setup-agents-md

A repository-specific guide for AI coding agents. AGENTS.md is a plain-text file that records how to work in a code repository, including its commands, structure, conventions, and safety rules.

In plain words
What is it for?
Use it to create or improve an AGENTS.md file by examining the actual repository and documenting its real workflows and boundaries.
Why use it?
It prevents agents from guessing how to build, test, or change the project and from relying on generic instructions.

Skill for Claude CodeCodex

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 skills/openhands/extensions/setup-agents-md
Any agent
npx skills add OpenHands/extensions --skill setup-agents-md
Clone the repo
git clone --depth 1 https://github.com/OpenHands/extensions

Made for: Claude Code, Codex.

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,370 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00076 $0.01370
Opus 5 $0.00038 $0.00685
Sonnet 5 $0.00015 $0.00274
Haiku 4.5 $0.00008 $0.00137

Measured 2d ago against content hash 33abece9c9e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup-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.

plugins/onboarding/skills/setup-agents-md/SKILL.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.

Generate AGENTS.md

Create a repo-specific AGENTS.md that gives AI agents the context they need to work effectively. Every section should reference real commands, real paths, and real conventions from the repository — not generic advice.

Why this matters

An AGENTS.md is the single highest-impact addition for agent readiness. It directly addresses features across multiple pillars:

  • Agent Instructions: agent instruction file, README with build/run/test, contributing guide, environment variable documentation
  • Feedback Loops: test run documentation — agents need exact commands
  • Policy & Governance: guardrails the agent must follow

Without it, agents guess at build commands, miss project conventions, run the wrong test suite, and don't know what's dangerous. The best AGENTS.md files share the same core pattern: real commands, clear structure, explicit boundaries.

How to run

Step 0: Check for an existing AGENTS.md

Look for an existing AGENTS.md (or .agents/AGENTS.md) in the repo root. If one exists, do not rewrite it from scratch. Instead, read the repo (Step 1), compare what you find against what's already documented, and suggest specific additions or changes. Present the suggestions to the user and let them decide what to incorporate.

If no file exists, proceed to create one.

Step 1: Read the repo

Before writing anything, gather the actual information. Check these sources:

Commands (most important — agents need to know how to build, test, lint):

  • Makefile / justfile / Taskfile.yml — look for build/test/lint/format targets
  • package.json scripts — npm/yarn/pnpm run targets
  • pyproject.toml [tool.prek] / [tool.pytest] — Python tooling config
  • .github/workflows/*.yml — CI steps reveal the real commands
  • Cargo.toml — Rust build/test commands
  • build.gradle / pom.xml — Java/Kotlin build commands
  • Rakefile — Ruby task definitions
  • docker-compose.yml — service orchestration commands

Project structure:

  • Top-level directory listing — what's in each major directory
  • Monorepo indicators: workspace configs, multiple package.json/Cargo.toml/pyproject.toml
  • Source vs test layout (where does code live, where do tests live)

Read the full file on GitHub · 151 lines

Files

What ships with it

1 file 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.

  1. 2d ago First seen · 151 lines · 76 tokens per session scan A 33abece9c9e2

Subscribe to this mod's changes

setup-agents-md is a skill published in the GitHub repository OpenHands/extensions (137 stars, last pushed 4d ago), licensed MIT. It adds 76 tokens to every session and 1,370 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens