I am doing something similar: I use openspec to create context and a sequential task list that I feed to ralph loops, so that i’m involved for the planning and the verification step but completely hands off the wheel during code generation.

Exactly that. I created an "Open Ralph" loop initially within Claude directly with review gates per phase in the OpenSpec task list.

But it was always just a workaround to what I truly wanted (what I'm building now), a full external managed orchestrator loop. The agents aren't aware of the loop, they don't need to be.