omc-teams_skill
- TypeScript
9.3k
GitHub Stars
1
Bundled Files
2 months ago
Catalog Refreshed
3 months ago
First Indexed
Readme & install
Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.
Installation
Preview and clipboard use veilstrat where the catalogue uses aiagentskills.
npx veilstrat add skill yeachan-heo/oh-my-claudecode --skill omc-teams- SKILL.md6.1 KB
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
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.