📄 skillActivePromisinghigh

codex-orchestrator

by kingbootoshi

Delegate tasks to OpenAI Codex agents via tmux sessions. Designed for Claude Code orchestration.

Supported Platforms

🤖 Claude Code🧠 Codex

Stars

312

Skill Type

🔄 Business Process & Team Automation

Quality Score

115/200

License

MIT

Forks

37

Last Updated

Jun 11, 2026

Discovered

Apr 17, 2026

Validation

Passed

github.com/kingbootoshi/codex-orchestrator

Quality Breakdown

115/ 200

Content Signals

â—‹Gotchas/Edge Cases+40
✓Progressive Disclosure+30
â—‹Trigger Description+20
✓Verification/Safety+20
✓Code Examples+15
✓Composability+15

Repo Health

✓Recent Activity+15
✓Scripts/Automation+10
✓Real Usage (Issues)+10
✓Single Responsibility+10
â—‹Config/Persistence+10
✓Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

high

Broad system access required. Carefully review permissions before installing.

Active

Updated within the last 90 days. Actively maintained.

Unverified skill. Always review source code before installing any skill from an unknown author.

Risk Assessment

  • Spawn subagents capability: Repository explicitly designed to spawn and orchestrate multiple parallel AI agents via tmux sessions without apparent human approval gates between tasks
  • Autonomous task delegation: Enables Claude to autonomously delegate coding tasks to OpenAI Codex agents and monitor execution
  • Shell/Bash execution: Contains bin/codex-agent and bin/codex-bg executables that interface with tmux for terminal command execution
  • Install scripts: plugins/codex-orchestrator/scripts/install.sh present - automated bootstrap script that downloads and executes code from repository
  • Persistent configuration: .claude-plugin directory and CLAUDE.md indicate Claude-specific configuration modification and persistence
  • Multi-agent orchestration: Explicitly advertises ability to 'spawn parallel coding agents' and send 'follow-up messages mid-task'