agents-md
Create and maintain AGENTS.md files that provide AI coding agents with project context, commands, code style, and boundaries.
Skill by adampoit
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/adampoit-agents-md
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/agents-md
What's inside
- Skill name
agents-md- Description
- Create and maintain AGENTS.md files that provide AI coding agents with project context, commands, code style, and boundaries. Use when updating an existing AGENTS.md, creating a new AGENTS.md for a repository, or improving agent instructions for a codebase.
- License
- MIT
- Instructions
- 233 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- best-practices.md · references/
- examples.md · references/
SKILL.md (first lines)
# Agents Md AGENTS.md is a README for AI agents: a dedicated place to provide context and instructions to help AI coding agents work effectively on a project. ## Important: Keep It Minimal **Key principle**: Include only what agents cannot infer from the codebase itself. Redundant documentation is harmful—agents already read files, search code, and understand common patterns. ## When to Create/Update - **Create**: When the project has non-obvious tooling, specific commands, or critical boundaries agents must know - **Update**: When commands change, new critical constraints are added, or tooling requirements evolve - **Omit**: If your repository has standard structure and common tooling (React, Python, etc.) that agents already understand ## What to Include Focus only on information agents cannot discover themselves: ### 1. Essential Commands (Required) Specific commands with full flags. Include only if non-standard or critical. ```markdown ## Commands - Install: `pnpm install` - Dev: `pnpm dev --port 3000` - Test: `pnpm test --coverage` - Build: `pnpm build` ``` **Skip this section if using standard commands** (e.g., `npm install`, `npm test`). ### 2. Tooling Requirements (If Non-Standard) Specify tools agents should use. Research shows agents DO follow specific tool instructions (e.g., `uv` usage increases 1.6x when mentioned). ```markdown ## Tooling - Use `uv` for Python dependency management - Use `ruff` for linting (not flake8) - Use `just` for task running (not Make) ``` **Only include if different from defaults** agents would assume. ### 3. Boundaries (Critical) What agents must NEVER do. This is the highest-value content. ```markdown ## Boundaries - Never commit secrets, API keys, or `.env` files - Never modify `vendor/`, `node_modules/`, or lock files - Never remove failing tests—fix or ask first - Ask before changing database schemas ``` **Always include this section.** It prevents costly mistakes. ### 4. Project-Specific Patterns (If Unusual) Only document patterns that differ from standard conventions in your stack. ```markdown ## Patterns - Use functional React components, not classes - Place tests in `__tests__/` folders (not `.test.ts` files) - Import order: React, third-party, `@/`, relative ``` **Skip if following standard conventions** for your framework/language. ## What to Avoid Based on research findings, do NOT include: ### ❌ Codebase Overviews Research shows "context files do not provide effective overviews"—agents don't discover files faster with overviews present. They already search and explore code effectively. **Don't write:** ```markdown ## Overview This is a React application with a component-based architecture... ``` ### ❌ Comprehensive Structure Documentation Listing every directory is redundant. Agents can explore the filesystem. **Don't write:** ```markdown ## Structure - `src/components/` - React components - `src/hooks/` - Custom hooks - `src/utils/` - Utility functions ``` ### ❌ Obvious Style Guidelines Agents already know common patterns (camelCase, functional components, etc.). **Don't write:** ```markdown ## Code Style - Use camelCase for functions - Use PascalCase for components - Prefer const over let ```
From adampoit/ai, MIT.
More from adampoit/ai
- 0.557score
taskwarrior
adampoit
Manage tasks with the `task` (Taskwarrior) CLI, including attaching notes with `task-note`.
SkillBFreshness: B★ 2Claude Code +9 - 0.507score
jj
adampoit
Use Jujutsu (`jj`) for version control operations including status, history, diffs, commits, rebases, splits, squashes, and Git interop.
SkillCFreshness: C★ 2Claude Code +9 - 0.504score
tmux-interactive-processes
adampoit
Use tmux instead of background bash for long-running, interactive, inspectable, or user-attachable terminal processes.
SkillCFreshness: C★ 2Claude Code +9 - 0.448score
chatgpt-share-markdown
adampoit
Convert public ChatGPT share links into clean Markdown transcripts for agent context.
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
jira
adampoit
Search Jira issues with JQL or free text, and read Jira issue details with comments using the external jira-cli (`jira`) command.
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
ddgr
adampoit
Search the web with DuckDuckGo using the `ddgr` CLI.
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
gh
adampoit
Use the GitHub CLI (`gh`) for repository operations including PR and issue inspection, GitHub search, checks, and API calls.
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
notmuch
adampoit
Search and read local email with the `notmuch` CLI.
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
khal
adampoit
Read calendar events with the `khal` CLI.
SkillDFreshness: D★ 2Claude Code +9 - 0.441score
skill-creator
adampoit
Guide for creating effective agent skills.
SkillDFreshness: D★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Mar 15, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/adampoit/ai
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from adampoit
- 0.557score
taskwarrior
adampoit
Manage tasks with the `task` (Taskwarrior) CLI, including attaching notes with `task-note`.
SkillBFreshness: B★ 2Claude Code +9 - 0.507score
jj
adampoit
Use Jujutsu (`jj`) for version control operations including status, history, diffs, commits, rebases, splits, squashes, and Git interop.
SkillCFreshness: C★ 2Claude Code +9 - 0.504score
tmux-interactive-processes
adampoit
Use tmux instead of background bash for long-running, interactive, inspectable, or user-attachable terminal processes.
SkillCFreshness: C★ 2Claude Code +9 - 0.448score
chatgpt-share-markdown
adampoit
Convert public ChatGPT share links into clean Markdown transcripts for agent context.
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
khal
adampoit
Read calendar events with the `khal` CLI.
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
ddgr
adampoit
Search the web with DuckDuckGo using the `ddgr` CLI.
SkillDFreshness: D★ 2Claude Code +9
Cite this page
agents-md skill. Agent Mart. https://agentmart.dev/skills/adampoit-agents-md (last updated 2026-10-24)