oh-my-claudecode
Multi-agent orchestration for Claude Code: teams, roles, autopilot and task routing across skills and subagents
High risk
We rate an entry high when the tool writes to external systems, handles money, production databases or secrets, or runs arbitrary commands. The CLI installs it only with your consent.
Why this level
- Autopilot and agent teams write code, run shell commands and edit project files
- It can run without the user supervising every step
Install
In your terminal, with SkillFoxx CLI
npx skillfoxx add plugins/oh-my-claudecodeDetects the agents on your machine, checks the risk and pins the version.
Other ways to install
Run one by one in the Claude Code chat
/plugin marketplace add yeachan-heo/oh-my-claudecode
/plugin install oh-my-claudecode@omcInstall the plugin with two commands, one at a time: /plugin marketplace add https://github.com/Yeachan-Heo/oh-my-claudecode, then /plugin install oh-my-claudecode. After install run /omc-setup. For the terminal there is a separate CLI: npm i -g oh-my-claude-sisyphus@latest.
Other ways from the author
/plugin marketplace add https://github.com/Yeachan-Heo/oh-my-claudecode
/plugin install oh-my-claudecodeEnter the commands one at a time. After install run /omc-setup.
This is third-party code. Review the repository files before installing.
What it does
The plugin adds a ready set of skills, subagents, slash commands and hooks on top of Claude Code so you work on a task as a team of roles rather than alone. Autopilot mode drives a task end to end: plan, execution, verification and fixes. Team mode runs a staged pipeline of plan, prd, exec, verify and a fix loop, spreading work across subagents. The ask command sends a patch or question for a second opinion to another agent such as codex, gemini or grok. A separate terminal CLI, omc, runs the same flows from the shell.
Who it is for. For developers who run large tasks in Claude Code and want to parallelize work across several agents.
Good fit when
- You need to drive a large task from plan to verification with a team of agents
- You want to parallelize several subagents inside one session
- You want a second opinion from another agent on a patch or decision
Not a fit when
- You need a single small edit that does not justify a full orchestrator
- You have no access to Claude Code or an Anthropic account
Example request
/autopilot build a REST API for managing tasksLimitations
The plugin runs on top of Claude Code and needs an Anthropic account. The terminal CLI installs separately via npm and needs Node.js. Team mode uses Claude Code experimental agent teams, which must be enabled with a settings flag. Named autopilot profiles only work on Linux with the flock utility. Anthropic is not reachable from Russia without a VPN.
How to disable. Remove the oh-my-claudecode plugin via /plugin. If you installed the CLI, uninstall the global oh-my-claude-sisyphus package via npm.
Security check
- Autopilot and agent teams write code, run shell commands and edit project files
- It can run without the user supervising every step
README in short
The README presents oh-my-claudecode as a multi-agent orchestration system for Claude Code, installed through the plugin marketplace with an optional npm package. Quick start comes down to install, the /omc-setup command and running autopilot with one phrase. It describes two surfaces, the omc terminal commands and in-session slash commands, plus team mode with a plan, prd, exec, verify and fix pipeline. Team agents require enabling an experimental flag in Claude Code settings. MIT licensed, with a sibling project oh-my-codex for the Codex CLI.
FAQ
How is this different from plain Claude Code?
The plugin adds ready commands, subagent roles, team mode and autopilot, so you do not assemble orchestration by hand.
Is the separate CLI required?
No. Everything works through slash commands inside a session. The omc CLI installs separately via npm if you want to run it from the terminal.
Related
Open-source personal AI assistant on your own machine: answers in Telegram, Slack, Discord and WhatsApp, extended with skills and plugins
A self-improving agent from Nous Research with a TUI, messaging gateway, cron jobs and skills it writes itself
An open source coding agent for the terminal and desktop with build and plan modes
Open prompt library with a Claude Code plugin, MCP server and CLI: search, fetch and improve prompts and skills from an agent