Skip to content

Plugins

Plugins are packages that add functionality to Claude Code in one go: they bundle skills, subagents, commands, hooks, and MCP servers. It's the fastest way to supercharge your installation with work already done by others.

What is a plugin?

A plugin packages multiple extensions into a single installable unit:

  • Skills — specialized workflows and procedures.
  • Subagents — assistants with specific roles.
  • Commands — slash commands ready to use.
  • Hooks — event automations.
  • MCP servers — connections to external tools.

A marketplace is a repository (usually on GitHub) with a plugin registry. You add the marketplace once and then install whichever plugins you want from it.

Adding a marketplace

Anthropic's official marketplace:

Terminal
/plugin marketplace add anthropics/claude-plugins-official

You can also add one from the community or a private one from your company:

Terminal
/plugin marketplace add https://github.com/user/my-marketplace

Installing a plugin

Terminal
# From an added marketplace
/plugin install github@claude-plugins-official

# Directly from a repo
/plugin install https://github.com/user/my-plugin

Or use the interactive interface: type /plugin and go to Discover to browse, see what each plugin includes, and its estimated context cost before installing.

Managing plugins

Terminal
/plugin           # Opens the panel: list, enable, disable
/plugin list      # View installed plugins

Useful plugins people install

  • GitHub integration (issues, PRs, commits).
  • PR review toolkits (pr-review-toolkit).
  • Commit and deployment workflows.
  • Scientific skill bundles (biology, chemistry with databases).
  • skill-creator for creating and evaluating your own skills.

Getting started quickly with plugins

Creating your own plugin

If you have skills, subagents, or commands you use across multiple projects, you can package them into a plugin and share it (with your team or publicly) by creating a repository with marketplace structure. Ask Claude Code:

Complete Aulafy mapSee how this lesson fits without leaving your path.

Complete Aulafy map

How all courses connect

This is not a checklist. Start with the foundation, choose an outcome, and go deeper only when your project needs more control.

  1. 1Understand
  2. 2Apply or build
  3. 3Operate with confidence
01

Choose an application

Turn the foundation into a visible outcome: a website, a business improvement, media, or an interactive experience.

Continue into the technical branch when you need to maintain code, data, or infrastructure.

02

Build with code

Prepare your environment, work with coding agents, and run models while keeping control of your projects.

This branch prepares you to design and operate reliable AI systems.

03

Take systems to production

Combine retrieval, agents, evaluation, security, deployment, and model adaptation when the problem requires it.

You do not need every course: choose the component your system needs and return as it grows.

View full catalogue