This compatibility command keeps `/oh-my-claudecode:ask` available without loading the full `ask` skill description in every Claude Code session.
This compatibility command keeps `/oh-my-claudecode:autoresearch` available without loading the full `autoresearch` skill description in every Claude Code session.
This compatibility command keeps `/oh-my-claudecode:ccg` available without loading the full `ccg` skill description in every Claude Code session.
Prepare OMC context for a manual Claude Code /compact handoff.
This compatibility command keeps `/oh-my-claudecode:configure-notifications` available without loading the full `configure-notifications` skill description in every Claude Code session.
Pre-planning consultant for requirements analysis (Opus)
Strategic Architecture & Debugging Advisor (Opus, READ-ONLY)
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.
Work plan and code review expert — thorough, structured, multi-perspective (Opus)
Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode
QA cycling workflow - test, verify, fix, repeat until goal met
Parallel execution engine for high-throughput task completion
Verify that a change really works before you claim completion
Structured visual QA verdict for screenshot-to-reference comparisons
Matches all tools
Hooks run on every tool call, not just specific ones
Admin access level
Server config contains admin-level keywords
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Executables (bin/) — files in this plugin's bin/directory are added to the Bash tool's PATH while the plugin is enabled.
Executes bash commands
Executes bash commands
Hook triggers when Bash tool is used
Hook triggers when Bash tool is used
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
English | 한국어 | 中文 | 日本語 | Español | Tiếng Việt | Português
Multi-agent orchestration for Claude Code. Zero learning curve.
Don't learn Claude Code. Just use OMC.
Get Started • Full Reference • Migration Guide • Architecture
Step 1: Install (from a local checkout)
This fork is run directly from a local checkout — there is no published npm package or marketplace listing.
# Clone this repo
git clone https://github.com/markrmiller/oh-my-claudecode.git
cd oh-my-claudecode
# Install dependencies and build the plugin + CLI
npm install
npm run build
# Expose the `omc` command from the checkout (ensure ~/.local/bin is on your PATH)
mkdir -p ~/.local/bin
ln -sf "$PWD/bridge/cli.cjs" ~/.local/bin/omc
omc --version
Step 2: Setup
Point Claude Code at your local checkout and run setup in one step:
# From the checkout directory
omc --plugin-dir "$PWD" setup --plugin-dir-mode
Then launch Claude Code normally — it will use your local checkout. Inside a session you can also re-run /setup or /omc-setup.
.mcp.jsonserver conflict: with--plugin-dir, the repo's.mcp.jsonserver named"t"collides with the plugin's own. Add{ "disabledMcpjsonServers": ["t"] }to your~/.claude/settings.json. See the Plugin directory flags section in REFERENCE.md and CONTRIBUTING.md for the full local-checkout flows.
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 tasks
That's it. Everything else is automatic.
OMC exposes two different surfaces:
omc ... from your shell using the omc symlink created from your local checkout (see Install above)./... inside a Claude Code session after installing the plugin/setup flow.| 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 "review this patch" | /ask codex "review this patch" | Both route through the same advisor flow. Providers: claude, codex, gemini, grok. |
| 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. |
| Autopilot / Ralph / Ultrawork / Deep Interview | — | /autopilot ..., /ralph ..., /ultrawork ..., /deep-interview ... | These are in-session skills. There is no omc autopilot / omc ralph / omc ultrawork 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. |
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.
npx claudepluginhub markrmiller/oh-my-claudecodev9.52.0 - Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.
Supergraph enforces a complete, evidence-based coding pipeline — scan → plan → TDD → fix → verify → review — grounded in real codebase analysis at every step. It combines AST dependency graphs, LSP-level code intelligence, and a structured skill chain so Claude never guesses about impact before making a change.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.