Skills oh-my-claudecode

install

source · Clone the upstream repo

git clone https://github.com/TerminalSkills/skills

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/TerminalSkills/skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/oh-my-claudecode" ~/.claude/skills/terminalskills-skills-oh-my-claudecode && rm -rf "$T"

manifest: skills/oh-my-claudecode/SKILL.md

safety · automated scan (low risk)

This is a pattern-based risk scan, not a security review. Our crawler flagged:

global npm install

Always read a skill's source content before installing. Patterns alone don't mean the skill is malicious — but they warrant attention.

source content

oh-my-claudecode

Multi-agent orchestration for Claude Code. Run teams of AI agents in parallel — each with a role, shared context, and coordinated workflows. Zero learning curve.

GitHub: Yeachan-Heo/oh-my-claudecode

Overview

oh-my-claudecode (OMC) lets you run teams of Claude Code agents in parallel, each with assigned roles. It manages a staged pipeline (plan → PRD → execute → verify → fix) and supports mixing providers (Claude, Codex, Gemini). Agents share context through the filesystem and git branches, with automatic conflict resolution.

Instructions

Installation

Via Claude Code Plugin Marketplace (recommended):

/plugin marketplace add https://github.com/Yeachan-Heo/oh-my-claudecode
/plugin install oh-my-claudecode

Via npm:

npm i -g oh-my-claude-sisyphus@latest

Initial Setup

Run inside Claude Code:

/setup
/omc-setup

Enable experimental teams in

~/.claude/settings.json

{
  "env": {
    "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"
  }
}

Team Pipeline

Team mode runs a staged pipeline for every task:

team-plan → team-prd → team-exec → team-verify → team-fix (loop)

Plan — break down the task into sub-tasks and dependencies
PRD — generate a product requirements document
Execute — spawn N agents working in parallel
Verify — validate output against requirements
Fix — loop back to fix issues until tests pass

Agent Roles

Role	Focus	Example Tasks
`executor`	General coding	Feature implementation, refactoring
`reviewer`	Code review	PR reviews, architecture feedback
`tester`	Quality assurance	Test writing, coverage analysis
`architect`	System design	API design, database schema

Context Sharing

Agents in a team share context through:

Shared filesystem — all agents see the same project files
Team state file —
```
.omc/team-state.json
```
tracks progress
Git branches — each agent works on a feature branch, merged at verify stage

Configuration

~/.omc/config.json

{
  "defaultTeamSize": 3,
  "defaultRole": "executor",
  "providers": {
    "claude": { "enabled": true },
    "codex": { "enabled": true, "model": "codex-latest" },
    "gemini": { "enabled": true, "model": "gemini-2.5-pro" }
  },
  "pipeline": {
    "skipPRD": false,
    "autoFix": true,
    "maxFixLoops": 3
  }
}

Requires

codex

gemini

CLIs installed and an active tmux session for multi-provider workers (v4.4.0+).

Examples

Example 1: Team Execution with Mixed Roles

# Spawn 3 executor agents to fix all TypeScript errors
/team 3:executor "fix all TypeScript errors"

# Use Codex agents for code review
omc team 2:codex "review auth module for security issues"

# Gemini agents for UI work
omc team 2:gemini "redesign UI components for accessibility"

Example 2: Autopilot and Deep Interview

# Let OMC handle everything — from planning to execution
autopilot: build a REST API for managing tasks

# When requirements are vague, use Socratic questioning first
/deep-interview "I want to build a task management app"
# The interview clarifies requirements before any code is written

Example 3: Tri-Model Advisor

Route work to Codex + Gemini, then Claude synthesizes the results:

/ccg Review this PR — architecture (Codex) and UI components (Gemini)

Guidelines

Start with
```
autopilot:
```
for well-defined tasks
Use
```
/deep-interview
```
when requirements are fuzzy
Mix providers: Codex for review, Gemini for UI, Claude for logic
Keep team size at 5 or fewer for most tasks — diminishing returns beyond that
Use
```
omc team status <task-id>
```
to monitor long-running teams
The verify-fix loop catches most issues automatically
When multiple agents modify the same file, OMC detects conflicts at merge time and spawns a resolver agent