94% vs 16%: How I made Claude's code reviews consistent by encoding 12 classic engineering books

I ran the same code review with Claude twice. First time: caught the SQL injection, mentioned "separation of concerns". Second time: focused on naming conventions, missed the injection entirely. Same code. Same model. Completely different results. That's the problem I set out to fix — and it took 12 classic engineering books to do it. The Problem Most code quality tools count lines and cyclomatic complexity. That's useful, but it misses the deeper problems: architectural drift, kn...