agentleFS
Sign inStart free
yeaight7yeaight7/agent-powerups/AGENTS.md

agent-powerups

AGENTS.md6 starsChanged 4 months agoApache-2.0View on GitHub

Agent Powerups is a Node.js/TypeScript CLI plus a catalog of agent assets. Core CLI code lives in src/cli/, with command handlers in src/cli/commands/ and shared helpers in src/cli/utils/. Tests live in test/ as *.test.ts. Shipped assets are organized by type: skills/, commands/, hooks/, mcp/, agents-md/, workflows/, and examples/. Repository docs live in docs/. Keep catalog.json in sync whenever a shipped asset is added, renamed, removed, or materially changed. Use TypeScript ES modules targeting Node 20+. The project uses strict TypeScript,…

The file

We split this AGENTS.md into the rules it gives an agent

4 rules. About 1 is common, 0 are distinctive, and 3 are very specific to this project.

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Use TypeScript ES modules targeting Node 20+.

    line 23
  2. Very specific:

    Use kebab-case for asset folders and catalog names, for example skills/systematic-debugging/.

    line 25
  3. Very specific:

    Add or update focused tests in test/*.test.ts for CLI behavior and validation logic.

    line 29
  4. Common:

    Do not add secrets, machine-specific paths, hidden installers, or broad compatibility claims.

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

Repository Guidelines

Project Structure & Module Organization

Agent Powerups is a Node.js/TypeScript CLI plus a catalog of agent assets. Core CLI code lives in src/cli/, with command handlers in src/cli/commands/ and shared helpers in src/cli/utils/. Tests live in test/ as *.test.ts.

Shipped assets are organized by type: skills/, commands/, hooks/, mcp/, agents-md/, workflows/, and examples/. Repository docs live in docs/. Keep catalog.json in sync whenever a shipped asset is added, renamed, removed, or materially changed.

Build, Test, and Development Commands

  • npm install: install Node dependencies.
  • npm run build: compile TypeScript with tsc and create the apx wrapper.
  • npm run test: build, then run the Node test suite via scripts/run-node-tests.mjs.
  • apx doctor: run local health checks after building.
  • apx list: inspect catalog entries.
  • python scripts/validate-skills.py: validate skill metadata and required files.
  • python scripts/validate-catalog.py: validate catalog.json.
  • python scripts/validate-mirrors.py: validate that plugin skill copies match their root skills (variant allowlist inside the script).
  • python scripts/check-requirements.py: check documented tool requirements.

Coding Style & Naming Conventions

Use TypeScript ES modules targeting Node 20+. The project uses strict TypeScript, NodeNext modules, semicolons, double quotes, and two-space indentation. Prefer small named functions, explicit error messages, and local helpers in src/cli/utils/ when logic is shared.

Use kebab-case for asset folders and catalog names, for example skills/systematic-debugging/. Every skill folder must include SKILL.md with YAML frontmatter containing name and description. Agent instruction files should use YAML frontmatter plus a pure Markdown body with headings, not XML-like tags as normal top-level sections.

Testing Guidelines

Add or update focused tests in test/*.test.ts for CLI behavior and validation logic. Use npm run test for the full test path. For asset-only changes, also run the relevant Python validators. There is no separate coverage gate; cover changed behavior and edge cases directly.

Commit & Pull Request Guidelines

Recent history uses short Conventional Commit-style subjects such as feat: add ... and fix: update .... Keep commits scoped to one change.

Pull requests should describe the change, explain validation run, and link related issues when applicable. If shipped assets changed, confirm catalog.json was updated. For tool-dependent skills, document the required command, existence check, install command, approval requirement, and fallback behavior.

Security & Configuration Tips

Do not add secrets, machine-specific paths, hidden installers, or broad compatibility claims. Keep install flows explicit and reviewable; use dry-run commands before write or setup actions when possible.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free