Plugin · Claude Code · AI Agents

Kingbootoshi Codex Orchestrator

kingbootoshi-codex-orchestrator is a Claude Code plugin for the Build phase that spawns and manages OpenAI Codex agents in tmux sessions so Claude can delegate, monitor, and collect parallel coding results.

by kingbootoshi · github.com/kingbootoshi/codex-orchestrator

Let Claude Code spawn and monitor OpenAI Codex workers in parallel tmux sessions when one agent cannot finish the codebase alone.

263
GitHub stars
0
Installs
0
Community votes
One vote per signed-in builder - it helps surface the tools the community actually relies on.
Install

Add it to Claude Code

Install the plugin in Claude Code. One command, paste-ready.

Install the plugin
/plugin install kingbootoshi-codex-orchestrator@kingbootoshi/codex-orchestrator
Add to ClaudeUse the Agent APISkillselion is itself an MCP server - your agent can fetch this config directly.
Agent API

Built to be called by your agent

Skillselion is itself an MCP server. Your agent can pull this entry and a paste-ready install config straight from the API - no copy-paste.

Retrieve this entry with skillselion.get_details("plugin:kingbootoshi/codex-orchestrator") and the paste-ready config with skillselion.get_install_config("plugin:kingbootoshi/codex-orchestrator").

About

What it does

kingbootoshi-codex-orchestrator is a Claude Code plugin built to delegate work to OpenAI Codex agents running in tmux sessions while Claude remains the orchestrator. Solo builders hitting throughput limits on large refactors, test fixes, or multi-file features can spawn parallel Codex workers, monitor progress, send follow-ups, and capture results without manually babysitting separate terminal panes. The README and keyword list (agents, claude, codex, delegation, orchestrate, parallel, sessions, tmux, monitor, results) describe a systems-integration style plugin rather than a brainstorming methodology skill. Expect intermediate complexity: you need tmux, working Codex CLI auth, and comfort reading session output. It pairs naturally with ship-phase review when you want Codex to implement and Claude to integrate or gate merges. This is multi-agent dev infrastructure, not a marketing or analytics tool—install when Claude Code is your control plane and Codex is your secondary implementer pool.

Highlights

  • Delegates tasks to OpenAI Codex agents through tmux sessions
  • Designed explicitly for Claude Code orchestration over Codex workers
  • Supports parallel spawn, monitor, capture messages, follow-up, and results aggregation
  • Single-plugin bundle; kingbootoshi/codex-orchestrator with ~263 GitHub stars
  • Keyword surface spans orchestration, sessions, delegation, progress, and claude↔codex handoff

Why builders use it

One Claude Code session cannot efficiently run several long Codex jobs in parallel or track their output without brittle manual terminal juggling.

After registration, Claude Code can orchestrate multiple Codex tmux sessions with delegation, monitoring, follow-ups, and captured results in one workflow.

At a glance

  • Type - Plugin in AI Agents.
  • Adoption - 0 installs, 263 stars, 0 votes.

FAQ

Who is kingbootoshi-codex-orchestrator for?

It is for developers who orchestrate from Claude Code and want OpenAI Codex agents running as managed tmux workers with progress and result capture.

When should I use kingbootoshi-codex-orchestrator?

Use it during build (and ship review) when tasks should run in parallel Codex sessions while Claude coordinates delegation and follow-up messages.

How do I add kingbootoshi-codex-orchestrator to my agent?

Install the kingbootoshi/codex-orchestrator Claude Code plugin, ensure tmux and Codex CLI are configured, then invoke the orchestrator commands from Claude Code per the repo docs.

Discussion

Comments

Share how you use kingbootoshi-codex-orchestrator, gotchas, or tips for other indie builders.

No comments yet - be the first to share how you use it.

This week for builders

Five minutes, every Monday — the tools, releases and tactics for shipping solo.

unsubscribe anytime.