Agent Development

Comprehensive guide for building autonomous agents in Claude Code plugins with structured frontmatter, system prompts, and triggering conditions. 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: Agent identifier used for namespacing and invocation. Format: lowercase, numbers, hyphens only Length: 3-50 characters Pattern: Must start and end with alphanumeric Good examples: Bad examples: Defines when Claude should trigger this agent. This is the most critical field. Must include: Format: Best practices: Which model the agent should use. Options: Recommendation: Use inherit unless agent needs specific model capabilities.