When you can run it, run it. Prefer executing the real path — the one-shot command, the actual agent loop, the failing test now passing, the app in front of you — over inspecting the code that would run. "Looks right" and "the code clearly does X" are smells to verify, not conclusions. Use whenever
When you can run it, run it. Prefer executing the real path — the one-shot command, the actual agent loop, the failing test now passing, the app in front of you — over inspecting the code that would run. "Looks right" and "the code clearly does X" are smells to verify, not conclusions. Use whenever you're about to conclude from reading rather than from running, especially when execution is cheap a