Plugins are shareable packages that bundle slash commands, subagents, skills, hooks, and MCP servers into single installable units.
Before plugins, setting up Claude Code with custom commands, agents, and integrations meant scattered configuration files across different projects. When teammates asked "How do I set up the same thing?", reproducing your setup was tedious and error-prone.
Plugins solve this
Bundle all your customizations into shareable packages that install with a single command. Share with your team or use across your own projects. Learn more in the official plugin guide.
Plugins can include any combination of these five component types. Note the key distinction between user-invoked (Commands) and model-invoked (Skills) components:
Custom shortcuts you explicitly trigger with a forward slash (/)
Commands are user-triggered actions you invoke by typing a forward slash followed by the command name (e.g., /deploy). Unlike Skills which Claude uses automatically, Commands require intentional user action each time.
Example: /deploy - Deploy your application to production
Specialized AI agents that users can invoke manually or Claude can trigger contextually
Agents are Claude instances with specific expertise. Users access them through the /agents interface or by calling them directly by name. Claude can also invoke agents automatically based on task context.
Example: security-reviewer - Specialized agent for security audits
Capabilities that Claude autonomously uses based on task context
Skills are model-invoked—Claude autonomously decides when to use them based on your request and the Skill's description. Unlike Commands which require explicit user action, Skills are automatically applied when Claude determines they match your needs.
Example: api-integration - Claude automatically uses it when you need to interact with REST APIs
Event handlers that automatically trigger at specific lifecycle points
Hooks let plugins run custom scripts automatically at specific points in your workflow—before tool execution, after prompts, when sessions start or end, and more. They execute without prompting.
Example: pre-commit hook - Run tests before every commit
Connections to external tools and data sources via Model Context Protocol
MCP servers provide standardized connections to external services like databases, APIs, cloud providers, and development tools. They start automatically when the plugin is enabled.
Example: GitHub MCP - Access repositories and pull requests
Learn more in the official Claude Code plugin reference.
Single commands, agents, or MCP servers configured manually
Bundled packages that work together seamlessly
Imagine you're working on a web application that needs deployment automation. A DevOps plugin might include:
/deploy command
User-invoked: One-command secure deployments
Infrastructure subagent
Specialized knowledge of your cloud setup
Deployment skill
Model-invoked: Claude uses it automatically when deployment context is detected
Cloud provider MCP
Direct connections to AWS/Vercel/etc.
Pre-deployment hook
Event-driven: Run security scans before every deployment
/plugin install devops-suite and get the complete automation stackNow that you understand what plugins are, learn how to install and use them.