agents
by wshobson
A large collection of ready-made plugins, specialist agents, skills and commands for AI coding tools such as Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Antigravity and Pi. It gives these tools reusable instructions for work like Python and JavaScript development, code review, testing and security scanning.
- Stars
- 41.9k +60 a day
- Licence
- MIT
- Runs on
- Your computer
- Setup
- Moderate
- Language
- Python
- Age
- 459 days
What you can do with it
- Install a plugin such as python-development into Claude Code or Codex to get specialist agents and a project scaffolding command
- Add a single skill, such as python-testing-patterns, using the gh skill or npx skills installers
- Run security review, code review and debugging workflows through your AI coding assistant
Make money with it
A freelance developer could use these agents to deliver client web apps and APIs faster, taking on more paid projects in the same time.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- A freelance developer can speed up building, testing and reviewing client projects by reusing specialist agents and skills
- A small team without a dedicated security reviewer can run automated security and dependency checks on its code before release
Can you use it commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Getting it running
For Claude Code or Codex, you add the marketplace with a command and install plugins; for OpenCode, Antigravity, Copilot and Pi, you clone the repository and run a make command, which needs uv and Python 3.12 or later.
Follow the official instructions in the project README.
Things to check
- Needs an AI coding tool, which may require a paid subscription or API usage
- Output from AI agents needs human review before use in production
- Features and quality differ between supported tools, as some use generated adapters
Who's talking about it
- Githot: This week on GitHub Trending (20–26 Oct 2026) Featured in a roundup
Checked 27 Oct 2026. Summary drafted by AI from the project's README.
