codex-claude-subagent AGENTS.md

codex-claude-subagent AGENTS.md is an instructions file for Codex, OpenCode from zetsubo-dev/codex-claude-subagent. It costs 743 tokens per session, scanned A, original, MIT.

A repository instruction file for a Codex–Claude Subagent plugin. It records the plugin's folder structure, names, settings, development commands, and release requirements.

In plain words
What is it for?
Use it when developing, testing, packaging, or releasing the Codex–Claude Subagent plugin.
Why use it?
It gives contributors one shared reference for keeping the plugin package and its supporting files consistent.

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/zetsubo-dev/codex-claude-subagent/agents-md
Clone the repo
git clone --depth 1 https://github.com/zetsubo-dev/codex-claude-subagent

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.

agentmods badge for codex-claude-subagent AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zetsubo-dev/codex-claude-subagent/agents-md.svg)](https://agentmods.dev/instructions/zetsubo-dev/codex-claude-subagent/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/zetsubo-dev/codex-claude-subagent/agents-md"><img src="https://agentmods.dev/badge/instructions/zetsubo-dev/codex-claude-subagent/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 743 This file is loaded in full into every session.
When invoked 743 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 $0.00743 $0.00743
Opus 5 $0.00371 $0.00371
Sonnet 5 $0.00149 $0.00149
Haiku 4.5 $0.00074 $0.00074

Measured 2d ago against content hash 39ea1d467e3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-claude-subagent 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 2d 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 · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex–Claude Subagent

Repository shape

This repository is a local Codex marketplace containing one independently packaged plugin:

.agents/plugins/marketplace.json       local marketplace entry
package.json                           root development command wrapper
plugins/codex-claude-subagent/         plugin source and standalone package

The plugin directory is the package boundary. Keep its package.json and bundled server.bundle.mjs valid for installation without relying on the repository root.

The root package.json is intentionally private and contains development-only tooling. The repository is a pnpm workspace; the root lockfile covers the root tooling and the plugin's build dependency.

Naming contract

  • Display name: Codex–Claude Subagent
  • Plugin identifier: codex-claude-subagent
  • MCP server key: codex_claude_subagent
  • Plugin-specific environment variables: CODEX_CLAUDE_SUBAGENT_*
  • Default state directory: ~/.codex/codex-claude-subagent

Keep generated MCP tool names, package metadata, documentation, tests, and marketplace metadata aligned with this contract.

Development commands

Run commands from the repository root:

pnpm run deps:install
pnpm run verify

Useful focused commands are pnpm run build, pnpm run format:check, pnpm run lint, pnpm run check, pnpm test, pnpm run smoke, and pnpm run smoke:package. The live smoke test is opt-in:

pnpm run smoke:live -- /absolute/project/path

server.bundle.mjs is a committed generated artifact. Edit source files under the plugin, then run pnpm run build; do not hand-edit the bundle.

Release and distribution

The end-user distribution is a prebuilt ZIP containing the repository marketplace and Install.command. Install.command is a tracked installer source file; pnpm run build does not generate it. The release packaging command verifies the bundle and tests first, then creates the ZIP under the ignored dist/ directory:

Read the full file on GitHub · 90 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.

  1. 2d ago First seen · 90 lines · 743 tokens per session scan A 39ea1d467e3d

Subscribe to this mod's changes

codex-claude-subagent AGENTS.md is an instructions file published in the GitHub repository zetsubo-dev/codex-claude-subagent (0 stars, last pushed 1mo ago), licensed MIT. It adds 743 tokens to every session, about $0.0037 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.