oh-my-claudecode
Orchestrate multi-agent Claude Code teams — assign roles, coordinate parallel tasks, share context between agents, and manage team workflows. Use when: running multiple Claude Code agents simultaneously, building team-based AI development workflows, coordinating complex multi-agent coding projects.
What this skill does
# 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](https://github.com/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):
```bash
/plugin marketplace add https://github.com/Yeachan-Heo/oh-my-claudecode
/plugin install oh-my-claudecode
```
Via npm:
```bash
npm i -g oh-my-claude-sisyphus@latest
```
### Initial Setup
Run inside Claude Code:
```bash
/setup
/omc-setup
```
Enable experimental teams in `~/.claude/settings.json`:
```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)
```
1. **Plan** — break down the task into sub-tasks and dependencies
2. **PRD** — generate a product requirements document
3. **Execute** — spawn N agents working in parallel
4. **Verify** — validate output against requirements
5. **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`:
```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
```bash
# 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
```bash
# 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:
```bash
/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
## Resources
- [Documentation](https://yeachan-heo.github.io/oh-my-claudecode-website)
- [CLI Reference](https://yeachan-heo.github.io/oh-my-claudecode-website/docs.html#cli-reference)
- [Workflows](https://yeachan-heo.github.io/oh-my-claudecode-website/docs.html#workflows)
- [Discord](https://discord.gg/qRJw62Gvh7)
- [Migration Guide](https://github.com/Yeachan-Heo/oh-my-claudecode/blob/main/docs/MIGRATION.md)
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.