skills/agents-md/SKILL.md
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.
npx skillsauth add adampoit/ai agents-mdInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
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.
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.
Focus only on information agents cannot discover themselves:
Specific commands with full flags. Include only if non-standard or critical.
## 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).
Specify tools agents should use. Research shows agents DO follow specific tool instructions (e.g., uv usage increases 1.6x when mentioned).
## 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.
What agents must NEVER do. This is the highest-value content.
## 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.
Only document patterns that differ from standard conventions in your stack.
## 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.
Based on research findings, do NOT include:
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:
## Overview
This is a React application with a component-based architecture...
Listing every directory is redundant. Agents can explore the filesystem.
Don't write:
## Structure
- `src/components/` - React components
- `src/hooks/` - Custom hooks
- `src/utils/` - Utility functions
Agents already know common patterns (camelCase, functional components, etc.).
Don't write:
## Code Style
- Use camelCase for functions
- Use PascalCase for components
- Prefer const over let
Code examples are clearer than paragraphs. One snippet beats three paragraphs.
Prefer:
## Commands
- Test: `pytest -xvs tests/`
Over:
## Testing
To run tests, use the pytest command. This will discover all tests in the tests directory and execute them with verbose output and fail-fast behavior...
# AGENTS.md
## Commands
- Install: `uv pip install -e ".[dev]"`
- Dev: `uvicorn app.main:app --reload --port 8000`
- Test: `pytest -xvs`
- Lint: `ruff check --fix .`
## Tooling
- Use `uv` for dependencies (not pip)
- Use `ruff` for linting and formatting
## Boundaries
- Never commit `.env` files
- Never modify `alembic/versions/` after merge
- Ask before schema changes
# AGENTS.md
## Overview
This is a FastAPI backend application with SQLAlchemy ORM.
## Tech Stack
- Python 3.12
- FastAPI 0.109
- SQLAlchemy 2.0
- PostgreSQL
## Structure
- `app/` - Application code
- `api/` - Route handlers
- `models/` - SQLAlchemy models
- `tests/` - Test files
## Code Style
- Use type hints on all functions
- Write docstrings for public functions
- Use async where possible
## Commands
- Install: `pip install -e ".[dev]"`
- Dev: `uvicorn app.main:app --reload`
- Test: `pytest`
Why it's bad: Stack and structure are discoverable from files. Style guidelines are standard Python practices. Overview is unnecessary.
For monorepos, place minimal AGENTS.md files at subproject roots:
repo/
├── AGENTS.md (root - only if repo-wide constraints exist)
├── packages/
│ ├── api/
│ │ └── AGENTS.md (API-specific tooling/boundaries)
│ └── web/
│ └── AGENTS.md (web-specific tooling/boundaries)
Keep each file focused on what differs from defaults.
tools
Use tmux instead of background bash for long-running, interactive, inspectable, or user-attachable terminal processes. Use for development servers, watch-mode tests, REPLs, debuggers, interactive CLIs, log tailing, and commands that may run indefinitely or need later input/inspection.
tools
Use Jujutsu (`jj`) for version control operations including status, history, diffs, commits, rebases, splits, squashes, and Git interop. Use when a repository is initialized for jj or the user asks for jj/Jujutsu workflows.
tools
Manage tasks with the `task` (Taskwarrior) CLI. Use when the user asks to review tasks, get task summaries, add work items, or complete tasks.
business
Search Slack messages and read Slack threads. Use when the user asks to search Slack, find messages, look up conversations, read thread replies, or retrieve Slack content. Triggers on requests involving Slack message lookup, conversation history, or thread reading.