##### ###### ##### ### # # ### # # ###### ## ## ## ## ## ## ## # # # # # ## ##### #### ##### # # # # # # # #### ## # ## ## ## ## # # # # # ## ## # ###### ## ### # ### # ######
##### ###### ##### ### # # ### # # ###### ## ## ## ## ## ## ## # # # # # ## ##### #### ##### # # # # # # # #### ## # ## ## ## ## # # # # # ## ## # ###### ## ### # ### # ######
Sub-agents for complex work
For complex tasks, Claude Code can spawn sub-agents. Each sub-agent gets its own context window, preventing context overflow.
Example: "Create a sub-agent to refactor the authentication module while I work on the API endpoints."
Sub-agents work in parallel and report back results. This scales to larger projects than a single conversation can handle.
