home / skills / yeachan-heo / oh-my-claudecode / omc-teams

omc-teams skill

/skills/omc-teams

This skill launches multiple tmux CLI workers (claude, codex, or gemini) to execute tasks in parallel and return structured results.

npx playbooks add skill yeachan-heo/oh-my-claudecode --skill omc-teams

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
6.1 KB
---
name: omc-teams
description: Spawn claude, codex, or gemini CLI workers in tmux panes for parallel task execution
aliases: []
---

# OMC Teams Skill

Spawn N CLI worker processes in tmux panes to execute tasks in parallel. Supports `claude`, `codex`, and `gemini` agent types.

`/omc-teams` is a legacy compatibility skill for the CLI-first runtime: use `omc team ...` commands (not deprecated MCP runtime tools).

## Usage

```bash
/oh-my-claudecode:omc-teams N:claude "task description"
/oh-my-claudecode:omc-teams N:codex "task description"
/oh-my-claudecode:omc-teams N:gemini "task description"
```

### Parameters

- **N** - Number of CLI workers (1-10)
- **agent-type** - `claude` (Claude CLI), `codex` (OpenAI Codex CLI), or `gemini` (Google Gemini CLI)
- **task** - Task description to distribute across all workers

### Examples

```bash
/omc-teams 2:claude "implement auth module with tests"
/omc-teams 2:codex "review the auth module for security issues"
/omc-teams 3:gemini "redesign UI components for accessibility"
```

## Requirements

- **tmux binary** must be installed and discoverable (`command -v tmux`)
- **Active tmux session** required to launch worker panes (`$TMUX` set, or start/attach tmux first)
- **claude** CLI: `npm install -g @anthropic-ai/claude-code`
- **codex** CLI: `npm install -g @openai/codex`
- **gemini** CLI: `npm install -g @google/gemini-cli`

## Workflow

### Phase 0: Verify prerequisites

Check tmux explicitly before claiming it is missing:

```bash
command -v tmux >/dev/null 2>&1
```

- If this fails, report that **tmux is not installed** and stop.
- If `tmux` exists but `$TMUX` is empty, report that the user is **not currently inside an active tmux session**. Do **not** say tmux is missing; tell them to start or attach tmux, then rerun.
- If you need to confirm the active session, use:

```bash
tmux display-message -p '#S'
```

### Phase 1: Parse + validate input

Extract:

- `N` — worker count (1–10)
- `agent-type` — `claude|codex|gemini`
- `task` — task description

Validate before decomposing or running anything:

- Reject unsupported agent types up front. `/omc-teams` only supports **`claude`**, **`codex`**, and **`gemini`**.
- If the user asks for an unsupported type such as `expert`, explain that `/omc-teams` launches external CLI workers only.
- For native Claude Code team agents/roles, direct them to **`/oh-my-claudecode:team`** instead.

### Phase 2: Decompose task

Break work into N independent subtasks (file- or concern-scoped) to avoid write conflicts.

### Phase 3: Start CLI team runtime

Activate mode state (recommended):

```text
state_write(mode="team", current_phase="team-exec", active=true)
```

Start workers via CLI:

```bash
omc team <N>:<claude|codex|gemini> "<task>"
```

Team name defaults to a slug from the task text (example: `review-auth-flow`).

After launch, verify the command actually executed instead of assuming Enter fired. Check pane output and confirm the command or worker bootstrap text appears in pane history:

```bash
tmux list-panes -a -F '#{session_name}:#{window_index}.#{pane_index} #{pane_id} #{pane_current_command}'
tmux capture-pane -pt <pane-id> -S -20
```

Do not claim the team started successfully unless pane output shows the command was submitted.

### Phase 4: Monitor + lifecycle API

```bash
omc team status <team-name>
omc team api list-tasks --input '{"team_name":"<team-name>"}' --json
```

Use `omc team api ...` for task claiming, task transitions, mailbox delivery, and worker state updates.

### Phase 5: Shutdown (only when needed)

```bash
omc team shutdown <team-name>
omc team shutdown <team-name> --force
```

Use shutdown for intentional cancellation or stale-state cleanup. Prefer non-force shutdown first.

### Phase 6: Report + state close

Report task results with completion/failure summary and any remaining risks.

```text
state_write(mode="team", current_phase="complete", active=false)
```

## Deprecated Runtime Note

Legacy MCP runtime tools are deprecated for execution:

- `omc_run_team_start`
- `omc_run_team_status`
- `omc_run_team_wait`
- `omc_run_team_cleanup`

If encountered, switch to `omc team ...` CLI commands.

## Error Reference

| Error                        | Cause                               | Fix                                                                                 |
| ---------------------------- | ----------------------------------- | ----------------------------------------------------------------------------------- |
| `not inside tmux`            | Shell not running inside tmux       | Start tmux and rerun                                                                |
| `Unsupported agent type`     | Requested agent is not claude/codex/gemini | Use `claude`, `codex`, or `gemini`; for native Claude Code agents use `/oh-my-claudecode:team` |
| `codex: command not found`   | Codex CLI not installed             | `npm install -g @openai/codex`                                                      |
| `gemini: command not found`  | Gemini CLI not installed            | `npm install -g @google/gemini-cli`                                                 |
| `Team <name> is not running` | stale or missing runtime state      | `omc team status <team-name>` then `omc team shutdown <team-name> --force` if stale |
| `status: failed`             | Workers exited with incomplete work | inspect runtime output, narrow scope, rerun                                         |

## Relationship to `/team`

| Aspect       | `/team`                                   | `/omc-teams`                                         |
| ------------ | ----------------------------------------- | ---------------------------------------------------- |
| Worker type  | Claude Code native team agents            | claude / codex / gemini CLI processes in tmux        |
| Invocation   | `TeamCreate` / `Task` / `SendMessage`     | `omc team [N:agent]` + `status` + `shutdown` + `api` |
| Coordination | Native team messaging and staged pipeline | tmux worker runtime + CLI API state files            |
| Use when     | You want Claude-native team orchestration | You want external CLI worker execution               |

Overview

This skill spawns N CLI worker processes in tmux panes to execute tasks in parallel using claude, codex, or gemini CLIs. It uses a tmux-based runtime so each worker runs as a visible CLI process, writes results to inbox/done files, and returns structured JSON summaries. Designed for teams-first multi-agent orchestration where CLI autonomy and parallel execution are required.

How this skill works

The skill parses a user command (N, agent-type, and task), decomposes the task into N independent subtasks, and starts a background job via the MCP start tool. A runtime process creates tmux split panes, launches the selected CLI for each worker, and each worker reads its inbox and writes done.json on completion. A single wait call polls until the job reaches a terminal state and then returns a consolidated result object; workers remain running if the wait times out.

When to use it

  • Run parallel, independent CLI agents for coding, review, or testing tasks.
  • You need visible, debuggable worker processes inside tmux panes.
  • You want to mix claude, codex, or gemini CLI workers across a job.
  • You need a single, structured result instead of managing N separate processes.
  • You prefer file-based inbox/done coordination rather than native agent messaging.

Best practices

  • Keep each subtask independent and scoped to avoid conflicting writes.
  • Use 1–10 workers; increase workers only when tasks can run without coordination.
  • Ensure tmux is running and CLIs are installed before starting a job.
  • Set sensible timeoutSeconds; a default 60s is recommended for quick jobs, increase for longer tasks.
  • Use omc_run_team_status before cleanup to inspect live progress if wait times out.

Example use cases

  • Spawn 3 gemini workers to redesign UI components across different feature folders.
  • Run 2 codex workers to perform independent security reviews of separate modules.
  • Start 2 claude workers to implement and test two distinct backend endpoints concurrently.
  • Launch a single codex worker to generate comprehensive tests for a specific directory.

FAQ

What happens if omc_run_team_wait times out?

Workers are left running; you can call omc_run_team_wait again or use omc_run_team_cleanup to stop panes.

Which agent types are supported?

Supported types are claude, codex, and gemini; other types are rejected with an error.

How do workers communicate their results?

Each worker writes a done.json sentinel into its workspace; the runtime collects those files and returns structured JSON.