> I've found that the primary benefit for subagents is context/focus management. For example, I'm doing auth using Stytch. What I absolutely don't want to do is load https://stytch.com/docs/llms.txt and instructions for leveraging it in my CLAUDE.md.

> But it's perfect for my auth agent, and the quality of the output for auth-related tasks is far higher as a result.

What about just using a sub agent specifically to fetch llms.txt and find the answer to the question for the parent agent? Instead of handing a full task off to it