That’s what this is. It’s just defining two types of subagent relationship (spawned and forked) and providing the minimal MCP API for controlling them. It’s up to the LLMs when and how to use subagents.

They do. But with fine tuning for your use case you will get more power over what they do and if you do it right (no idea yet, if this tool here will really help) - you will get better results.