codex-worker

Orchestrate parallel Codex CLI agents in isolated git worktrees and tmux sessions.

Updated Feb 8, 2026

Search Tags:#automation #codex #orchestration #worktree #tmux #ai-agent #parallelism

Ready to run

npx skills add https://github.com/Zidane786/os-coding-agents --skill codex-worker

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: codex-worker
Source: https://github.com/Zidane786/os-coding-agents/tree/main/kimi-cli/.agents/skills/codex-worker
Command: npx skills add https://github.com/Zidane786/os-coding-agents --skill codex-worker

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Orchestrate multiple Codex CLI agents running in parallel, enabling decomposition of complex tasks into independent subtasks and reducing overall completion time.

Core Features & Use Cases

Parallel task execution: spawn multiple codex workers, each in its own git worktree and tmux session, to tackle subtasks concurrently.
Preflight checks: validate that codex, tmux, and git are available and that the repository supports worktrees.
Clear naming and lifecycle: standardized task names, worktrees, and tmux sessions to simplify monitoring and cleanup.
Use cases: triage multiple issues, refactor several modules, and run lint/tests across packages in parallel.
Replaces Task tool when codex and tmux are available to enable richer agent capabilities.

Quick Start

Create a codex worker by launching a new tmux session and a dedicated worktree for your task, then attach to the session to interact with the agent.

Frequently Asked Questions about codex-worker

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I run multiple Codex agents in parallel using tmux?▼

You can run multiple Codex agents in parallel by orchestrating them through isolated git worktrees and tmux sessions. This setup allows each agent to handle an independent subtask concurrently, reducing overall completion time for complex projects.

What are the prerequisites for spawning parallel Codex CLI workers?▼

To spawn parallel Codex CLI workers, your environment must have the codex CLI, tmux, and a git repository configured to support worktrees. These preflight requirements ensure isolated workspaces and terminal sessions for each agent.

When should I orchestrate Codex workers instead of using the built-in Task tool?▼

You should orchestrate Codex workers instead of the built-in Task tool when codex and tmux are available, enabling richer agent capabilities. It is ideal for decomposing tasks into independent subtasks like triaging issues or parallel module refactors.

Can I manage and clean up parallel git worktrees and tmux sessions easily?▼

Yes, you can manage and clean up parallel git worktrees and tmux sessions using standardized naming conventions and lifecycle commands. This approach simplifies monitoring active agents and safely removing worktrees after task completion.

What is the best way to refactor multiple modules concurrently with AI agents?▼

The best way to refactor multiple modules concurrently is to decompose the task into independent subtasks and spawn a dedicated Codex worker for each. Each worker operates in its own isolated git worktree and tmux session to prevent conflicts.