Writing Plugins

Writing Plugins

Scope: covers plugin design and architecture. The examples use the Claude Code layout (.claude-plugin/plugin.json + auto-discovered commands/, agents/, skills/, hooks/). The same artifact-selection and architecture reasoning maps to the other tools — only the manifest path and packaging differ:

• Codex CLI: .codex-plugin/plugin.json manifest + .agents/plugins/marketplace.json; skills live at .agents/skills/. See [[nlpm:conventions-codex]].
• Antigravity: gemini-extension.json (becoming "Antigravity plugins"); skills at .agent/skills/. See [[nlpm:conventions-antigravity]].
• Cross-tool skills: a SKILL.md collection with no plugin wrapper installs into any tool via npx skills add. See [[writing-skills]].

For individual artifact authoring, see [[writing-skills]], [[writing-agents]], [[writing-hooks]], [[writing-rules]].

1. Plugin = Commands + Agents + Skills + Hooks

A plugin is a collection of NL artifacts that work together. Before writing anything, decide which artifacts you need.

Artifact Selection Guide

Minimum Viable Plugin

The smallest useful plugin has one artifact:

my-plugin/
  .claude-plugin/
    plugin.json
  commands/
    do-thing.md

Don't add agents, skills, or hooks until you need them. Each artifact adds maintenance burden.

2. Architecture Patterns

Pattern: Single Command (simplest)

Command does everything itself. No agents, no orchestration.

Command receives input --> processes --> outputs result

Use when: task is simple, deterministic, single-step. Example: loc-guardian /scan -- counts lines, checks limits, reports.

File structure:

my-plugin/
  .claude-plugin/plugin.json
  commands/do-thing.md

Pattern: Command + Agent

Command parses input and dispatches one agent for heavy work.

Command parses input --> dispatches agent --> formats output

Use when: task requires AI judgment but has a clear entry point. Example: /nlpm:score dispatches a scorer agent.

File structure:

my-plugin/
  .claude-plugin/plugin.json
  commands/analyze.md
  agents/analyzer.md

Pattern: Command + Multiple Agents (parallel)

Command dispatches 2–6 agents in parallel, synthesizes results.

Command --> agent-1 (security)
        --> agent-2 (performance)    --> synthesize --> output
        --> agent-3 (architecture)

Use when: multiple independent analyses of the same input. Example: grill dispatches 6 review agents in parallel.

File structure:

my-plugin/
  .claude-plugin/plugin.json
  commands/review.md
  agents/
    security-agent.md
    performance-agent.md
    architecture-agent.md

Pattern: Command + Agent Pipeline (sequential)

Each agent feeds into the next. Stages have different model requirements.

Command --> parse (haiku) --> analyze (sonnet) --> QC (sonnet) --> output

Use when: multi-phase processing where each phase depends on the previous. Example: reading-assistant's 4-phase pipeline.

File structure:

my-plugin/
  .claude-plugin/plugin.json
  commands/process.md
  agents/
    parser.md       # haiku
    analyzer.md     # sonnet
    qc-agent.md     # sonnet

Pattern: Hooks Only (no commands)

Plugin enforces policy silently via hooks. No user-facing commands.

Event fires --> hook checks --> allow/deny/advise

Use when: enforcement should be automatic, not user-initiated. Example: tdd-guardian's pre-commit quality gate.

File structure:

my-plugin/
  .claude-plugin/plugin.json
  hooks/hooks.json
  scripts/check.sh

Pattern Selection Matrix

3. The plugin.json Manifest

Required Fields

Only name is strictly required:

{
  "name": "my-plugin"
}

Recommended Fields

Ship with these for discoverability and marketplace listing:

{
  "name": "my-plugin",
  "version": "0.1.0",
  "description": "What this plugin does in one sentence",
  "author": { "name": "your-name" },
  "license": "MIT",
  "keywords": ["relevant", "search", "terms"],
  "category": "developer-tools"
}

Field Reference

4. File Structure

Full Plugin Layout

my-plugin/
  .claude-plugin/
    plugin.json              # manifest (required)
    marketplace.json         # for marketplace publishing
  commands/                  # auto-discovered by Claude Code
    do-thing.md              # user-invocable: /plugin:do-thing
    advanced-thing.md
    shared/                  # non-invocable partials
      common-logic.md        # user-invocable: false
      format-output.md
  agents/                    # auto-discovered
    worker.md
    reviewer.md
  skills/                    # auto-discovered
    my-plugin/
      domain-knowledge/
        SKILL.md
      advanced-topic/
        SKILL.md
        references/
          deep-dive.md
  hooks/
    hooks.json               # hook definitions
  scripts/                   # hook scripts, utilities
    check.sh
    validate.sh
  CLAUDE.md                  # architecture guide (for Claude)
  README.md                  # user documentation (for humans)
  LICENSE

Directory Conventions

Naming Conventions

5. Versioning

Semver Rules

Four-Place Update

When bumping version, update in four places:

Order: push plugin repo first, then update central marketplace. The marketplace points to the repo -- if the repo isn't updated yet, users pull stale code.

6. CLAUDE.md for Plugins

Your plugin's CLAUDE.md is for Claude (the AI), not the user. It tells Claude how the plugin's artifacts relate to each other.

What to Include

# my-plugin

## Architecture
Brief description of what the plugin does and how artifacts interact.

## Artifacts

### Commands
| Command | Purpose |
|---------|---------|
| /plugin:scan | Discovers and inventories files |
| /plugin:fix | Auto-fixes issues found by scan |

### Agents
| Agent | Model | Role |
|-------|-------|------|
| scanner | haiku | Mechanical file discovery |
| fixer | sonnet | AI-powered fix generation |

### Conventions
- All agents output findings in severity-tagged format
- Scanner runs before fixer (sequential dependency)
- Hook scripts use fail-open pattern

What NOT to Include

• Installation instructions (those go in README.md)
• User-facing documentation (README.md)
• Changelog (CHANGELOG.md or git history)
• Contributing guidelines (CONTRIBUTING.md)

7. Shared Partials

Extract repeated logic into commands/shared/*.md with user-invocable: false.

Partial Frontmatter

---
user-invocable: false
description: "Shared config loading logic"
---

Good Candidates for Extraction

When NOT to Extract

• Logic used by only 1 command (premature abstraction)
• Simple logic under 10 lines (duplication is fine)
• Logic that differs slightly between commands (forced generalization adds complexity)

8. Testing Your Plugin

Pre-Publish Checklist

Testing Agent Triggers

For each agent, test with 3 types of queries:

9. Marketplace Publishing

1. Push your plugin repo to GitHub
2. Add entry to central marketplace.json (name, source, description, version, author, license, keywords, category)
3. Add row to central marketplace README.md version table
4. Commit and push the central marketplace repo
5. Verify: claude plugin install my-plugin@xiaolai --scope project

Pre-publish checks: claude plugin validate ., verify no hardcoded paths (grep -r '/Users/' commands/ agents/ hooks/), verify all scripts executable, verify version matches in all 4 locations.

10. Common Mistakes