Exactly, for me starting with spec works well. I even do multiple rounds with Claude: "review this from the clean code / SOLID perspective", "check if everything is consistent and follows project conventions". Only after that I allow him to proceed with implementation. And I have architecture and tech stack clearly described in CLAUDE.md
I've noticed the cleaner the codebase, the better AI agents perform on it. They pick up on existing patterns and follow them. Throw them at a messy repo and they'll invent a new pattern every time.
It's basically like hiring a new developer for one task and letting them go right after. They don't know your conventions, your history, or why things are the way they are. The only thing they have is what they can see in the code. Your code quality is basically the prompt now.
Nice! I always forget the lsof flags and end up googling them every time. Would be cool if it could run in the system tray and show what's running on your ports at a glance. Also, the name had me thinking SonarQube at first, might be worth considering a rename to avoid the confusion.