npx skills add ...
npx skills add anthropics/claude-code --skill plugin-structure
npx skills add anthropics/claude-code --skill plugin-structure
This skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components", "set up plugin.json", "use ${CLAUDE_PLUGIN_ROOT}", "add commands/agents/skills/hooks", "configure auto-discovery", or needs guidance on plugin directory layout, manifest configuration, component organization, file naming conventions, or Claude Code plugin architecture best practices.
The same skill content is published under more than one repo. The install counts are split across them; any of these commands works.
Claude Code plugins follow a standardized directory structure with automatic component discovery. Understanding this structure enables creating well-organized, maintainable plugins that integrate seamlessly with Claude Code.
Key concepts:
.claude-plugin/plugin.json${CLAUDE_PLUGIN_ROOT}Every Claude Code plugin follows this organizational pattern:
Critical rules:
plugin.json manifest MUST be in .claude-plugin/ directory.claude-plugin/The manifest defines plugin metadata and configuration. Located at .claude-plugin/plugin.json:
Name requirements:
code-review-assistant, test-runner, api-docsVersion format: Follow semantic versioning (MAJOR.MINOR.PATCH) Keywords: Use for plugin discovery and categorization
Specify custom paths for components (supplements default directories):
Important: Custom paths supplement defaults—they don't replace them. Components in both default directories and custom paths will load.
Path rules:
./Location: commands/ directory
Format: Markdown files with YAML frontmatter
Auto-discovery: All .md files in commands/ load automatically
Example structure:
File format:
Usage: Commands integrate as native slash commands in Claude Code
Location: agents/ directory
Format: Markdown files with YAML frontmatter
Auto-discovery: All .md files in agents/ load automatically
Example structure:
File format:
Usage: Users can invoke agents manually, or Claude Code selects them automatically based on task context
Location: skills/ directory with subdirectories per skill
Format: Each skill in its own directory with SKILL.md file
Auto-discovery: All SKILL.md files in skill subdirectories load automatically
Example structure:
SKILL.md format:
Supporting files: Skills can include scripts, references, examples, or assets in subdirectories
Usage: Claude Code autonomously activates skills based on task context matching the description
Location: hooks/hooks.json or inline in plugin.json
Format: JSON configuration defining event handlers
Registration: Hooks register automatically when plugin enables
Example structure:
Configuration format:
Available events: PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification
Usage: Hooks execute automatically in response to Claude Code events
Location: .mcp.json at plugin root or inline in plugin.json
Format: JSON configuration for MCP server definitions
Auto-start: Servers start automatically when plugin enables
Example format:
Usage: MCP servers integrate seamlessly with Claude Code's tool system
Use ${CLAUDE_PLUGIN_ROOT} environment variable for all intra-plugin path references:
Why it matters: Plugins install in different locations depending on:
Where to use it:
Never use:
/Users/name/plugins/...)./scripts/... in commands)~/plugins/...)In manifest JSON fields (hooks, MCP servers):
In component files (commands, agents, skills):
In executed scripts:
Commands: Use kebab-case .md files
code-review.md → /code-reviewrun-tests.md → /run-testsapi-docs.md → /api-docsAgents: Use kebab-case .md files describing role
test-generator.mdcode-reviewer.mdperformance-analyzer.mdSkills: Use kebab-case directory names
api-testing/database-migrations/error-handling/Scripts: Use descriptive kebab-case names with appropriate extensions
validate-input.shgenerate-report.pyprocess-data.jsDocumentation: Use kebab-case markdown files
api-reference.mdmigration-guide.mdbest-practices.mdConfiguration: Use standard names
hooks.json.mcp.jsonplugin.jsonClaude Code automatically discovers and loads components:
.claude-plugin/plugin.json when plugin enablescommands/ directory for .md filesagents/ directory for .md filesskills/ for subdirectories containing SKILL.mdhooks/hooks.json or manifest.mcp.json or manifestDiscovery timing:
Override behavior: Custom paths in plugin.json supplement (not replace) default directories
Logical grouping: Group related components together
scripts/ for different purposesMinimal manifest: Keep plugin.json lean
Documentation: Include README files
Consistency: Use consistent naming across components
test-runner, name related agent test-runner-agentClarity: Use descriptive names that indicate purpose
api-integration-testing/, code-quality-checker.mdutils/, misc.md, temp.shLength: Balance brevity with clarity
review-pr, run-ci)code-reviewer, test-generator)error-handling, api-design)Single command with no dependencies:
Complete plugin with all component types:
Plugin providing only skills:
Component not loading:
SKILL.md (not README.md or other name)Path resolution errors:
${CLAUDE_PLUGIN_ROOT}./ in manifestecho $CLAUDE_PLUGIN_ROOT in hook scriptsAuto-discovery not working:
.claude-plugin/)Conflicts between plugins:
For detailed examples and advanced patterns, see files in references/ and examples/ directories.
{
"name": "plugin-name",
"version": "1.0.0",
"description": "Brief explanation of plugin purpose",
"author": {
"name": "Author Name",
"email": "author@example.com",
"url": "https://example.com"
},
"homepage": "https://docs.example.com",
"repository": "https://github.com/user/plugin-name",
"license": "MIT",
"keywords": ["testing", "automation", "ci-cd"]
}{
"name": "plugin-name",
"commands": "./custom-commands",
"agents": ["./agents", "./specialized-agents"],
"hooks": "./config/hooks.json",
"mcpServers": "./.mcp.json"
}commands/
├── review.md # /review command
├── test.md # /test command
└── deploy.md # /deploy command---
name: command-name
description: Command description
---
Command implementation instructions...agents/
├── code-reviewer.md
├── test-generator.md
└── refactorer.md---
description: Agent role and expertise
capabilities:
- Specific task 1
- Specific task 2
---
Detailed agent instructions and knowledge...skills/
├── api-testing/
│ ├── SKILL.md
│ ├── scripts/
│ │ └── test-runner.py
│ └── references/
│ └── api-spec.md
└── database-migrations/
├── SKILL.md
└── examples/
└── migration-template.sql---
name: Skill Name
description: When to use this skill
version: 1.0.0
---
Skill instructions and guidance...hooks/
├── hooks.json # Hook configuration
└── scripts/
├── validate.sh # Hook script
└── check-style.sh # Hook script{
"PreToolUse": [{
"matcher": "Write|Edit",
"hooks": [{
"type": "command",
"command": "bash ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/validate.sh",
"timeout": 30
}]
}]
}{
"mcpServers": {
"server-name": {
"command": "node",
"args": ["${CLAUDE_PLUGIN_ROOT}/servers/server.js"],
"env": {
"API_KEY": "${API_KEY}"
}
}
}
}{
"command": "bash ${CLAUDE_PLUGIN_ROOT}/scripts/run.sh"
}"command": "${CLAUDE_PLUGIN_ROOT}/scripts/tool.sh"Reference scripts at: ${CLAUDE_PLUGIN_ROOT}/scripts/helper.py#!/bin/bash
# ${CLAUDE_PLUGIN_ROOT} available as environment variable
source "${CLAUDE_PLUGIN_ROOT}/lib/common.sh"my-plugin/
├── .claude-plugin/
│ └── plugin.json # Just name field
└── commands/
└── hello.md # Single commandmy-plugin/
├── .claude-plugin/
│ └── plugin.json
├── commands/ # User-facing commands
├── agents/ # Specialized subagents
├── skills/ # Auto-activating skills
├── hooks/ # Event handlers
│ ├── hooks.json
│ └── scripts/
├── .mcp.json # External integrations
└── scripts/ # Shared utilitiesmy-plugin/
├── .claude-plugin/
│ └── plugin.json
└── skills/
├── skill-one/
│ └── SKILL.md
└── skill-two/
└── SKILL.md