rook-claude: Instructions file for Codex

AGENTS.md

rook-claude AGENTS.md is an instructions file for Codex, OpenCode from jhoblitt/rook-claude. It costs 802 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for agents and contributors working on the rook-claude Claude Code plugin marketplace.

In plain words
What is it for?
Following contribution rules, deciding when a skill needs a Mermaid flowchart, and keeping skill diagrams synchronized with their procedures.
Why use it?
They explain which documentation and checks must stay aligned when changing skills, reducing the risk of prose or workflow rules becoming outdated.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; mentions AGENTS.md.

This is jhoblitt/rook-claude's own configuration. It tells Codex and OpenCode how to work on rook-claude itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything rook-claude configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jhoblitt/rook-claude. 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/jhoblitt/rook-claude/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/jhoblitt/rook-claude

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 rook-claude AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jhoblitt/rook-claude/agents-md.svg)](https://agentmods.dev/instructions/jhoblitt/rook-claude/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/jhoblitt/rook-claude/agents-md"><img src="https://agentmods.dev/badge/instructions/jhoblitt/rook-claude/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 802 This file is loaded in full into every session.
When invoked 802 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00802 $0.00802
Opus 5 $0.00401 $0.00401
Sonnet 5 $0.00160 $0.00160
Haiku 4.5 $0.00080 $0.00080

Measured 7d ago against content hash de0c7b8cdc0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

rook-claude 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 7d 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 · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Notes for agents and humans changing this repository. This repo is a Claude Code plugin marketplace; the shipped product is plugins/rook-maintainer, whose "code" is mostly instruction prose that steers a model. A prose defect here is a real defect.

The contribution mechanics — Conventional Commits, never bumping the plugin version by hand, and the checks CI runs — live in README.md under "Development". This file does not restate them.

Skill workflows are documented in the README

Every skill that executes a procedure has a mermaid flowchart in README.md under "Skill workflows", kept in sync with its SKILL.md.

A skill is a procedure if its SKILL.md has any of: numbered phases or steps, a modes table, ordered gates, or agent fan-out. The test is mechanical so the question is checkable rather than argued each time.

Changing a skill's phases, modes, gates, or fan-out is not complete until its diagram matches. This clause is the point of the rule. Without it the rule catches a missing diagram but not a stale one, and stale is the failure that actually happens: when PR takeover moved out of rook-code-review into its own skill, the skills table was updated and the diagram was left asserting takeover was still a mode.

Adding a skill adds its diagram in the same PR. Removing one removes it.

Reference skills are exempt

A skill with no entry point, no ordered steps, and no output contract — one other skills consult rather than run — gets no workflow diagram. Diagramming a rules document invents a flow that does not exist and makes the README worse.

rook-conventions is the exempt case: its own text says references are read by trigger and skipped otherwise, and that a report "lands in ITS OWN output contract" — the caller's, not its. It has a precedence ladder where a procedure would have an entry point.

An exemption claimed for a skill that in fact has phases or modes is a review blocker.

What an exempt skill owes instead

Read the full file on GitHub · 79 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. 7d ago First seen · 79 lines · 802 tokens per session scan A de0c7b8cdc0e

Subscribe to this mod's changes

rook-claude AGENTS.md is an instructions file published in the GitHub repository jhoblitt/rook-claude (4 stars, last pushed 2d ago), licensed Apache-2.0. It adds 802 tokens to every session, about $0.0040 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.

Related

Other instructions, from other repositories

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 · 5,182 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

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

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens