plugin-structure

name	plugin-structure
description	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 ${KODIK_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.
version	0.1.0

Plugin Structure for Claude Code

Overview

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:

• Conventional directory layout for automatic discovery
• Manifest-driven configuration in .kodik-plugin/plugin.json
• Component-based organization (commands, agents, skills, hooks)
• Portable path references using ${KODIK_PLUGIN_ROOT}
• Convention-based component loading

Directory Structure

Every Claude Code plugin follows this organizational pattern:

plugin-name/
├── .kodik-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
└── scripts/                 # Helper scripts and utilities

Critical rules:

1. Manifest location: The plugin.json manifest MUST be in .kodik-plugin/ directory
2. Component locations: All component directories (commands, agents, skills, hooks) MUST be at plugin root level, NOT nested inside .kodik-plugin/
3. Optional components: Only create directories for components the plugin actually uses
4. Naming convention: Use kebab-case for all directory and file names

Plugin Manifest (plugin.json)

The manifest defines plugin metadata and configuration. Located at .kodik-plugin/plugin.json:

Required Flat Fields

{
  "schemaVersion": 1,
  "id": "plugin-name",
  "version": "1.0.0",
  "title": "Plugin Name",
  "description": "Brief explanation of plugin purpose.",
  "category": "developer-tools",
  "icon": "./assets/app-icon.svg",
  "author": {
    "name": "Kodik"
  },
  "homepageUrl": "https://example.com/plugin",
  "sourceUrl": "https://github.com/Kodik-AI/kodik/tree/main/marketplace/plugins/plugin-name",
  "tags": ["automation"],
  "prompts": [],
  "userConfig": {}
}

ID requirements:

• Use kebab-case format (lowercase with hyphens)
• Must be unique across installed plugins
• Must match the plugin directory name
• No spaces or special characters
• Example: code-review-assistant, test-runner, api-docs

Manifest rules:

• category must use one of the official lower-kebab ids: coding, developer-tools, productivity, design, engineering, research, api-integrations, or utilities.
• icon must be exactly ./assets/app-icon.svg.
• author is { "name": "Kodik" } for official marketplace plugins.
• tags, prompts, and userConfig are always present; use [] or {} when empty.
• Do not add component path fields such as skills, agents, commands, rules, or hooks.
• Do not add import-only fields such as originalAuthor, sourceMarketplace, keywords, repository, license, or interface.

Component Organization

Commands

Location: commands/ directory Format: Markdown files with YAML frontmatter Auto-discovery: Top-level .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

Agents

Location: agents/ directory Format: Markdown files with YAML frontmatter Auto-discovery: Top-level .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

Skills

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
version: 1.0.0
---

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

Hooks

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 ${KODIK_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

MCP Servers

Location: .mcp.json at plugin root Format: JSON configuration with MCP server definitions under servers Auto-start: Servers start automatically when plugin enables

Example format:

{
  "servers": {
    "server-name": {
      "type": "stdio",
      "command": "node",
      "args": ["${KODIK_PLUGIN_ROOT}/servers/server.js"],
      "env": {
        "API_KEY": "${API_KEY}"
      }
    }
  },
  "meta": {
    "server-name": {
      "id": "server-name",
      "title": "Server Name",
      "description": "Short user-facing description of this MCP server."
    }
  }
}

Usage: MCP servers integrate seamlessly with Claude Code's tool system

Portable Path References

${KODIK_PLUGIN_ROOT}

Use ${KODIK_PLUGIN_ROOT} environment variable for all intra-plugin path references:

{
  "command": "bash ${KODIK_PLUGIN_ROOT}/scripts/run.sh"
}

Why it matters: Plugins install in different locations depending on:

• User installation method (marketplace, local, npm)
• Operating system conventions
• User preferences

Where to use it:

• Hook command paths
• MCP server command arguments
• Script execution references
• Resource file paths

Never use:

• Hardcoded absolute paths (/Users/name/plugins/...)
• Relative paths from working directory (./scripts/... in commands)
• Home directory shortcuts (~/plugins/...)

Path Resolution Rules

In manifest JSON fields (hooks, MCP servers):

"command": "${KODIK_PLUGIN_ROOT}/scripts/tool.sh"

In component files (commands, agents, skills):

Reference scripts at: ${KODIK_PLUGIN_ROOT}/scripts/helper.py

In executed scripts:

#!/bin/bash
# ${KODIK_PLUGIN_ROOT} available as environment variable
source "${KODIK_PLUGIN_ROOT}/lib/common.sh"

File Naming Conventions

Component Files

Commands: Use kebab-case .md files

• code-review.md → /code-review
• run-tests.md → /run-tests
• api-docs.md → /api-docs

Agents: Use kebab-case .md files describing role

• test-generator.md
• code-reviewer.md
• performance-analyzer.md

Skills: Use kebab-case directory names

• api-testing/
• database-migrations/
• error-handling/

Supporting Files

Scripts: Use descriptive kebab-case names with appropriate extensions

• validate-input.sh
• generate-report.py
• process-data.js

Documentation: Use kebab-case markdown files

• api-reference.md
• migration-guide.md
• best-practices.md

Configuration: Use standard names

• hooks.json
• .mcp.json
• plugin.json

Auto-Discovery Mechanism

Kodik automatically discovers and loads components:

1. Plugin manifest: Reads .kodik-plugin/plugin.json when plugin enables
2. Commands: Scans commands/ directory for .md files
3. Agents: Scans agents/ directory for .md files
4. Skills: Scans skills/ for subdirectories containing SKILL.md
5. Hooks: Loads configuration from hooks/hooks.json
6. MCP servers: Loads configuration from the root .mcp.json

Discovery timing:

• Plugin installation: Components register with Kodik
• Plugin enable: Components become available for use
• No restart required: Changes take effect on the next Kodik session

Override behavior: Component path overrides are not supported; use the conventional root directories.

Best Practices

Organization

1. Logical grouping: Group related components together

   • Put test-related commands, agents, and skills together
   • Create subdirectories in scripts/ for different purposes

2. Canonical manifest: Keep plugin.json flat

   • Use only the v1 manifest fields
   • Rely on auto-discovery for standard layouts
   • Put MCP server definitions in .mcp.json

3. Documentation: Include README files

   • Plugin root: Overall purpose and usage
   • Component directories: Specific guidance
   • Script directories: Usage and requirements

Naming

1. Consistency: Use consistent naming across components

   • If command is test-runner, name related agent test-runner-agent
   • Match skill directory names to their purpose

2. Clarity: Use descriptive names that indicate purpose

   • Good: api-integration-testing/, code-quality-checker.md
   • Avoid: utils/, misc.md, temp.sh

3. Length: Balance brevity with clarity

   • Commands: 2-3 words (review-pr, run-ci)
   • Agents: Describe role clearly (code-reviewer, test-generator)
   • Skills: Topic-focused (error-handling, api-design)

Portability

1. Always use ${KODIK_PLUGIN_ROOT}: Never hardcode paths
2. Test on multiple systems: Verify on macOS, Linux, Windows
3. Document dependencies: List required tools and versions
4. Avoid system-specific features: Use portable bash/Python constructs

Maintenance

1. Version consistently: Update version in plugin.json for releases
2. Deprecate gracefully: Mark old components clearly before removal
3. Document breaking changes: Note changes affecting existing users
4. Test thoroughly: Verify all components work after changes

Common Patterns

Minimal Plugin

Single command with no dependencies:

my-plugin/
├── .kodik-plugin/
│   └── plugin.json    # Canonical flat manifest
└── commands/
    └── hello.md       # Single command

Full-Featured Plugin

Complete plugin with all component types:

my-plugin/
├── .kodik-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

Skill-Focused Plugin

Plugin providing only skills:

my-plugin/
├── .kodik-plugin/
│   └── plugin.json
└── skills/
    ├── skill-one/
    │   └── SKILL.md
    └── skill-two/
        └── SKILL.md

Troubleshooting

Component not loading:

• Verify file is in correct directory with correct extension
• Check YAML frontmatter syntax (commands, agents, skills)
• Ensure skill has SKILL.md (not README.md or other name)
• Confirm plugin is enabled in Claude Code settings

Path resolution errors:

• Replace all hardcoded paths with ${KODIK_PLUGIN_ROOT}
• Keep plugin component paths in their conventional root directories
• Check that referenced files exist at specified paths
• Test with echo $KODIK_PLUGIN_ROOT in hook scripts

Auto-discovery not working:

• Confirm directories are at plugin root (not in .kodik-plugin/)
• Check file naming follows conventions (kebab-case, correct extensions)
• Remove any manifest path overrides; component discovery is convention-only
• Restart Claude Code to reload plugin configuration

Conflicts between plugins:

• Use unique, descriptive component names
• Namespace commands with plugin name if needed
• Document potential conflicts in plugin README
• Consider command prefixes for related functionality

---

For detailed examples and advanced patterns, see files in references/ and examples/ directories.