p_kuni

This depends heavily on your product. There is certain software where I agree with you. But for the usual business CRUD app, why would I need to know my code? It's vastly cheaper to understand code on demand, than digging into every single line of code preemptively.

In my products I definitely take care of architecture, interfaces and data, as they have a high cost of failure. Anything else doesn't matter. If an user finds a rare edge condition, asking an agent to fix it costs less than 10€. Properly reviewing a big PR costs somewhere between 100-1.000€. I would be completely irresponsible to my business to review the code in-depth.

Why would you have a spec drift? My team has an AI review that matches the existing specs against the current implementation. This is very useful and keeps both in sync. If there are any conflicts they are noted in the pull request review and can be fixed. This works very nicely.

Although I don't use it, Antigravity should be configurable to prevent reads / writes to certain files. You should definitely do that and ideally configure a hook to automatically run the linter after the LLM completes, then feed it back to the LLM if it's red. Don't prompt your agent to do stuff, build your loop in a deterministic manner.

Why does your harness allow the LLM to generate output that can disable rules & checks?