oh-my-claudecode
Teams-first Multi-agent orchestration for Claude Code
- 40.2k estrellas
- 3.6k forks
- 2 issues abiertos
- Lenguaje: TypeScript
- Licencia: MIT
- actualizado
Instalación
git clone https://github.com/Yeachan-Heo/oh-my-claudecode && cp oh-my-claudecode/*.md ~/.claude/agents/- Clone the repository and copy the agent .md definitions into ~/.claude/agents (or .claude/agents inside a project).
- Start a new Claude Code session to load the agents.
- Delegate work to them with the Task/Agent tool or by name.
Nota editorial
oh-my-claudecode is a multi-agent orchestration layer built on top of Claude Code, installable either as a Claude Code plugin via the marketplace or as a global npm package (`oh-my-claude-sisyphus`). It introduces a collection of slash commands and terminal CLI commands that coordinate multiple Claude Code subagents working in parallel on a single codebase. The central feature is `/autopilot`, which accepts a natural-language task description and automatically delegates subtasks across agents without requiring users to configure or manage the orchestration manually. Setup is handled through `/setup` or `/omc-setup` inside a Claude Code session, after which skills and agents become available immediately. The project also includes a `better-sqlite3`-backed runtime for tracking agent state across sessions. Developers who want to parallelize agentic coding work in Claude Code, particularly teams splitting large features across concurrent agents, are the primary audience. A sibling project, oh-my-codex, ports the same orchestration approach to OpenAI Codex CLI.
24 items en este repositorio
Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode
Process-first advisor routing for Claude, Codex, Gemini, Antigravity, Grok, or Cursor via `omc ask`, with artifact capture and no raw CLI assembly
Stateful single-mission improvement loop with strict evaluator contract, markdown decision logs, and max-runtime stop behavior
Cancel any active OMC mode (autopilot, ralph, ultragoal, swarm, ultrapilot, pipeline, team) and clean up retired legacy state
Claude-Codex-Gemini tri-model orchestration via /ask codex + /ask antigravity (or gemini), then Claude synthesizes results
Expert code review specialist with severity-rated feedback, logic defect detection, SOLID principle checks, style, performance, and quality strategy
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.
Configure notification integrations (Telegram, Discord, Slack) via natural language
Work plan and code review expert — thorough, structured, multi-perspective (Opus)
Diagnose the current OMC session or repo state using logs, traces, state, and focused reproduction
Root-cause analysis, regression isolation, stack trace analysis, build/compilation error resolution
2-stage pipeline: trace (causal investigation) -> deep-interview (requirements crystallization) with 3-point injection
Socratic deep interview with mathematical ambiguity gating before explicit execution approval
Lay the keel of the shipyard harness in any repo — the 4-pillar shared environment (Context, Rules, Tools, Standards) across 5 surfaces (CLAUDE.md, skills, design-system, mcp/cli, shared context) so that every human and agent inherits the same design language and anyone can ship. Run once per repo; re-run with --check to audit drift.
Resumen de Subagents
English | 한국어 | 中文 | 日本語 | Español | Tiếng Việt | Português
oh-my-claudecode
For Codex users: Check out oh-my-codex — the same orchestration experience for OpenAI Codex CLI.
Liked OmC but found it a bit overkill? Try gajae-code. Keeps Claude OAuth as-is while being faster, cheaper, simpler, and more powerful — with an SDK-based integration path built for OpenClaw, Hermes, Grokbot, and similar agent runtimes.
Multi-agent orchestration for Claude Code. Zero learning curve.
Don't learn Claude Code. Just use OMC.
Get Started • Documentation • CLI Reference • Workflows • Migration Guide • Discord
Core Maintainers
| Role | Name | GitHub |
|---|---|---|
| Creator & Lead | Yeachan Heo | @Yeachan-Heo |
Ambassadors
| Name | GitHub |
|---|---|
| Sigrid Jin | @sigridjineth |
Document Specialists
| Name | GitHub |
|---|---|
| devswha | @devswha |
Top Collaborators
| Name | GitHub | Commits |
|---|---|---|
| JunghwanNA | @shaun0927 | 65 |
| riftzen-bit | @riftzen-bit | 52 |
| Seunggwan Song | @Nathan-Song | 20 |
| BLUE | @blue-int | 20 |
| Junho Yeo | @junhoyeo | 15 |
Quick Start
Step 1: Install
Marketplace/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@latestKnown npm warning: npm may print
deprecated prebuild-install@7.1.3during the CLI install. This currently comes from the upstreambetter-sqlite3native-addon dependency (better-sqlite3 -> prebuild-install);prebuild-install@7.1.3is still the latest published version, so there is no safe repo-side dependency bump or override to remove the warning yet. The warning is tracked in #2913 and does not by itself mean the OMC CLI install failed.
Step 2: Setup
# Inside a Claude Code / OMC session
/omc-setup
# From your terminal
omc setupIf you run OMC via omc --plugin-dir or claude --plugin-dir, add --plugin-dir-mode to omc setup (or export OMC_PLUGIN_ROOT before running it) so the installer doesn't duplicate skills/agents that the plugin already provides at runtime. See the Plugin directory flags section in REFERENCE.md for a complete decision matrix and all available flags.
Step 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 tasksNamed autopilot stage profiles (v1)
Select a configured stage profile only through /autopilot --workflow:
/autopilot --workflow plan-build-qa "build a REST API for managing tasks"Profiles are configured under autopilot.workflows in .claude/omc.jsonc (project) or ~/.config/claude-omc/config.jsonc (user). A v1 profile contains only version: 1 and stages:
{
"autopilot": {
"workflows": {
"plan-build-qa": {
"version": 1,
"stages": ["ralplan", "execution", "qa"]
}
}
}
}The admitted sequences are [ralplan, execution], [ralplan, execution, ralph], [ralplan, execution, qa], and [ralplan, execution, ralph, qa]. A project profile of the same name wholly replaces the user profile; different names coexist. Environment variables cannot define profiles. Profiles remain within autopilot's existing state, cancel, resume, Stop, and HUD lifecycle; legacy invocations without --workflow remain compatible.
Named profiles currently require Linux with the flock utility because their transcript evidence boundary uses Linux no-follow file-descriptor traversal and their recoverable mutation lock uses kernel advisory locking. Unsupported environments reject explicit --workflow invocation before creating or changing autopilot state; legacy autopilot remains available.
V1 intentionally excludes model fields or routing (stageModels), inline execution, dynamic commands/modes/state, arbitrary stages or plugins, and the separate custom-skill frontmatter parser mismatch. See Named Autopilot Stage Profiles ADR and Reference.
That'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 the npm/runtime path (npm i -g oh-my-claude-sisyphus@latest) or from a local checkout.In-session skills: run
/...inside a Claude Code session after installing the plugin/setup flow.
| Feature | Terminal CLI | In-session skill | Notes |
|---|---|---|---|
| Setup | omc setup | /omc-setup | Both are real entrypoints. |
| Ask providers | omc ask codex "review this patch" | /ask codex "review this patch" | Both route through the same advisor flow. Providers: claude, codex, gemini, antigravity, grok, cursor, muse. |
| Team orchestration | omc team 2:codex "review auth flow" | /team 3:executor "fix all TypeScript errors" | Both exist, but they are different runtimes: omc team launches tmux CLI workers; /team runs the in-session native team workflow. |
| Pre-flight danger scan | omc lookout scan --brief "..." [--json] [--strict] | — | Advisory only: scans the task briefing and workspace before an unattended run and reports danger findings (findings/severity contract). Exit codes: 0 for successful non-strict scans (and strict scans without high-risk signals), 1 --strict with high-risk signals, 2 usage/scan error. |
| Autopilot / Ralph / Execute / Deep Interview | — | /autopilot ..., /ralph ..., /execute ..., /deep-interview ... | These are in-session skills. There is no omc autopilot / omc ralph / omc execute CLI subcommand in this repo. |
| Autoresearch | omc autoresearch (hard-deprecated shim) | /deep-interview --autoresearch ... + /oh-my-claudecode:autoresearch | Setup stays in deep-interview; execution now belongs to the stateful skill. |
VS Code, Agent SDK, and automation scope
Lo que la gente pregunta sobre oh-my-claudecode
¿Qué es Yeachan-Heo/oh-my-claudecode?
Yeachan-Heo/oh-my-claudecode es subagents para el ecosistema de Claude AI. Teams-first Multi-agent orchestration for Claude Code Tiene 40.2k estrellas en GitHub y su última actualización registrada es del 2026-10-23.
¿Cómo se instala oh-my-claudecode?
Puedes instalar oh-my-claudecode clonando el repositorio (https://github.com/Yeachan-Heo/oh-my-claudecode) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar Yeachan-Heo/oh-my-claudecode?
Nuestro agente de seguridad ha analizado Yeachan-Heo/oh-my-claudecode y le ha asignado un Trust Score de 100/100 (tier: Verified). Revisa el desglose completo de comprobaciones superadas y flags en esta página.
¿Quién mantiene Yeachan-Heo/oh-my-claudecode?
Yeachan-Heo/oh-my-claudecode es mantenido por Yeachan-Heo. La última actividad registrada en GitHub es del 2026-10-23, con 2 issues abiertos.
¿Hay alternativas a oh-my-claudecode?
Sí. En ClaudeWave puedes explorar subagents similares en /categories/agents, ordenados por popularidad o actividad reciente.
¿Mantienes este repo? Muestra su Trust Score en tu README
La insignia muestra el Trust Score y el veredicto actuales de este repositorio y enlaza a esta página. Sigue los datos del catálogo: nadie puede comprar ni editar la puntuación que enseña.
[](https://claudewave.com/en/repo/yeachan-heo-oh-my-claudecode)<a href="https://claudewave.com/en/repo/yeachan-heo-oh-my-claudecode"><img src="https://claudewave.com/api/badge/yeachan-heo-oh-my-claudecode" alt="ClaudeWave Trust Score for Yeachan-Heo/oh-my-claudecode" width="320" height="64"></a>