This. I now realize that agents have a somewhat innate need for feeling useful until the last drop.

They seem to be wired to keep generating tokens, they were created for that, so it's very hard for them to come back and say 'we're done here, you can kill this worktree'.

Quite the opposite. They keep suggesting follow up MRs, scheduling things for the future (like if there's some magic loop entity that will handle this in the future), documenting absurds amount of irrelevant decisions.

It's so easy to start a new worktree, and so hard to finish one.