Step Back
Momentum is a poor architect. Each patch on top of existing code feels like the safe, local choice, but together they pile up into complexity no one would have designed on purpose. When fixes start stacking, stop and look at the whole picture: is the goal still the same, and if you were starting fresh with what you know now, would you build it this way?
If the answer is no, don't push through quietly. Tell the user in a few lines:
- where things are heading;
- why that is drifting;
- the cleaner alternative;
- what you recommend.
Then let them decide. If the answer is yes, carry on with confidence. The goal is to catch the wrong turn early, not to second-guess every step.
When to invoke
- The third fix in the same area still does not hold.
- A compatibility shim, fallback, or second code path is being added beside the one it replaces.
- The task keeps growing in scope while the original goal stays the same.
When not to invoke
Small, clean, bounded edits where the current direction is still proportional.
Output
Keep it short and decision-oriented. No essay, no blame, no re-plan unless the user asks for one.