Agent Development

This handles everything around building autonomous agents for Claude Code plugins. You'll use it when you need to understand agent frontmatter structure, write triggering descriptions with proper example blocks, design system prompts that actually work, or figure out when to use an agent versus a command. The source material is thorough on the mechanics: YAML frontmatter requirements, the description field format with context/user/assistant/commentary examples, model and color options, and tool restrictions. It also covers the system prompt template with responsibilities, process steps, and output formats. If you're building a plugin that needs subagents to handle complex workflows autonomously, this gives you the complete structure and validation rules. The AI-assisted generation method is particularly useful if you want Claude to scaffold agent configs from natural language descriptions.