A weapon, not a tool
Multi-AI orchestration plugin for Claude Code. Coordinate Claude, Gemini, and Codex with 19 specialized agents, 39 skills, and MCP-powered tools.
Native Windows hook manifest fixes, durable Ultragoal, Claude goal workflow polish, plugin/runtime hardening, and safer cleanup guardrails across the v4.14 series.
Plugin hook manifests now call node "$CLAUDE_PLUGIN_ROOT"/scripts/run.cjs directly on Windows, avoiding sh, /bin/sh, and find-node.sh launch regressions.
omc ultragoal now persists multi-goal plans and ledgers under .omc/ultragoal, with fail-closed checkpointing and Claude Code /goal handoff guidance.
The v4.14 line clarifies Claude /goal boundaries, maps goal artifacts to OMC storage roots, and improves durable workflow UX across sessions.
Plugin cache repair, registry alignment, command wrapper preservation, and update-check cache paths are hardened so marketplace and CLI updates stay consistent.
Destructive worktree cleanup and teleport removal paths now require safer path validation and fallbacks before deleting local state.
Windows HUD, PowerShell team worker startup, native Claude version detection, and hook shutdown paths are more portable across shells and platforms.
Claude, Codex, and Gemini CLI workers running in parallel tmux panes — each doing what it does best.
The Conductor
Spawns a real gemini CLI process in a tmux pane. 1M token context for design review and UI work across your entire codebase.
Spawns a real codex CLI process in a tmux pane. Deep code analysis, architecture validation, and security review.
Claude decomposes tasks, fans out work to tmux workers via /omc-teams or /ccg, and synthesizes results — no MCP servers required.
Install via Claude Code plugin marketplace, or use the npm package directly: [email protected].
Install the plugin
# In Claude Code, run:
/plugin marketplace add https://github.com/Yeachan-Heo/oh-my-claudecode
/plugin install oh-my-claudecode
Or install the npm package directly
# CLI install via npm:
npm install -g [email protected]
Run setup
/oh-my-claudecode:omc-setup
# That's it! You're ready.
Choose how you want to work. From full autopilot to token-efficient parallel execution.
Full autonomous execution from high-level idea to working, tested code. No manual intervention required.
Self-referential loop until completion with architect verification. The boulder never stops rolling.
Maximum parallelism with aggressive agent delegation. Process multiple tasks simultaneously.
Socratic questioning to clarify vague ideas before execution. Exposes hidden assumptions and measures clarity.
N coordinated agents on a shared task list using Claude Code native teams. Real-time messaging and task coordination.
Strategic interview-based planning workflow. Gather requirements before diving into implementation.
Language server integration, structural code analysis, and persistent state - all built in.
Hover info, go-to-definition, find references, and project-wide type checking with any language server.
Structural code search and replace. Find patterns by syntax, not just text matching.
Persistent Python environment with pandas, numpy, and matplotlib for data analysis.
Notepad, project memory, and session state that persists across conversations.
Just say the keyword and the right mode activates automatically.
| Keyword | Effect | Example |
|---|---|---|
autopilot |
Full autonomous execution | "autopilot: build a todo app" |
ralph |
Persistence mode until completion | "ralph: refactor auth system" |
ulw |
Maximum parallelism (ultrawork) | "ulw fix all errors" |
plan |
Planning interview mode | "plan the new API" |
ralplan |
Iterative planning consensus | "ralplan this feature" |
deep-interview |
Socratic requirements clarification | "/deep-interview 'vague idea'" |
team |
Coordinated native teams (replaces swarm/ultrapilot) | "team 5:executor fix all errors" |
swarm Deprecated |
Use team instead |
"team 5:executor fix all errors" |
Unified agents organized by domain. Use the model parameter to match complexity.
Core workflow from exploration to verification
Multi-dimensional code quality checks
Deep expertise for specialized tasks
All agents use model-optimized routing (Opus for architecture/analysis, Sonnet for standard work, Haiku for quick lookups).
No docs needed. No commands to memorize. Just say what you want.
"Build me a REST API" - that's it. Autopilot detects your intent and orchestrates 19 agents automatically.
Say "fast" and it activates parallelism. Say "don't stop" and it persists. Every intent maps to the right mode.
Delegates to specialists, routes to the right model tier, verifies with architect. You focus on the what, not the how.
Install from Claude's plugin marketplace, run /oh-my-claudecode:omc-setup - done. Everything else is automatic.