whatisgithub

What is claude-codex-orchestrator?

bostonvex/claude-codex-orchestrator — explained in plain English

Analysis updated 2026-05-18

1HTMLAudience · developerComplexity · 4/5Setup · moderate

In one sentence

A Claude Code skill that runs an autonomous work loop, splitting tasks between Claude and Codex and tracking every task as a self pacing GitHub issue.

Mindmap

mindmap
  root((codex-loop))
    What it does
      Splits tasks
      Claude and Codex
      Self paces
    Tech stack
      Claude Code
      Codex CLI
      GitHub CLI
    Use cases
      Auto assign issues
      Unattended loop
      Issue based state
    Audience
      Developers
      Automation builders

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Automatically hand backlog issues to Codex for implementation while Claude verifies and merges.

USE CASE 2

Run an unattended, self pacing development loop that restarts itself without manual kicks.

USE CASE 3

Track the state of every AI assigned task using GitHub issue labels instead of in-memory context.

What is it built with?

Claude CodeCodex CLIGitHub CLINode.jsGit

How does it compare?

bostonvex/claude-codex-orchestratorabhas9/escape-runabhishek-kumar09/mern-live-js-june-2021
Stars111
LanguageHTMLHTMLHTML
Last pushed2021-09-13
MaintenanceDormant
Setup difficultymoderateeasymoderate
Complexity4/52/52/5
Audiencedevelopergeneraldeveloper

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · moderate Time to first run · 30min

Requires an authenticated gh CLI with merge and push permissions, plus a Codex CLI subscription or OpenAI API key for local workers.

So what is it?

codex-loop is a tool that turns Claude Code into a self running work loop for any code repository. It splits a backlog of tasks between two AI coding assistants: Claude, which plans, checks, merges, and ships the work, and Codex, which implements the tasks it is assigned. Every task is tracked as a normal GitHub issue, and the labels plus a small set of comment conventions on that issue act as the memory of where each task stands, so nothing about the state depends on the AI remembering anything between runs. The main problem it solves is that a typical automated loop stops as soon as its work queue is briefly empty or one pass finishes, and a person has to manually start it again. codex-loop instead paces itself: it checks more frequently while work is actively moving, checks less often when there is nothing to do, and stops entirely once everything is finished or paused, without needing anyone to restart it by hand. Using it requires Claude Code itself, the gh command line tool logged into the target repository, and git. By default it also needs the codex command line tool, which runs on Node.js and is billed through its own ChatGPT or Codex subscription or an OpenAI API key rather than through Claude or Anthropic. Depending on setup, work can also be sent to a Codex Cloud agent instead of running Codex locally. The account running all of this needs permission in the target repository to create labels and issues, merge pull requests, and push to the default branch. First use in a repository triggers an automatic setup step that creates the needed labels and a single pinned tracking issue holding its configuration, and every setting in that configuration has a working default so nothing has to be changed before a first run. From there, a person opens GitHub issues for each piece of work, labels each one for either Claude or Codex to implement, and either runs one iteration by hand or starts the self pacing autonomous mode. The loop never force pushes and never merges when checks are failing.

Copy-paste prompts

Prompt 1
Walk me through installing codex-loop as a Claude Code skill and scaffolding it in my repository.
Prompt 2
Show me how to label GitHub issues so codex-loop assigns them to Codex versus Claude.
Prompt 3
Explain the difference between running /codex-loop once and running /loop /codex-loop for autonomous mode.
Prompt 4
Help me set the worker and verify config keys in codex-loop's Control Tower issue for my repo.

Frequently asked questions

What is claude-codex-orchestrator?

A Claude Code skill that runs an autonomous work loop, splitting tasks between Claude and Codex and tracking every task as a self pacing GitHub issue.

What language is claude-codex-orchestrator written in?

Mainly HTML. The stack also includes Claude Code, Codex CLI, GitHub CLI.

How hard is claude-codex-orchestrator to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is claude-codex-orchestrator for?

Mainly developer.

Open on GitHub → Ask about another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.