mcp-codex-worker AGENTS.md

Repository instructions for routing coding tasks to separate worker agents. They explain when to delegate searches, file reading, tests, reviews, and implementation work to reduce use of the main agent's context.

In plain words
What is it for?
Use it when working across a repository and deciding how to delegate discovery, analysis, shell commands, testing, and implementation loops.
Why use it?
Large searches, file reads, diffs, and test output can consume the main agent's working context. These rules keep the main agent focused on decisions and final checks.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/sorryorc/mcp-codex-worker/agents-md
Clone the repo
git clone --depth 1 https://github.com/sorryorc/mcp-codex-worker

Made for: Codex, OpenCode.

Per session 389 This file is loaded in full into every session.
When invoked 389 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00389 $0.00389
Opus 5 $0.00195 $0.00195
Sonnet 5 $0.00078 $0.00078
Haiku 4.5 $0.00039 $0.00039

Measured yesterday against content hash b11b3cd8904f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-codex-worker 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 yesterday.

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 · 36 lines

What it actually says

AGENTS.md - Codex Worker Routing Rules

This repository exists to reduce premium Codex context usage. Treat worker routing as part of the task, not as an optional optimization.

Routing Contract

  • Before repository-wide search, bulk file reads, review, diffs, test output, or implementation loops, expose mcp__codex_async_worker tools with tool_search if they are not already callable.
  • Use mcp__codex_async_worker.search for repo discovery instead of main-thread rg when the output could be more than a few lines.
  • Use mcp__codex_async_worker.read_pack or analyze for file-reading and explanation tasks instead of reading whole files into the main thread.
  • Use mcp__codex_async_worker.shell with digest:true for tests, builds, lint, and noisy commands.
  • Use mcp__codex_async_worker.diff_digest and review before ingesting full diffs.
  • Use mcp__codex_async_worker.start for implementation loops. Prefer include_diff:false, scoped paths, and explicit checks.

Main-Thread Budget

Keep the main Codex thread for planning, decisions, small verification, and final review. Do not use main-thread shell or file reads as a substitute for worker tools when the task is large enough to affect context usage.

Audits

  • Run npm run codex:audit -- --since-minutes=60 when checking whether recent work is being routed through the worker.
  • Run npm run stats:gate for the existing metrics gate.
  • Remember that worker metrics can only see worker/tool audit rows. Direct main-thread file reads, shell output, and chat context are outside the metrics file unless explicitly instrumented.
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.

  1. yesterday First seen · 36 lines · 389 tokens per session scan A b11b3cd8904f

Subscribe to this mod's changes

mcp-codex-worker AGENTS.md is an instructions file published in the GitHub repository sorryorc/mcp-codex-worker (2 stars, last pushed 14d ago), licensed MIT. It adds 389 tokens to every session, about $0.0019 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.