Oh My ClaudeCode
Multi-agent orchestration for Claude Code. Zero learning curve.

Multi-agent orchestration for Claude Code. Zero learning curve.
Don't learn Claude Code. Just use OMC.
Oh My ClaudeCode (OMC) is a multi-agent orchestration layer that runs on top of Claude Code. With a single prompt it coordinates specialized agents to automate complex development tasks end-to-end.
Quick Start
Step 1 — Install
Plugin install (recommended for most Claude Code users). These are Claude Code slash commands — enter them one at a time (pasting both lines at once will fail):
/plugin marketplace add https://github.com/Yeachan-Heo/oh-my-claudecodeThen:
/plugin install oh-my-claudecodeIf you prefer the npm CLI / runtime path instead of the marketplace flow:
npm i -g oh-my-claude-sisyphus@latestPackage naming note: The project is branded as oh-my-claudecode (repo, plugin, commands), but the published npm package is
oh-my-claude-sisyphus.
Step 2 — Setup
# Inside a Claude Code / OMC session
/setup
/omc-setup
# From your terminal
omc setupStep 3 — Build something
# Inside a Claude Code / OMC session
/autopilot "build a REST API for managing tasks"
# Natural-language in-session shortcut
autopilot: build a REST API for managing tasksThat's it. Everything else is automatic.
CLI Commands vs In-Session Skills
OMC exposes two different surfaces:
- Terminal CLI commands — run
omc ...from your shell after installing via npm. - In-session skills — run
/...inside a Claude Code session after installing the plugin.
| Feature | Terminal CLI | In-session skill | Notes |
|---|---|---|---|
| Setup | omc setup | /setup or /omc-setup | Both are real entrypoints. /setup is the easiest plugin-first path |
| Ask providers | omc ask codex "…" | /ask codex "…" | Both route through the same advisor flow |
| Team orchestration | omc team 2:codex "…" | /team 3:executor "…" | Different runtimes: omc team launches tmux CLI workers; /team runs the in-session native team workflow |
| Autopilot / Ralph / Ultrawork / Deep Interview | — | /autopilot, /ralph, /ultrawork, /deep-interview | In-session only; there is no omc autopilot CLI subcommand |
| Autoresearch | omc autoresearch "…" | /deep-interview --autoresearch "…" | The in-session path is the setup/interview lane that helps you launch it |
Not Sure Where to Start?
If you're uncertain about requirements, have a vague idea, or want to micromanage the design:
/deep-interview "I want to build a task management app"The deep interview uses Socratic questioning to clarify your thinking before any code is written. It exposes hidden assumptions and measures clarity across weighted dimensions, ensuring you know exactly what to build before execution begins.
Team Mode (Recommended)
Starting in v4.1.7, Team is the canonical orchestration surface in OMC. The legacy swarm keyword/skill has been removed; use team directly.
/team 3:executor "fix all TypeScript errors"Use /team ... for Claude Code's in-session native team workflow. Use omc team ... for terminal-launched tmux CLI workers (claude / codex / gemini panes).
Team runs as a staged pipeline:
team-plan → team-prd → team-exec → team-verify → team-fix (loop)Enable Claude Code native teams in ~/.claude/settings.json:
{
"env": {
"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"
}
}If teams are disabled, OMC warns you and falls back to non-team execution where possible.
tmux CLI Workers — Codex & Gemini
Use omc team ... to spawn real tmux worker panes running claude / codex / gemini CLIs:
omc team 2:codex "review auth module for security issues"
omc team 2:gemini "redesign UI components for accessibility"
omc team 1:claude "implement the payment flow"
omc team status auth-review
omc team shutdown auth-reviewFor mixed Codex + Gemini work in one command, use the /ccg skill (routes via /ask codex + /ask gemini, then Claude synthesizes):
/ccg Review this PR — architecture (Codex) and UI components (Gemini)| Surface | Workers | Best For |
|---|---|---|
omc team N:codex "…" | N Codex CLI panes | Code review, security analysis, architecture |
omc team N:gemini "…" | N Gemini CLI panes | UI/UX, docs, large-context tasks |
omc team N:claude "…" | N Claude CLI panes | General tasks via Claude CLI in tmux |
/ccg | /ask codex + /ask gemini | Tri-model advisor synthesis |
Workers spawn on-demand and die when their task completes — no idle resource usage. Requires codex / gemini CLIs installed and an active tmux session.
Why oh-my-claudecode?
- Zero configuration required — works out of the box with intelligent defaults
- Team-first orchestration — Team is the canonical multi-agent surface
- Natural language interface — no commands to memorize, just describe what you want
- Automatic parallelization — complex tasks distributed across specialized agents
- Persistent execution — won't give up until the job is verified complete
- Cost optimization — smart model routing saves 30–50% on tokens
- Learn from experience — extracts and reuses problem-solving patterns
- Real-time visibility — HUD statusline shows what's happening under the hood
Key Features
| Feature | Description |
|---|---|
| 19 Specialized Agents | Role-based division: explore, plan, implement, verify, review |
| 37 Skills | Automated workflows like autopilot, ralph, ultrawork, team |
| Magic Keywords | Run full pipelines with a single phrase like autopilot build me X |
| Team Orchestration | Coordinate Claude / Codex / Gemini agents with per-role routing |
| State Management | Persist context across sessions via notepad + project-memory |
| Multi-AI | Use Claude, Codex, and Gemini for cross-validation |
Updating
If you installed via npm:
npm i -g oh-my-claude-sisyphus@latestIf you installed via the Claude Code marketplace/plugin flow:
# 1. Update the marketplace clone
/plugin marketplace update omc
# 2. Re-run setup to refresh configuration
/setupIf you experience issues after updating, clear the old plugin cache:
/omc-doctorIf marketplace auto-update is not enabled, you must manually run
/plugin marketplace update omcto sync the latest version before running setup.
Documentation
Getting Started
Installation, first session, and configuration
Core Concepts
Agents, skills, hooks, and state management
Guides
Autopilot, team mode, and debugging guides
Agents
Detailed reference for all 19 agents
Skills
Detailed reference for all 37 skills
Hooks
Hook system and magic keywords
Tools
MCP tools (State, Notepad, LSP, etc.)
Reference
Configuration, environment variables, changelog