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/f/check-ai/agents-mdgit clone --depth 1 https://github.com/f/check-aiWhat 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 | $0.01395 | $0.01395 |
| Opus 5 | $0.00698 | $0.00698 |
| Sonnet 5 | $0.00279 | $0.00279 |
| Haiku 4.5 | $0.00139 | $0.00139 |
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- check-ai CLAUDE.md — 97% identical, 2 lines differ
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 modulescli.test.mjs- CLI argument parsing and integration testsscanner.test.mjs- Scanner logic and deep scan testsscorer.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,detailfor each check
src/scorer.mjs - Converts findings into scores:
- Sums
weightvalues 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
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 · 133 lines · 1,395 tokens per session scan A 94a9bbcd1f65
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.
Other instructions, from other repositories
langgraph AGENTS.md
AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.
agentgateway copilot-instructions.md
Copilot instructions for agentgateway/agentgateway: Do not check for, speculate about, or report compilation errors during code review. Compilation diagnostics from review are frequently incorrect; rely on CI to detect and report compilation failures.
hatch3r CLAUDE.md
Instructions for hatch3r/hatch3r, covering hatch3r — development instructions, architecture, development commands, two-axis pillar framework (2.0.0) and orchestrator self-discipline (bypass protection).
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
ken CLAUDE.md
Instructions for townsendmerino/ken, covering claude.md, what this is, repository ownership (read this first), commands and embedding parity & golden fixtures (now in aikit).
gangsta GEMINI.md
Instructions for kucherenko/gangsta, a project described as: AI agentic skills framework for spec-driven development, built on the organizational model of mafia.