What Is oh-my-claudecode? Multi-Agent for Claude Code
What Is oh-my-claudecode?
oh-my-claudecode (OMC) is an open-source multi-agent orchestration plugin for Claude Code. It coordinates Claude, Gemini, and OpenAI Codex with 19 specialized agents and 36 skills, turning Claude Code into a team of AI collaborators.
Last verified: April 2026
Quick Facts
| Detail | Info |
|---|---|
| Type | Claude Code plugin |
| By | Yeachan Heo |
| License | Open source |
| Models | Claude, Gemini, Codex |
| Agents | 19 specialized |
| Skills | 36 built-in |
| Status | Active, GitHub Trending |
What It Does
Instead of one Claude Code instance doing everything, OMC splits work across specialized agents:
- Architect agent — Plans system design and file structure
- Coder agent — Writes implementation code
- Reviewer agent — Reviews code for bugs and best practices
- Tester agent — Generates and runs tests
- DevOps agent — Handles deployment and CI/CD
- Researcher agent — Searches docs and APIs
Each agent can use a different model — route complex reasoning to Claude Opus 4.6, fast code generation to Gemini, and test generation to a cheaper model.
Why It’s Trending
Claude Code already authors ~4% of all public GitHub commits (~135,000/day). OMC takes this further by enabling team-like workflows for solo developers. As one analyst noted: “We’re moving from AI that responds to AI that acts.”
Getting Started
# In Claude Code
/plugin marketplace add https://github.com/Yeachan-Heo/oh-my-claudecode
/plugin install oh-my-claudecode
Key Features
- Multi-model routing — Use the right model for each task
- Team orchestration — Agents collaborate like a dev team
- 36 built-in skills — TDD, code review, refactoring, deployment, etc.
- Bedrock support — Works with AWS Bedrock model access
- Plugin system — Extensible with custom agents and skills
Who Should Use It
- Solo developers who want team-like AI coding workflows
- Teams already using Claude Code who want to add Gemini/Codex capabilities
- Developers building complex multi-file projects where different tasks benefit from different models
Last verified: April 2026