What is claude-codex-orchestrator-mcp AGENTS.md?

An `AGENTS.md` instruction set describing an orchestrator, worker agents, and controlled automation lanes. An orchestrator breaks a request into smaller tasks and coordinates their execution.

Coordinating worker tasks, invoking Codex coding workers, running allowlisted automation plans, and deciding whether work should continue, retry, stop, or ask for input.

It gives agents defined responsibilities and rules for handling coding, automation, approvals, and blockers.

How sixflower666/claude-codex-orchestrator-mcp configures Codex and Op

Reuse

Borrowing it

Nothing to install: this file belongs to sixflower666/claude-codex-orchestrator-mcp. 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/sixflower666/claude-codex-orchestrator-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/sixflower666/claude-codex-orchestrator-mcp

Made for: Codex, OpenCode.

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/sixflower666/claude-codex-orchestrator-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/sixflower666/claude-codex-orchestrator-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/sixflower666/claude-codex-orchestrator-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sixflower666/claude-codex-orchestrator-mcp/agents-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/sixflower666/claude-codex-orchestrator-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sixflower666/claude-codex-orchestrator-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 417 This file is loaded in full into every session.

When invoked 417 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	$0.00417	$0.00417
Opus 5	$0.00209	$0.00209
Sonnet 5	$0.00083	$0.00083
Haiku 4.5	$0.00042	$0.00042

Measured 9d ago against content hash 42fb79047783, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

claude-codex-orchestrator-mcp AGENTS.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 9d 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.

AGENTS.md · 43 lines

What it actually says

Agent Definitions

Orchestrator

Implementation: Claude Code / Claude CLI.
Responsibilities:
- Analyze and decompose user requests into atomic worker tasks.
- Select the execution lane and invoke one worker at a time.
- Read compact status artifacts and decide continue, retry, stop, or ask the user.
- Surface approval, user-input, and blocker states instead of bypassing them.
Stable entrypoint: tools/invoke-orchestrated-task.ps1.
Workspace: D:\workspace\workspace.

Codex Worker Lanes

app

Implementation: codex app-server --stdio through tools/invoke-codex-app-worker.ps1.
Runtime identity: Codex Desktop/app-server protocol, currently verified as Codex Desktop/0.144.6 on Windows.
Use for coding, file operations, and tasks that may produce app-server tool, approval, or user-input events.
No visible Codex Desktop GUI needs to be open.

automation

Implementation: tools/run-controlled-automation.ps1.
Input: allowlisted JSON plan.
Default: dry-run.
Real browser/Windows actions require an explicit -AllowRealAutomation call and must pass plan allowlists.
Never convert arbitrary natural-language input directly into unrestricted process launches.

code

Implementation: codex exec through tools/invoke-codex-worker.ps1.
Use for legacy isolated code-only work.
Fixed worker defaults remain gpt-5.5, workspace-write, --ephemeral, --json, shell_tool, with unified_exec disabled.

Safety and Configuration

Do not edit C:\Users\chenjinhan\.codex\config.toml.
Do not default to dangerously-bypass-approvals-and-sandbox.
Keep worker artifacts under .orchestrator\ and inspect compact status before raw event logs.
Use PowerShell on Windows and preserve existing user changes.

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.

9d ago First seen · 43 lines · 417 tokens per session scan A 42fb79047783

Subscribe to this mod's changes

claude-codex-orchestrator-mcp AGENTS.md is an instructions file published in the GitHub repository sixflower666/claude-codex-orchestrator-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 417 tokens to every session, about $0.0021 per session on Opus 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 2026-08-31.

Building agents Planning

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

claude-codex-orchestrator-mcp: Instructions file for Codex