Is prompt constraints or using a secondary review agent better for preventing implementation drift?

Plan mode in coding agents sounds great on paper but actual implementation almost always deviates from the approved scope. Unwanted refactoring and premature "task finished" triggers are huge productivity killers.

Some developers use a second agent instance purely as a linter/checker, while others restrict execution to ultra strict prompt specs.

For those running agentic workflows daily: what setup has actually worked to keep implementation locked strictly to your initial plan