Agent skill

Creating agents.md Files

by pr-pm in pr-pm/prpm

Guides writing an agents.md project-context file: plain markdown with no frontmatter, focused on what an AI coding assistant cannot already know.

MITAuto-check passedAgent Workflows

Install Creating agents.md Files

skills CLI
$ npx skills add pr-pm/prpm --skill creating-agents-md -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install pr-pm/prpm creating-agents-md --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/pr-pm/prpm.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/creating-agents-md .claude/skills/creating-agents-md && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
creating-agents-md
GitHub stars
122
Token cost
~2k tokens
SKILL.md length
391 words
Files
1
Skills in repo
35
Repo updated
First seen
Licence
MIT

At a glance

Guides writing an agents.md project-context file: plain markdown with no frontmatter, focused on what an AI coding assistant cannot already know.

  • Works in 7 steps: Be concise: Focus on project-specific… → Keep updated: Review and update as… → Real examples: Show actual code patterns… → …
  • Writing a new agents.md for a project
  • SKILL.md covers Overview, Quick Reference, Creating agents.md Files and What to Include, plus 10 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

An agents.md file gives AI coding assistants project-specific context, and this skill describes the simplest version of the format: plain markdown only, no YAML frontmatter, no required structure, normally a single file in the project root.

The agent is told to include information the model cannot already know, such as the project overview and purpose, architecture decisions, tech stack, file layout, coding conventions, development workflow, testing approach and domain knowledge, and to skip general programming advice, language syntax and framework basics. Worked examples cover a backend API project and a frontend component library, a table lists common mistakes such as adding frontmatter or padding with generic advice, and a short comparison shows concise writing next to verbose writing.

When your agent uses it

  • Writing a new agents.md for a project
  • Cleaning up an agents.md that has frontmatter or generic advice
  • Deciding what project context an AI assistant actually needs

Example prompts

  • “Create an agents.md for this repo covering the architecture, conventions and testing approach.”
  • “My agents.md has YAML frontmatter and long tutorials. Rewrite it to be concise and project-specific.”
  • “What should go into the agents.md for a payment gateway API?”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Be concise: Focus on project-specific info (AI knows general practices)
  2. Keep updated: Review and update as project evolves
  3. Real examples: Show actual code patterns from your project
  4. Plain markdown: No YAML frontmatter or special syntax
  5. Human-readable: Write for both AI and human developers
  6. Project-specific: Avoid generic advice that AI already knows
  7. Natural structure: Organize however makes sense for your project

What it can do on your machine

Read from SKILL.md and the folder at commit 5f993e6. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Creating agents.md Files loads about 2k tokens when it runs. Until then it costs about 46 tokens; SKILL.md has 391 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~46
When it runs · the whole SKILL.md, loaded when a task matches
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from pr-pm/prpm at commit 5f993e6, republished under its MIT licence (© pr-pm). 391 words, ~2,018 tokens.

Download SKILL.mdSave it as .claude/skills/creating-agents-md/SKILL.md (or your agent's skills folder).
name
creating-agents-md
description
Use when creating agents.md files - provides plain markdown format with NO frontmatter, free-form structure, and project context guidelines for AI coding assistants

Creating agents.md Files

Overview

The agents.md format provides project-specific context for AI coding assistants. It's the simplest format: plain markdown only with NO YAML frontmatter, NO special syntax.

CRITICAL:

  • No frontmatter - Pure markdown only (no YAML)
  • Free-form content - No required structure
  • Single file - Typically agents.md in project root

Quick Reference

AspectRequirement
FormatPlain markdown
FrontmatterNone (forbidden)
StructureFree-form
File locationagents.md in project root

Creating agents.md Files

Plain markdown with no frontmatter:

markdown
# TaskMaster Development Guide

## Project Overview

TaskMaster is a task management application for remote teams, built with real-time collaboration features and offline-first architecture.

## Architecture

### Frontend

- React 18 with TypeScript
- Vite for build tooling
- Zustand for state management
- React Query for server state
- Tailwind CSS for styling

### Backend

- Node.js with Express
- PostgreSQL with Prisma ORM
- WebSocket for real-time features
- Redis for caching and pub/sub
- JWT for authentication

## Coding Conventions

- Use TypeScript strict mode
- Functional components with hooks (no class components)
- Server components by default in Next.js
- Colocate tests with source files (*.test.tsx)
- Use Zod for runtime validation

## File Structure

\`\`\`
src/
  components/     # Reusable UI components
  features/       # Feature-based modules
  hooks/          # Custom React hooks
  lib/            # Utility functions
  pages/          # Route pages
  types/          # TypeScript types
\`\`\`

## Development Workflow

1. Create feature branch from `main`
2. Write tests first (TDD)
3. Implement feature
4. Run `pnpm test` and `pnpm lint`
5. Create PR with description
6. Merge after approval

## Testing

- Use Vitest for unit tests
- Use Playwright for E2E tests
- Aim for 80% coverage on new code
- Mock external dependencies

What to Include

Focus on project-specific information AI doesn't already know:

High Priority:

  • Project overview and purpose
  • Architecture decisions and patterns
  • Tech stack and dependencies
  • File structure and organization
  • Coding conventions
  • Development workflow
  • Testing approach
  • Domain knowledge and business logic

Skip:

  • General programming best practices
  • Language syntax explanations
  • Framework basics
  • Obvious code quality rules

Example: Backend API Project

markdown
# Payment Gateway API

## Overview

RESTful API for payment processing with support for multiple payment providers.

## Tech Stack

- Node.js 20.x
- Express
- PostgreSQL 15
- Redis for rate limiting
- Stripe and PayPal integrations

## API Design

### Endpoints

All endpoints follow REST conventions:

- `GET /api/payments` - List payments
- `GET /api/payments/:id` - Get payment details
- `POST /api/payments` - Create payment
- `PUT /api/payments/:id` - Update payment
- `DELETE /api/payments/:id` - Cancel payment

### Error Handling

Return consistent error format:

\`\`\`json
{
  "error": {
    "code": "PAYMENT_FAILED",
    "message": "Payment could not be processed",
    "details": {...}
  }
}
\`\`\`

## Security

- All endpoints require JWT authentication
- Rate limiting: 100 requests/minute per IP
- Input validation with Zod schemas
- SQL injection prevention via Prisma
- PCI DSS compliance for payment data

## Database

### Conventions

- Use snake_case for table/column names
- Add timestamps (created_at, updated_at) to all tables
- Use UUIDs for primary keys
- Foreign keys follow `{table}_id` pattern

Example: Frontend Component Library

markdown
# Design System Components

A React component library following Atomic Design principles.

## Component Structure

All components follow this structure:

\`\`\`
ComponentName/
  ComponentName.tsx       # Main component
  ComponentName.test.tsx  # Tests
  ComponentName.stories.tsx # Storybook stories
  index.ts                 # Exports
\`\`\`

## Styling

- Use Tailwind CSS utility classes
- Create custom classes in `styles/components/` for complex components
- Follow BEM naming for custom classes
- Responsive by default (mobile-first)

## TypeScript

\`\`\`typescript
// Good: Explicit prop types
interface ButtonProps {
  variant: 'primary' | 'secondary' | 'ghost';
  size?: 'sm' | 'md' | 'lg';
  disabled?: boolean;
  onClick?: () => void;
  children: React.ReactNode;
}

export function Button({ variant, size = 'md', ...props }: ButtonProps) {
  return <button className={cn(variants[variant], sizes[size])} {...props} />;
}
\`\`\`

## Accessibility

- All interactive elements must be keyboard accessible
- Use semantic HTML (button, nav, main, etc.)
- Include ARIA labels for icon-only buttons
- Test with screen readers
- Maintain minimum 4.5:1 contrast ratio

Content Format

Free-form markdown including:

  • Project overview: Purpose and goals
  • Architecture notes: Technical decisions and patterns
  • Conventions: Coding standards and practices
  • Context: Domain knowledge and business logic
  • Workflows: Development processes
  • File structure: Directory organization
  • Dependencies: Key libraries and tools

Common Mistakes

MistakeFix
Adding YAML frontmatterNo frontmatter allowed - plain markdown only
Generic best practicesFocus on project-specific patterns
Verbose explanationsBe concise, AI already knows general concepts
Language tutorialsSkip basics, focus on project conventions
Missing contextInclude domain knowledge and business logic

Writing Style

Concise (Good):

markdown
## Testing

- Vitest for unit tests
- Playwright for E2E
- 80% coverage target
- Mock external dependencies

Verbose (Bad):

markdown
## Testing

When you are writing tests, it's important to understand that we use Vitest
for our unit tests because it's fast and modern. For end-to-end testing,
we have chosen to use Playwright because it provides excellent cross-browser
support and has a great developer experience...

File Placement

Typically in project root:

project-root/
  agents.md           # Main file
  src/
  tests/
  package.json

Can also be in subdirectories for monorepos:

monorepo/
  packages/
    frontend/
      agents.md       # Frontend-specific context
    backend/
      agents.md       # Backend-specific context
Show full SKILL.md (152 more words)Show less

Validation

Documentation: /Users/khaliqgant/Projects/prpm/app/packages/converters/docs/agents-md.md

Schema location: /Users/khaliqgant/Projects/prpm/app/packages/converters/schemas/agents-md.schema.json

Best Practices

  1. Be concise: Focus on project-specific info (AI knows general practices)
  2. Keep updated: Review and update as project evolves
  3. Real examples: Show actual code patterns from your project
  4. Plain markdown: No YAML frontmatter or special syntax
  5. Human-readable: Write for both AI and human developers
  6. Project-specific: Avoid generic advice that AI already knows
  7. Natural structure: Organize however makes sense for your project

Migration from Other Formats

When converting to agents.md:

  1. Strip all frontmatter - Remove YAML headers completely
  2. Focus on content - Keep only markdown content
  3. Combine files - Merge multiple rule files into one cohesive document
  4. Simplify - Remove format-specific features (globs, regex, etc.)
  5. Plain markdown only - Use standard markdown syntax

Official Specification

For the authoritative specification, see: https://github.com/openai/agents.md


Remember: agents.md uses plain markdown with NO frontmatter. Free-form structure. Focus on project-specific context AI doesn't already know.

© pr-pm, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/creating-agents-md of pr-pm/prpm.

Open the folder on GitHubat commit 5f993e6

Compare with similar skills

Creating agents.md Files next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Creating agents.md Files compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Creating agents.md Files this skillpr-pm/prpm122—~2kAutomated safety check: PassMIT
Create SkillPINA-org/PINA797—~1.8kAutomated safety check: PassMIT
Writing Docsc15t/c15t1.9k—~872Automated safety check: PassApache-2.0
EnforceQuentinCody/interlinked-cli178—~19kAutomated safety check: PassMIT
Lint Repository Markdowncodsen/codsen214—~832Automated safety check: PassMIT
Using Agent Skillsaddyosmani/agent-skills103k4 repos~2.4kAutomated safety check: PassMIT

Similar skills

  • Create Skill

    PINA-org/PINA

    Create, modify, and improve PINA skills. An agent skill from PINA-org/PINA.

    797 GitHub stars~1.8k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed
  • Writing Docs

    c15t/c15t

    Author or edit c15t documentation in docs//.mdx — the source for both the c15t.com site and the docs bundled into published packages.

    1.9k GitHub stars~872 tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Enforce

    QuentinCody/interlinked-cli

    Distill imperative markdown guidance (AGENTS.md, CLAUDE.md, .clinerules/, GEMINI.md, SKILL.md with hard imperatives) into deterministic Interlinked harness hook rules with verbatim source provenance.

    178 GitHub stars~19k tokensUpdated 6 days ago
    Agent WorkflowsAuto-check passed
  • Keep the repository's linted Markdown passing npm run lint:markdown.

    214 GitHub stars~832 tokensUpdated 8 days ago
    DevelopmentAuto-check passed
  • Using Agent Skills

    addyosmani/agent-skills

    Meta-skill for choosing which workflow skill fits the task at hand, plus always-on habits: surface assumptions, stop on confusion, push back, keep it simple and stay in scope.

    103k GitHub starsUsed in 4 repos~2.4k tokens
    Agent WorkflowsAuto-check passed
  • Claude Reflect

    BayramAnnakov/claude-reflect

    Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md.

    1.7k GitHub starsUsed in 2 repos~627 tokens
    Agent WorkflowsAuto-check passed

More from pr-pm/prpm

All 35 skills in this repo
  • Reference for writing Claude Code agent files: location, frontmatter fields, validation limits, tool and model choices, and the required content format.

    122 GitHub starsUsed in 3 repos~4k tokens
    Auto-check passed
  • Covers how to build, configure and publish Claude Code hooks: event types, exit codes, JSON I/O, and PRPM packaging.

    122 GitHub starsUsed in 2 repos~3.9k tokens
    Auto-check: notes
  • Shows how to write .claude/rules/ files correctly: paths frontmatter instead of globs, quoted glob patterns, global rules and conversion of Cursor rules.

    122 GitHub starsUsed in 2 repos~551 tokens
    Auto-check passed
  • Reference for writing portable Agent Skills packages, covering SKILL.md frontmatter limits, name rules, directory layout and where Codex CLI, GitHub Copilot and Amp look for skills.

    122 GitHub starsUsed in 1 repo~1.5k tokens
    Auto-check passed
  • A skill your agent uses when building custom Kiro AI agents or when user asks for agent configurations - provides JSON structure, tool configuration, prompt patterns, and security best practices for…

    122 GitHub starsUsed in 1 repo~1.9k tokens
    Auto-check passed
  • A skill your agent uses when creating OpenCode agents - provides markdown format with YAML frontmatter, mode/tools/permission configuration, and best practices for specialized AI assistants

    122 GitHub starsUsed in 1 repo~2k tokens
    Auto-check passed

Categories

Questions about Creating agents.md Files

What does Creating agents.md Files do?

Guides writing an agents.md project-context file: plain markdown with no frontmatter, focused on what an AI coding assistant cannot already know. md file gives AI coding assistants project-specific context, and this skill describes the simplest version of the format: plain markdown only, no YAML frontmatter, no required structure, normally a single file in the project root.

When should I use Creating agents.md Files?

Creating agents.md Files fits situations like: writing a new agents.md for a project; cleaning up an agents.md that has frontmatter or generic advice; deciding what project context an AI assistant actually needs.

How do I install Creating agents.md Files in Claude Code?

Run `npx skills add pr-pm/prpm --skill creating-agents-md -a claude-code`. Or copy the skill folder (.claude/skills/creating-agents-md in pr-pm/prpm) into .claude/skills/creating-agents-md in your project. Claude Code loads it when a task matches its description.

How do I install Creating agents.md Files in Codex?

Run `npx skills add pr-pm/prpm --skill creating-agents-md -a codex`. Or copy the skill folder (.claude/skills/creating-agents-md in pr-pm/prpm) into .agents/skills/creating-agents-md in your project. Codex loads it when a task matches its description.

Can I use Creating agents.md Files in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add pr-pm/prpm --skill creating-agents-md -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/creating-agents-md, .gemini/skills/creating-agents-md, .github/skills/creating-agents-md and .opencode/skills/creating-agents-md in your project.

What does Creating agents.md Files need to run?

SKILL.md names no scripts, command-line tools or credentials: Creating agents.md Files is instructions for the agent only.

Does Creating agents.md Files access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Creating agents.md Files safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Creating agents.md Files use?

Creating agents.md Files is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Creating agents.md Files use?

About 2k tokens (SKILL.md is roughly 8.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Creating agents.md Files?

Skills that share tags, products or a category with Creating agents.md Files: Create Skill (PINA-org/PINA, 797 stars), Writing Docs (c15t/c15t, 1.9k stars), Enforce (QuentinCody/interlinked-cli, 178 stars) and Lint Repository Markdown (codsen/codsen, 214 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Creating agents.md Files?

pr-pm (a GitHub organization) maintains it in pr-pm/prpm, which has 122 GitHub stars. The repository holds 35 skills in this directory. The repository was last updated on October 6, 2026.

Source: pr-pm/prpm on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.