News for hackers. Stuff that matters.
Re:Agents fail like engineers, so I review them like engineers by Azkar on Sunday October 25, 2026 @02:40AM (#50228922)
I use the max plan, I don’t usually check the usage for a full build so I don’t know exact token usage.

Looking at my recent usage, it’s the second most after the feature orchestration itself. It will also depend on how many claims it has to verify and what I’m building. It’s the most valuable piece of glue that I’ve found when passing things between other focused agents.

My experience is with Claude, but I expect other frontier models would work just as well.

There are no comments on this comment yet.