This is pretty close to a process I use (regardless of model size) and I would agree getting it into a workflow I can run with a one-liner is a good idea. There are a few ways of doing this and I have tended to fallback to markdown engineering. (custom agents and subs in opencode)
It's really interesting to see the progress in the 27-30B range, they have gotten quite good but still make noticeably more hallucinations or bad assumptions (ime).
It's really interesting to see the progress in the 27-30B range, they have gotten quite good but still make noticeably more hallucinations or bad assumptions (ime).