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 ${CLAUDE_PLUGIN_ROOT}", "add commands/agents/skills/hooks", "configure auto-discovery", or needs guidance on plugin directory layout, manifest configuration, component organization, file naming conventions, or Claude Code plugin architecture best practices.
/plugin marketplace add astrosteveo/harness/plugin install harness@astrosteveo-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
README.mdexamples/advanced-plugin.mdexamples/minimal-plugin.mdexamples/standard-plugin.mdreferences/component-patterns.mdreferences/manifest-reference.mdClaude Code plugins follow a standardized directory structure with automatic component discovery. Understanding this structure enables creating well-organized, maintainable plugins that integrate seamlessly with Claude Code.
Key concepts:
.claude-plugin/plugin.json${CLAUDE_PLUGIN_ROOT}Every Claude Code plugin follows this organizational pattern:
plugin-name/
├── .claude-plugin/
│ └── plugin.json # Required: Plugin manifest
├── commands/ # Slash commands (.md files)
├── agents/ # Subagent definitions (.md files)
├── skills/ # Agent skills (subdirectories)
│ └── skill-name/
│ └── SKILL.md # Required for each skill
├── hooks/
│ └── hooks.json # Event handler configuration
├── .mcp.json # MCP server definitions
├── .lsp.json # LSP server definitions
└── scripts/ # Helper scripts and utilities
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": "plugin-name"
}
Name requirements:
code-review-assistant, test-runner, api-docs{
"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"]
}
Version format: Follow semantic versioning (MAJOR.MINOR.PATCH) Keywords: Use for plugin discovery and categorization
Specify custom paths for components (supplements default directories):
{
"name": "plugin-name",
"commands": "./custom-commands",
"agents": ["./agents", "./specialized-agents"],
"hooks": "./config/hooks.json",
"mcpServers": "./.mcp.json",
"lspServers": "./.lsp.json",
"outputStyles": "./styles/"
}
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:
commands/
├── review.md # /review command
├── test.md # /test command
└── deploy.md # /deploy command
File format:
---
name: command-name
description: Command description
---
Command implementation instructions...
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:
agents/
├── code-reviewer.md
├── test-generator.md
└── refactorer.md
File format:
---
description: Agent role and expertise
capabilities:
- Specific task 1
- Specific task 2
---
Detailed agent instructions and knowledge...
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:
skills/
├── api-testing/
│ ├── SKILL.md
│ ├── scripts/
│ │ └── test-runner.py
│ └── references/
│ └── api-spec.md
└── database-migrations/
├── SKILL.md
└── examples/
└── migration-template.sql
SKILL.md format:
---
name: Skill Name
description: When to use this skill
---
Skill instructions and guidance...
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:
hooks/
├── hooks.json # Hook configuration
└── scripts/
├── validate.sh # Hook script
└── check-style.sh # Hook script
Configuration format:
{
"PreToolUse": [{
"matcher": "Write|Edit",
"hooks": [{
"type": "command",
"command": "bash ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/validate.sh",
"timeout": 30
}]
}]
}
Available events: PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification
Usage: Hooks execute automatically in response to Claude Code events
Location: .mcp.json at plugin root or inline in plugin.json
Format: JSON configuration for MCP server definitions
Auto-start: Servers start automatically when plugin enables
Example format:
{
"mcpServers": {
"server-name": {
"command": "node",
"args": ["${CLAUDE_PLUGIN_ROOT}/servers/server.js"],
"env": {
"API_KEY": "${API_KEY}"
}
}
}
}
Usage: MCP servers integrate seamlessly with Claude Code's tool system
Location: .lsp.json at plugin root or inline in plugin.json
Format: JSON configuration for Language Server Protocol definitions
Auto-start: Servers start automatically when plugin enables
Example format:
{
"go": {
"command": "gopls",
"args": ["serve"],
"extensionToLanguage": {
".go": "go"
}
}
}
Required fields:
command: LSP binary to execute (must be in PATH)extensionToLanguage: Maps file extensions to language identifiersUsage: LSP servers provide code intelligence (diagnostics, go to definition, find references)
Note: For complete LSP configuration options, see the lsp-integration skill.
Location: Custom directory specified in plugin.json
Format: Markdown files defining output style configurations
Purpose: Customize Claude's response formatting
Example configuration:
{
"name": "plugin-name",
"outputStyles": "./styles/"
}
Directory structure:
styles/
├── concise.md # Concise output style
├── detailed.md # Detailed output style
└── technical.md # Technical documentation style
Usage: Output styles customize how Claude formats responses for specific use cases
Use ${CLAUDE_PLUGIN_ROOT} environment variable for all intra-plugin path references:
{
"command": "bash ${CLAUDE_PLUGIN_ROOT}/scripts/run.sh"
}
Why it matters: Plugins install in different locations depending on:
Where to use it:
Never use:
/Users/name/plugins/...)./scripts/... in commands)~/plugins/...)In manifest JSON fields (hooks, MCP servers):
"command": "${CLAUDE_PLUGIN_ROOT}/scripts/tool.sh"
In component files (commands, agents, skills):
Reference scripts at: ${CLAUDE_PLUGIN_ROOT}/scripts/helper.py
In executed scripts:
#!/bin/bash
# ${CLAUDE_PLUGIN_ROOT} available as environment variable
source "${CLAUDE_PLUGIN_ROOT}/lib/common.sh"
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:
my-plugin/
├── .claude-plugin/
│ └── plugin.json # Just name field
└── commands/
└── hello.md # Single command
Complete plugin with all component types:
my-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 utilities
Plugin providing only skills:
my-plugin/
├── .claude-plugin/
│ └── plugin.json
└── skills/
├── skill-one/
│ └── SKILL.md
└── skill-two/
└── SKILL.md
For security and verification purposes, Claude Code copies plugins to a cache directory rather than using them in-place. Understanding this behavior is important when developing plugins that reference external files.
When a plugin is installed, Claude Code copies the plugin files to a cache directory:
source field is copied recursively.claude-plugin/plugin.json: The implicit root directory (containing .claude-plugin/) is copied recursivelyPlugins cannot reference files outside their copied directory structure. Paths that traverse outside the plugin root (such as ../shared-utils) will not work after installation because those external files are not copied to the cache.
This will NOT work:
{
"command": "bash ../shared-scripts/run.sh"
}
This WILL work:
{
"command": "bash ${CLAUDE_PLUGIN_ROOT}/scripts/run.sh"
}
If a plugin needs to access files outside its directory, there are two options:
Option 1: Use symlinks
Create symbolic links to external files within the plugin directory. Symlinks are followed during the copy process:
# Inside plugin directory
ln -s /path/to/shared-utils ./shared-utils
The symlinked content will be copied into the plugin cache.
Option 2: Restructure for marketplace
Set the plugin path to a parent directory that contains all required files:
{
"name": "my-plugin",
"source": "./",
"description": "Plugin that needs root-level access",
"commands": ["./plugins/my-plugin/commands/"],
"agents": ["./plugins/my-plugin/agents/"],
"strict": false
}
This approach copies the entire marketplace root, giving the plugin access to sibling directories.
--plugin-dirComponent 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.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.