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.
npx agentmods add instructions/zetsubo-dev/codex-claude-subagent/agents-mdgit clone --depth 1 https://github.com/zetsubo-dev/codex-claude-subagentWrote 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.
[](https://agentmods.dev/instructions/zetsubo-dev/codex-claude-subagent/agents-md)<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>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 | $0.00743 | $0.00743 |
| Opus 5 | $0.00371 | $0.00371 |
| Sonnet 5 | $0.00149 | $0.00149 |
| Haiku 4.5 | $0.00074 | $0.00074 |
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.
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:
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.
- 2d ago First seen · 90 lines · 743 tokens per session scan A 39ea1d467e3d
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.
Other instructions, from other repositories
superset CLAUDE.md
Claude Code instructions for superset-sh/superset, a project described as: Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.
crystal CLAUDE.md
Instructions for stravu/crystal, covering crystal - multi-session claude code manager, project overview, references, implementation status: ✅ complete and ✅ implemented features.
easy-cheese python.instructions.md
Instructions for paulnsorensen/easy-cheese, covering hard rules, what to flag and what not to flag.
claude-bridge AGENTS.md
Instructions for kadaba/claude-bridge, covering agents.md — using claude-bridge from any ai coding cli, two independent channels, 1. coordination (the conversation), 2. file transfer (the bytes) — same for every tool and workflows.
AmbyKit CLAUDE.md
Instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.
sugar AGENTS.md
AGENTS.md instructions for roboticforce/sugar, covering sugar - agents.md, git branching rules (strict), always create branches from develop, after work is complete and then create pr targeting develop.