confidence-checklisted

# confidence-check — is the ground under this actually known? Three things get assumed at the start of implementation and are wrong often enough to be worth a minute: that nothing equivalent already exists, that the API is what you remember, and that the bug's cause is understood rather than guessed. Settle them before writing, not after. ## Five checks 1. **No duplicate exists** - Search codebase for similar functionality - Check if existing code can be extended instead 2. **Architecture compliant** - Uses existing stack/patterns in the project - No unnecessary new dependencies - Follows project's established conventions 3. **Official docs reviewed** - Library/framework API verified against current version - Breaking changes checked if upgrading 4. **Working reference found** - OSS example or proven pattern identified - Not relying on untested approach 5. **Root cause understood** - For bugs: clear understanding of WHY it fails - For features: clear understanding of requirements ## What to do with the answers **Any check unsatisfied — say which, and ask.** All five satisfied — proceed. That is the whole rule, and it is what the old weighted score already encoded: the weights summed to 85 without any one of them, so a single miss could never reach the "proceed" band. The percentage carried no information the list of failed checks did not, while looking like a measurement. It also invited the wrong move. A number can be nudged — one c