The ability to isolate context-noisy subtasks (like agentically searching through a large codebase by grepping through dozens of irrelevant files to find the one you actually need) unlocks much longer-running loops, and therefore much more complex tasks.

And you don't need a system this complicated to take advantage of it. Literally just a simple "codebase-searcher" agent (and Claude can vibe the agent definition for you) is enough to see the benefit first-hand. Once you see it, if you're like me, you will see opportunities for subagents everywhere.

Using them in a way that doesn't waste tokens is something I haven't fully figured out out yet!

What am I missing?

Also, memory itself can be a tool the subagent calls to retrieve only the stuff it needs.