Does that work? I'd think if it could plan things out itself it wouldn't need a roadmap, but maybe it is like how LLMs "reason" by arguing with themselves.

I use something similar (openspec change specifications rather than a literal ROADMAP.md file) and I will sometimes spend hours iterating on the details of a change file, before letting my agent actually implement it. Yes, the agent is generally dealing with doing the actual editing, but I will read it and use dictation to direct modifications to the file.