Post

Just noticed myself doing agent<->agent a lot more, which in Q1 I wasn't sure was going to be useful. Seems like it is? Small post

what use case pushed you toward it? for me it was tasks with different context needs, one agent scoping the work before another executes made both cleaner

Pretty much that logic. Controlling the context window is really important

I have a Claude code skill /Conductor which allows one supervisory session to communicate with (via a file bus) other sessions. I have to set up the sessions but from there it runs autonomously. Using Fable as the supervisor and mostly Opus for the workers gets good results.

Each task gets a deep-dive context and the supervisor sees only what matters so it can stay focused on the big picture. Benefit over pure agents is that the sessions talk ongoing throughout the project, so the worker can ask questions as needed.

Also you can see what each worker is doing and intervene if necessary.

the observability + intervention capability is what separates this from fire-and-forget. being able to see what each worker is doing mid-run and step in when something goes sideways makes it practical. does the supervisor poll the file bus or do workers signal when they're ready for review?