions in English and Traditional Chinese that describe the P7/P9/P10 operating modes
- A settings example for turning individual hooks on or off
Works with
Claude Code only. The agents are Markdown files and the hooks are small JavaScript and shell scripts.
How to install
/plugin marketplace add NYCU-Chung/my-claude-devteam
/plugin install devteam@my-claude-devteam
Maintenance and safety
The plugin is MIT-licensed. There have been no commits since April 2026, so check that it still works with current Claude Code releases. The hooks run on every tool call, so read them before you enable them. The optional curl command for the methodology file overwrites your existing ~/.claude/CLAUDE.md. Some prompts use deliberate pressure language, which the README calls "PUA mode", and not everyone will want that in their sessions. The audit results in the README are the author's own reports and have not been checked independently.
Who should use it
It suits Claude Code users who want a ready-made multi-agent structure with strict review steps and branch-protection hooks. It can also serve as a starting point to fork and adapt. If you want a lighter setup, install only the agents you need.
Pros
- Clear role split with per-agent tool permissions
- Useful safety hooks like secret and force-push blocking
- Editable Markdown agents you can fork
Cons
- No commits since April 2026
- Optional curl overwrites your ~/.claude/CLAUDE.md, and prompts use pressure language
Similar subagents & agents
All agent workflows & frameworks →Spec Kit 🤖 AgentFree
GitHub's toolkit for spec-driven development with AI coding agents
Task Master 🤖 AgentFree
AI task management that turns a PRD into tasks your coding agent works through
Fast Agent 🤖 AgentOpen source
Python framework for building, orchestrating and evaluating MCP-native AI agents
OpenSpec 🤖 AgentFree
Lightweight spec-driven development: agree on changes before the agent codes
CC Safety Net 🤖 AgentOpen source
Pre-execution guard that blocks destructive commands and secret access for coding agents
BMAD Method 🤖 AgentFree
Agile AI-driven development with analyst, PM, architect, developer and UX agents