check-ai AGENTS.md

Repository-specific instructions for check-ai, a Node.js command-line tool that checks whether a code repository is ready for AI-assisted development. They describe the project, commands, and tests.

In plain words
What is it for?
Use them when developing, testing, linting, formatting, or running check-ai locally.
Why use it?
They give a coding agent the context needed to work in the repository and verify changes with its built-in test runner.

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/f/check-ai/agents-md
Clone the repo
git clone --depth 1 https://github.com/f/check-ai

Made for: Codex, OpenCode.

Per session 1,395 This file is loaded in full into every session.
When invoked 1,395 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 $0.01395 $0.01395
Opus 5 $0.00698 $0.00698
Sonnet 5 $0.00279 $0.00279
Haiku 4.5 $0.00139 $0.00139

Measured 2d ago against content hash 94a9bbcd1f65, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

check-ai 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

check-ai is a zero-dependency CLI tool that audits repositories for AI-readiness. It runs 66 checks across 8 sections (Repo Hygiene, Grounding Docs, Testing, Agent Configs, AI Context, Prompts & Skills, MCP, AI Deps) and produces a 0-10 score with letter grades.

The tool is designed to be run via npx check-ai and works entirely offline using Node.js built-ins.

Commands

Development

# Run tests (Node.js native test runner)
npm test

# Run linting
npm run lint
npm run lint:fix

# Format code
npm run format
npm run format:check

# Run the CLI locally
node bin/cli.mjs
node bin/cli.mjs /path/to/repo
node bin/cli.mjs --json
node bin/cli.mjs --verbose
node bin/cli.mjs badge

Testing

The test suite uses Node.js native test runner (node:test). Tests are in tests/*.test.mjs:

  • audits.test.mjs - Tests for individual audit modules
  • cli.test.mjs - CLI argument parsing and integration tests
  • scanner.test.mjs - Scanner logic and deep scan tests
  • scorer.test.mjs - Scoring and grading logic tests

Test fixtures are dynamically created in tests/.fixtures/ during test runs.

Architecture

Core Components

bin/cli.mjs - Entry point. Handles argument parsing, determines interactive vs static output mode, coordinates scan → score → report flow. Exits with code 1 if score < 3 (for CI integration).

src/scanner.mjs - The scanning engine:

  • Dynamically loads all audit modules from src/audits/*.mjs
  • Performs a single-pass deep tree walk (up to 6 levels) to collect files matching deep-scan patterns
  • Evaluates each check: file/dir existence, deep-scan matches, or custom handlers
  • Returns raw findings array with found, matches, detail for each check

src/scorer.mjs - Converts findings into scores:

  • Sums weight values from passed checks
  • Normalizes to 0-10 scale
  • Assigns letter grade (A+, A, B, C, D, F) based on score thresholds
  • Groups findings by section in a fixed order

Read the full file on GitHub · 133 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 · 133 lines · 1,395 tokens per session scan A 94a9bbcd1f65

Subscribe to this mod's changes

check-ai AGENTS.md is an instructions file published in the GitHub repository f/check-ai (67 stars, last pushed 5mo ago), licensed MIT. It adds 1,395 tokens to every session, about $0.0070 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 2026-08-30.