Cannot show now because Github times out for me, again.
I had pi write me a ralph loop plugin. You plan with it, it breaks it down into tasks. Task success means clearing the context - if it runs out of context, it clears and starts on the same task again (code changes from previous run are left intact).
Complete with little docker-like names for Ralph sessions and the ability to resume sessions should you need to.
Point is, I would generally do this because it costs less context I think, and better tracks progress.
Ping me if you are interested and want it. Otherwise, plenty around :)
Hehe yes please. I’m not sure how it will go mixing it with Superpowers, but your workflow sounds really useful. I like that it can recover from zero.. especially when I overclock ram and then hangs
I do something similar to this, but manually. I just ask Opus to break the implementation into phases, after each phase is complete it'll update the handoff document, and I'll review the work before starting the next phase in a new session.
I actually started using Opus 5.5 2-3 weeks ago and I'm still having to adapt my workflow around it.