claude-code-config: Instructions file for Codex

AGENTS.md

claude-code-config AGENTS.md is an instructions file for Codex, OpenCode from RohiRIK/claude-code-config. It costs 1,806 tokens per session, scanned A, original, MIT.

A guide for contributing to a TypeScript command-line project that uses Node.js, pnpm, Biome, and Bats tests. It records the commands, build process, and repository conventions.

In plain words
What is it for?
Use it to install dependencies, build the CLI, run type checks, format and lint code, or run all or selected tests.
Why use it?
It puts the project’s setup and checks in one place, reducing errors such as using the wrong package manager or skipping required validation.

Instructions file for CodexOpenCode

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

This is RohiRIK/claude-code-config's own configuration. It tells Codex and OpenCode how to work on claude-code-config 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 claude-code-config configures →

Reuse

Borrowing it

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

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 claude-code-config AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rohirik/claude-code-config/agents-md/github.svg)](https://agentmods.dev/instructions/rohirik/claude-code-config/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/rohirik/claude-code-config/agents-md"><img src="https://agentmods.dev/badge/instructions/rohirik/claude-code-config/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.

agentmods 80×15 button for claude-code-config AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/rohirik/claude-code-config/agents-md"><img src="https://agentmods.dev/badge/instructions/rohirik/claude-code-config/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,806 This file is loaded in full into every session.
When invoked 1,806 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 $0.01806 $0.01806
Opus 5.5 $0.00722 $0.00722
Sonnet 5.5 $0.00361 $0.00361
Haiku 4.5 $0.00181 $0.00181

Measured 2mo ago against content hash 717eedd6b1b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-code-config 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 2mo 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 · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS GUIDE (Mixedbread mgrep)

Orientation for coding agents working in this repo. Keep this handy; follow commands and conventions before editing.

Project Snapshot

  • Runtime: Node.js 18+ (CI uses 20/24)
  • Language: TypeScript 5.x, ESM ("type": "module", module: "NodeNext")
  • Package manager: pnpm (lockfile present)
  • Lint/format: Biome (biome.json), import organize on save
  • Tests: bats (Bash Automated Testing System)
  • Dist: tsc outputs to dist/; CLI entry dist/index.js

How to Build/Test Fast

  • Install deps: pnpm install
  • Build: pnpm build
  • Dev run CLI: pnpm dev (compiles then runs dist/index.js)
  • Type check only: pnpm typecheck
  • Lint/format fix: pnpm format
  • Lint/format check (CI): pnpm format:check
  • Lint only: pnpm lint
  • Run all tests (default short): pnpm test
  • Run all including long-running: pnpm test --filter-tags long-running
  • Run a single bats test by name: bats test/test.bats --filter "pattern"
  • Run a single bats test by tag: bats test/test.bats --filter-tags tagname
  • CI pipeline order: format:check → test (long-running) → typecheck → build

Repo Conventions

  • ESM everywhere: use .js extension in imports, even for TS files (import { foo } from "./lib/foo.js").
  • Paths: prefer node:path utilities; avoid string concat for paths.
  • Logging: src/lib/logger.ts wires console to Winston; avoid new loggers unless necessary.
  • Git helpers live in src/lib/git.ts; prefer them over custom git shells.
  • Commands live under src/commands/; installers under src/install/; shared utils under src/lib/.
  • CLI wired in src/index.ts via Commander; add commands there when introducing new functionality.

TypeScript Style

  • strict mode on; noUnused*, noImplicitReturns, noFallthrough enforced.
  • Prefer explicit return types on exported functions.
  • Avoid any; use unknown or generics. Narrow early.
  • Use interfaces for public contracts; types acceptable for internal utility shapes.
  • Keep enums minimal; favor literal unions when possible.
  • Always await promises; handle rejections. Return typed results, not Promise<void> unless appropriate.
  • Use const over let where possible; avoid var entirely.
  • Keep functions small; extract helpers in src/lib when shared.

Read the full file on GitHub · 151 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. 2mo ago First seen · 151 lines · 1,806 tokens per session scan A 717eedd6b1b0

Subscribe to this mod's changes

claude-code-config AGENTS.md is an instructions file published in the GitHub repository RohiRIK/claude-code-config (10 stars, last pushed 3mo ago), licensed MIT. It adds 1,806 tokens to every session, about $0.0072 per session on Opus 5.5. 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

claude-code-config AGENTS.md compared with instructions from other repositories

claude-code-config AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
claude-code-config AGENTS.mdRohiRIK/claude-code-configInstructions file103mo agoMITA1,806Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k2d agoMITA4,313Codex, OpenCode