agent-development
Comprehensive guide for building autonomous agents in Claude Code plugins with structured frontmatter, system prompts, and triggering conditions.
- Agents are autonomous subprocesses defined in markdown files with YAML frontmatter; use them for multi-step independent work, not user-initiated commands
- Required frontmatter fields:
name(3–50 lowercase-hyphenated characters),description(with 2–4 concrete triggering examples),model(inherit/sonnet/opus/haiku), andcolor(blue/cyan/green/yellow/magenta/red) - System prompts should follow a structured template with clear responsibilities, step-by-step analysis process, quality standards, output format, and edge case handling; keep under 10,000 characters
- Optional
toolsfield restricts agent access to specific capabilities (e.g., Read, Write, Grep, Bash) following the principle of least privilege - Includes validation rules for identifiers and descriptions, testing strategies for triggering and system prompt behavior, and utility scripts for validation and testing
Agent Development for Claude Code Plugins
Overview
Agents are autonomous subprocesses that handle complex, multi-step tasks independently. Understanding agent structure, triggering conditions, and system prompt design enables creating powerful autonomous capabilities.
Key concepts:
- Agents are FOR autonomous work, commands are FOR user-initiated actions
- Markdown file format with YAML frontmatter
- Triggering via description field with examples
- System prompt defines agent behavior
- Model and color customization
Agent File Structure
Complete Format
---
More from anthropics/claude-plugins-official
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
7.9Kclaude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project memory optimization".
4.6Kplayground
Creates interactive HTML playgrounds — self-contained single-file explorers that let users configure something visually through controls, see a live preview, and copy out a prompt. Use when the user asks to make a playground, explorer, or interactive tool for a topic.
3.3Kclaude-automation-recommender
Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.
3.3Kskill-development
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
2.5Kskill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
2.5K