Yeachan-Heo/oh-my-claudecode

Teams-first Multi-agent orchestration for Claude Code

What it solves

oh-my-claudecode (OMC) is a multi-agent orchestration layer for Claude Code. It eliminates the need to manually manage complex workflows by providing a natural-language interface to coordinate multiple AI agents, automate end-to-end feature development, and route tasks to the most efficient models.

How it works

OMC integrates as a plugin for Claude Code or as a standalone CLI tool. It provides several orchestration modes:

  • Team Mode: A staged pipeline (plan $\rightarrow$ prd $\rightarrow$ exec $\rightarrow$ verify $\rightarrow$ fix) that coordinates multiple agents on a shared task list.
  • CLI Workers: Spawns real CLI processes (such as Codex, Gemini, Antigravity, Grok, or Cursor) in tmux panes to handle specialized tasks.
  • Autopilot: An autonomous single-lead agent for end-to-end feature work.
  • Specialized Loops: Modes like Ralph (persistent verify/fix loops) and UltraQA (repeated quality-gate cycling) ensure tasks are completed fully and pass all tests.
  • Deep Interview: A Socratic questioning process used to clarify requirements before any code is written.

Who it’s for

Developers using Claude Code who want to automate complex coding tasks, coordinate multiple different AI models (like Codex or Gemini) within a single session, and reduce token costs through smart model routing.

Highlights

  • Zero Configuration: Works out of the box with intelligent defaults.
  • Multi-Model Orchestration: Ability to spawn and coordinate workers from different providers (Codex, Gemini, Antigravity, Grok, Cursor).
  • Socratic Requirement Gathering: The /deep-interview skill helps users define project goals before execution.
  • Cost Optimization: Smart routing to save 30-50% on tokens.
  • Persistent Execution: Built-in verify/fix loops that prevent silent partial completions.