CCA-F
Start Free
Courses/Introduction to Subagents

Introduction to Subagents

Course

A comprehensive, hands-on course on Claude subagents — specialized AI assistants that run in their own context window, do focused work, and return only a clean summary. Learn how subagents preserve context, when to delegate (and when not to), how to create custom subagents in Claude Code (.claude/agents) and the Claude Agent SDK (AgentDefinition), the built-in Explore/Plan/general-purpose agents, tool restriction, model selection, parallel vs sequential execution, and the orchestrator-worker patterns behind Anthropic's multi-agent research system. Verified against official Anthropic docs. Free to start.

5 sections|18 lessons|0/18 completed
1What Are Subagents?2Why Context Isolation Matters3The Built-in Subagents: Explore, Plan, General-Purpose4How Delegation Works: The Description Drives Everything
5Creating Your First Subagent with /agents6The Config File: Frontmatter and System Prompt7Scope and Precedence: Where Subagents Live8Choosing Model, Tools, and Color
9Descriptions That Shape Input Prompts10Output Formats and Obstacle Reporting11Limiting Tool Access
12When Subagents Shine13Anti-Patterns: When Subagents Hurt14The Decision Rule and Execution Modes
15Subagents in the Claude Agent SDK16Parallel, Sequential, and the Workflow Tool17Multi-Agent Orchestration: The Orchestrator-Worker Pattern18Course Review and Exam Tips