A convention for AGENTS.md files, which are project notes written for AI coding agents. They record instructions such as how to build, test, and structure a codebase.

Use it to create or update agent instructions, document build and test commands, describe a monorepo’s layout, and record coding conventions.

It keeps an agent from guessing project-specific commands and coding rules. Files in subdirectories can provide more focused guidance for that part of the project.

agents-md — Skill for Claude Code by Tyler-R-Kendrick/agent-skills

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.

Any agent

npx skills add Tyler-R-Kendrick/agent-skills --skill agents-md

Clone the repo

git clone --depth 1 https://github.com/Tyler-R-Kendrick/agent-skills

Made for: Claude Code.

Or install agent-skills, the plugin that ships this one along with the rest of its 57 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tyler-r-kendrick/agent-skills/agents-md/github.svg)](https://agentmods.dev/skills/tyler-r-kendrick/agent-skills/agents-md)

Your own site

<a href="https://agentmods.dev/skills/tyler-r-kendrick/agent-skills/agents-md"><img src="https://agentmods.dev/badge/skills/tyler-r-kendrick/agent-skills/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/tyler-r-kendrick/agent-skills/agents-md"><img src="https://agentmods.dev/badge/skills/tyler-r-kendrick/agent-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,042 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00080	$0.01042
Opus 5.5	$0.00032	$0.00417
Sonnet 5.5	$0.00016	$0.00208
Haiku 4.5	$0.00008	$0.00104

Measured 2mo ago against content hash 84d7c4d612bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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.

skills/ai/agents-md/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Overview

AGENTS.md is a community convention for providing project-specific guidance to AI coding agents. Think of it as a README for agents — containing the tribal knowledge that senior engineers carry: build steps, test commands, architectural conventions, and coding standards. Adopted by 60,000+ open-source projects and supported by Claude Code, Codex, Gemini CLI, Jules, Factory, and Cursor.

File Placement

Location	Scope
`AGENTS.md` (repo root)	Applies to the entire repository
`src/AGENTS.md`	Applies to the `src/` directory and below
`src/api/AGENTS.md`	Applies to `src/api/` specifically

Agents read the most specific AGENTS.md for the files they're working on, inheriting from parent directories.

Recommended Structure

# AGENTS.md

## Build & Test
- Build: `npm run build`
- Test: `npm test`
- Lint: `npm run lint`
- Single test: `npm test -- --grep "test name"`

## Architecture
- Monorepo with packages in `packages/`
- API server in `packages/api/` (Express + TypeScript)
- Frontend in `packages/web/` (React + Vite)
- Shared types in `packages/shared/`

## Conventions
- Use TypeScript strict mode
- Prefer `async/await` over `.then()` chains
- Use named exports, not default exports
- Error messages must be user-facing strings, not developer jargon

## Testing
- Unit tests live next to source files: `foo.test.ts`
- Integration tests in `tests/integration/`
- Use `vitest` for all tests
- Mock external APIs, never hit real endpoints in tests

## Do NOT
- Do not modify `generated/` files — they are auto-generated
- Do not add dependencies without checking `package.json` first
- Do not use `any` type in TypeScript

Content Guidelines

Aim for under 150 lines — concise beats comprehensive
Use concrete rules, not vague guidance: "Use vitest" not "Use a good test framework"
Include exact commands: npm run build, not "run the build"
Organize by category: Build, Architecture, Conventions, Testing, Do-NOTs
Use bullet points for scanability
Include code examples where conventions aren't obvious

Read the full file on GitHub · 106 lines

Files

What ships with it

11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

2mo ago First seen · 106 lines · 80 tokens per session scan A 84d7c4d612bc

Subscribe to this mod's changes

agents-md is a skill published in the GitHub repository Tyler-R-Kendrick/agent-skills (13 stars, last pushed 5mo ago), licensed MIT. It adds 80 tokens to every session and 1,042 once invoked, about $0.0003 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.

Building agents

agents-md next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agents-mdTyler-R-Kendrick/agent-skills	Skill	13	5mo ago	MIT	A	80	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code