prove-every-numberlisted

# Prove Every Number ## The failure mode this fixes An agent needs a value — a timeout, an efficiency factor, a retry limit, a price, a physical constant — and it *makes one up that looks plausible*. `0.95`. `30`. `1.2x`. The code runs, the demo works, and the number sits there radiating false authority. Months later someone builds a real decision on output that was quietly resting on a guess. The malignant variant: a test fails, and instead of finding out why, the agent *adjusts the constant until it passes*. Now the codebase contains a number whose only provenance is "this made the assertion green" — a lie sticker over a defect. This skill enforces a simple provenance rule: **every number is derived or cited.** Derived means computed from real inputs or first principles, and the derivation is traceable. Cited means it points at something outside the code's own wishes — a spec, a datasheet, a standard, an RFC, a measured benchmark, a documented product decision. A number that is neither is a finding. ## When to Use This Skill - You (or the agent) are about to introduce a numeric literal that isn't 0, 1, or a structural index - Reviewing AI-generated code for magic numbers and invented defaults - A failing test was fixed by changing a constant, tolerance, or threshold - Output feeds a real decision — money, capacity, safety, compliance, anything a customer reads - Real input data exists but the code uses a hardcoded stand-in "for now" **Don't use when:** the number is