What is codex-orchestrator CLAUDE.md?

A project instruction file for a TypeScript and Bun command-line tool that delegates work to Codex agents through tmux terminal sessions. It also describes the repository's plugin structure and important source files.

It helps developers start the CLI, use its shell wrapper, run health checks, and find the files responsible for jobs, configuration, file loading, and session parsing.

It gives coding agents consistent guidance for developing, running, and checking the project.

How kingbootoshi/codex-orchestrator configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to kingbootoshi/codex-orchestrator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/kingbootoshi/codex-orchestrator/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/kingbootoshi/codex-orchestrator

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/kingbootoshi/codex-orchestrator/claude-md/github.svg)](https://agentmods.dev/instructions/kingbootoshi/codex-orchestrator/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/kingbootoshi/codex-orchestrator/claude-md"><img src="https://agentmods.dev/badge/instructions/kingbootoshi/codex-orchestrator/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/kingbootoshi/codex-orchestrator/claude-md"><img src="https://agentmods.dev/badge/instructions/kingbootoshi/codex-orchestrator/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 506 This file is loaded in full into every session.

When invoked 506 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00506	$0.00506
Opus 5.5	$0.00202	$0.00202
Sonnet 5.5	$0.00101	$0.00101
Haiku 4.5	$0.00051	$0.00051

Measured 2mo ago against content hash 2e8842665fde, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

codex-orchestrator CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Orchestrator

CLI tool for delegating tasks to GPT Codex agents via tmux sessions. Designed for Claude Code orchestration with bidirectional communication.

Stack: TypeScript, Bun, tmux, OpenAI Codex CLI

Structure: Shell wrapper -> CLI entry point -> Job management -> tmux sessions

For detailed architecture, see docs/CODEBASE_MAP.md.

Development

# Run directly
bun run src/cli.ts --help

# Or via shell wrapper
./bin/codex-agent --help

# Health check
bun run src/cli.ts health

Key Files

File	Purpose
`src/cli.ts`	CLI commands and argument parsing
`src/jobs.ts`	Job lifecycle and persistence
`src/tmux.ts`	tmux session management
`src/config.ts`	Configuration constants
`src/files.ts`	File loading for context injection
`src/session-parser.ts`	Parse Codex session files for metadata
`plugins/`	Claude Code plugin (marketplace structure)

Plugin Structure

This repo doubles as a Claude Code plugin marketplace:

.claude-plugin/marketplace.json     # marketplace registry
plugins/codex-orchestrator/         # the plugin
  .claude-plugin/plugin.json        # plugin metadata
  skills/codex-orchestrator/        # the orchestration skill
    SKILL.md                        # skill instructions
  scripts/install.sh                # dependency installer

Dependencies

Runtime: Bun, tmux, codex CLI
NPM: glob (file matching)

Notes

Jobs stored in ~/.codex-agent/jobs/
Uses script command for output logging
Completion detected via marker string in output
Bun is the TypeScript runtime - never use npm/yarn/pnpm for running

Claude Orchestration Pattern (Persisted)

Use codex-agent start "<task>" without --wait for background orchestration.
Track job IDs immediately.
Use codex-agent status <id> to check running/completed state.
Use codex-agent capture <id> [n] for incremental tails while running.
Use codex-agent output <id> for final transcript after completion.

Read the full file on GitHub · 68 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 68 lines · 506 tokens per session scan A 2e8842665fde

Subscribe to this mod's changes

codex-orchestrator CLAUDE.md is an instructions file published in the GitHub repository kingbootoshi/codex-orchestrator (360 stars, last pushed 5mo ago), licensed MIT. It adds 506 tokens to every session, about $0.0020 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents

codex-orchestrator CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
codex-orchestrator CLAUDE.mdkingbootoshi/codex-orchestrator	Instructions file	360	5mo ago	MIT	A	506	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

codex-orchestrator: Instructions file for Claude Code