Borrowing it
Nothing to install: this file belongs to ItsHege/agents-md-doctor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ItsHege/agents-md-doctor/main/AGENTS.mdgit clone --depth 1 https://github.com/ItsHege/agents-md-doctorWrote 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/itshege/agents-md-doctor/agents-md)<a href="https://agentmods.dev/instructions/itshege/agents-md-doctor/agents-md"><img src="https://agentmods.dev/badge/instructions/itshege/agents-md-doctor/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.
<a href="https://agentmods.dev/instructions/itshege/agents-md-doctor/agents-md"><img src="https://agentmods.dev/badge/instructions/itshege/agents-md-doctor/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01124 | $0.01124 |
| Opus 5 | $0.00562 | $0.00562 |
| Sonnet 5 | $0.00225 | $0.00225 |
| Haiku 4.5 | $0.00112 | $0.00112 |
Grade A, and why
agents-md-doctor 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 8d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md Doctor Public Agent Instructions
Scope Of This File
This file is public-safe project guidance for contributors and coding agents working inside the AGENTS.md Doctor repository.
Workspace-only coordination, role briefs, owner workflow, durable memory, and planning notes belong outside this publishable project. Do not copy local workspace instructions into this repository unless they have been deliberately cleaned into public documentation.
Project Goal
Build a small, practical open-source CLI and CI tool that validates repository-level AGENTS.md files for AI coding agents.
The project should stay focused on three user outcomes:
lint: instruction files are readable, scoped, and not bloated.verify: commands and paths in instructions match the real repo.explain: developers can see which instructions apply to a target file.
Current Baseline
- Package name:
agents-doctor. - Current public release line:
0.9.x;mainmay contain unreleased0.10.0work. - Runtime: Node.js
>=20, TypeScript, ESM. - Stable top-level report schema:
schemaVersion: "1.0.0". - Supported commands:
init,lint,verify, andexplain. - Supported output surfaces: human text, JSON, GitHub workflow annotations,
SARIF for
lint/verify, and JSON forexplain. - Supported tool profiles:
auto,codex,claude-code,cursor,gemini-cli,github-copilot,windsurf, andcline.
Working Rules
- Keep the first implementation narrow and testable.
- Prefer deterministic parsing and repository inspection before any LLM-based analysis.
- Do not add network calls to the core validator.
- Do not auto-rewrite user instructions in the MVP.
- Treat CI output as a first-class use case.
- Every rule should have a stable rule id, severity, message, and location when possible.
Architecture Boundaries
- Keep Markdown extraction, safe file reading, rule evaluation, report building, and renderers as separate layers.
- Markdown extraction belongs in
src/core/and should return typed facts with source locations; rules should consume those facts instead of walking raw AST nodes directly. - Public config and report details should stay schema-checked with Zod where they cross module or user-facing boundaries.
- Tool evidence is local repository inventory only. Do not claim that external tools loaded the same context at runtime.
- Profiles are deterministic inspection presets. They must not invoke external CLIs, model APIs, global memory, user home config, or network services.
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.
- 8d ago First seen · 116 lines · 1,124 tokens per session scan A a11e8c26dad9
agents-md-doctor AGENTS.md is an instructions file published in the GitHub repository ItsHege/agents-md-doctor (2 stars, last pushed 6d ago), licensed MIT. It adds 1,124 tokens to every session, about $0.0056 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
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.
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.
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).
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).
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.
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.