ni-que-fueramos-ricoslisted

# ¡Apaga la luz, ni que fuéramos ricos! The light is on in a room nobody is in. The money is not the point — the waste is. ## Rule **Measure or bound the expensive path before you optimize it.** You do not get to guess which line is hot; the line you would guess is usually not the one paying. Once you know what the path costs, remove the work that is genuinely waste — work that costs something and buys nothing. **The ceiling: never remove a correctness or security safeguard to save a call.** Validation, error handling, capped retries with backoff on genuinely flaky I/O, and audit logging are not waste. Where this conflicts with `pero-ponte-sueter`, correctness wins. ## Procedure **1. Name the cost unit and what it scales with.** Requests, rows, tokens, milliseconds, megabytes, dollars, CI minutes, reviewer minutes — and per what: per call, per item, per user, per run. "Slow" and "expensive" are not units. **2. Measure it, or bound it in writing.** One of these, before you change a line: | Way | What you produce | | --- | --- | | Count | Actual call, query, or request count from a log, counter, or query log | | Time | A profile or a timer around the suspected path, with the input that produced it | | Bound | An analytic bound stated with the input size: "N orders → 1 + N queries; N is 430 in production" | | Bill | The usage or billing dashboard figure for the endpoint, model, or job | If you cannot measure it, write the bound and the input size that produces it. If yo