Fundamentals

What Are Claude Code Plugins?

Plugins are shareable packages that bundle slash commands, subagents, skills, hooks, MCP servers, and LSP servers into single installable units.

The Problem Plugins Solve

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.

Plugin Components

Plugins can include any combination of these six component types. Note the key distinction between user-invoked (Commands) and model-invoked (Skills) components:

Slash Commands

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

User-invoked

Subagents

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

Hybrid

Skills

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

Model-invoked

Hooks

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

Event-driven

MCP Servers

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

Tool integration

LSP Servers

Language servers providing code intelligence like go-to-definition and hover docs

LSP servers connect Claude Code to language servers that provide IDE-like features: go-to-definition, find references, hover documentation, and code diagnostics. They require you to have the language server binary installed on your system.

Example: TypeScript LSP - Get type information and navigate to definitions

Code intelligence

Learn more in the official Claude Code plugin reference.

Choosing the Right Component

Not sure which component type fits your use case? Use this guide:

When You Need...	Best Choice	Why
Project-specific instructions	CLAUDE.md	Loaded automatically with every session, no plugin required
Reusable workflow across projects	Skill	Model-invoked based on context, portable between projects
User-triggered automation	Command	Explicit invocation with /name gives you control over when it runs
External API/service access	MCP Server	Standardized protocol with proper tool schema and permissions
Deterministic enforcement	Hook	Always executes, cannot be bypassed by prompting or context
Code intelligence features	LSP Server	Language-specific features like go-to-definition and hover docs

Pro tip: Start with CLAUDE.md

Begin with CLAUDE.md for project rules—it requires no plugin setup. Only create a plugin when you need to share functionality across projects or with teammates.

Plugins vs. Individual Components

Individual Components

Single commands, agents, or MCP servers configured manually

•One component at a time
•Manual configuration required
•Harder to share with others

Plugins

Bundled packages that work together seamlessly

✓Multiple components in one package
✓Simple installation process
✓Easy to share and standardize

Real-World Example

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

Result: Install once with /plugin install devops-suite and get the complete automation stack

Why Use Skills?

Skills use lazy loading—Claude only sees the skill name and description until it's actually needed. A detailed skill with hundreds of lines costs nothing until activated.

💡

Rule of Thumb

If you find yourself adding instructions to CLAUDE.md that only matter for specific tasks, extract them into a skill instead. Your context window stays clean for the work that matters.

Example: API Documentation Skill

skills/api-docs/SKILL.md

---
name: api-docs-helper
description: Generate OpenAPI documentation from code comments
---

# API Documentation Generator

When asked to document an API endpoint:
1. Extract JSDoc/docstring comments from the handler
2. Identify request/response types from TypeScript interfaces
3. Generate OpenAPI 3.0 YAML snippet
4. Include example request/response payloads

This entire skill loads only when Claude detects you're working on API documentation—not during unrelated tasks.

Command Patterns

Commands support parameters via $ARGUMENTS and can spawn subagents for complex workflows.

Parameterized Command

commands/deploy.md

---
name: deploy
description: Deploy to specified environment
arguments:
  - name: environment
    description: Target environment (staging/production)
    required: true
---

Deploy the current branch to $ARGUMENTS environment.

Before deploying:
1. Run the test suite
2. Check for uncommitted changes
3. Verify the target environment is valid

After deployment, report the deployed commit SHA and URL.

Usage: /deploy staging or /deploy production

Command with Subagent

commands/research.md

---
name: research
description: Spawn a research agent to investigate a topic
---

Use the Task tool to spawn a research subagent with these instructions:

"Research the following topic thoroughly: $ARGUMENTS

Focus on:
- Official documentation
- Recent changes or updates
- Common pitfalls and gotchas

Return a concise summary with source links."

This keeps research isolated from your main conversation context.

Subagents run in isolated context, preventing research from cluttering your main conversation.

Next Steps

Now that you understand what plugins are, learn how to install and use them.

Getting Started Browse Plugins

The Problem Plugins Solve

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.

Plugin Components

Plugins can include any combination of these six component types. Note the key distinction between user-invoked (Commands) and model-invoked (Skills) components:

Slash Commands

Custom shortcuts you explicitly trigger with a forward slash (/)

Example: /deploy - Deploy your application to production

User-invoked

Subagents

Specialized AI agents that users can invoke manually or Claude can trigger contextually

Example: security-reviewer - Specialized agent for security audits

Hybrid

Skills

Capabilities that Claude autonomously uses based on task context

Example: api-integration - Claude automatically uses it when you need to interact with REST APIs

Model-invoked

Hooks

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

Event-driven

MCP Servers

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

Tool integration

LSP Servers

Language servers providing code intelligence like go-to-definition and hover docs

Example: TypeScript LSP - Get type information and navigate to definitions

Code intelligence

When You Need...

Best Choice

Project-specific instructions

CLAUDE.md

Reusable workflow across projects

Skill

User-triggered automation

Command

External API/service access

MCP Server

Deterministic enforcement

Hook

Code intelligence features

LSP Server

Plugins vs. Individual Components

Individual Components

Single commands, agents, or MCP servers configured manually

•One component at a time
•Manual configuration required
•Harder to share with others

Plugins

Bundled packages that work together seamlessly

✓Multiple components in one package
✓Simple installation process
✓Easy to share and standardize

Real-World Example

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

Result: Install once with /plugin install devops-suite and get the complete automation stack

--- name: api-docs-helper description: Generate OpenAPI documentation from code comments --- # API Documentation Generator When asked to document an API endpoint: 1. Extract JSDoc/docstring comments from the handler 2. Identify request/response types from TypeScript interfaces 3. Generate OpenAPI 3.0 YAML snippet 4. Include example request/response payloads

--- name: deploy description: Deploy to specified environment arguments: - name: environment description: Target environment (staging/production) required: true --- Deploy the current branch to $ARGUMENTS environment. Before deploying: 1. Run the test suite 2. Check for uncommitted changes 3. Verify the target environment is valid After deployment, report the deployed commit SHA and URL.

--- name: research description: Spawn a research agent to investigate a topic --- Use the Task tool to spawn a research subagent with these instructions: "Research the following topic thoroughly: $ARGUMENTS Focus on: - Official documentation - Recent changes or updates - Common pitfalls and gotchas Return a concise summary with source links." This keeps research isolated from your main conversation context.