calibratelisted

# calibrate: right-size the model and effort before the session starts Every session runs on one model at one effort level, and that choice is made once, at the start. The prompt cache is scoped per model: switch mid-session and the entire conversation is re-read at full input price. So the calibration moment is *before* the work, ideally as a cheap throwaway question in a small-model session, and the output is a start command the user pastes. This skill carries a method, not a model table. Model names, prices and effort levels change; a hardcoded table would rot. What the session's tool offers today is looked up live, every time. ## The method 1. **Name the session's work.** One ticket per session (AGENTS.md efficiency rule), so the ticket defines the work. If the user hasn't said what the session is for, ask that one question first; without it there is nothing to calibrate against. 2. **Get the live lineup, never from memory and never from a saved URL.** First establish which tool the session will run in and which vendor's models it offers; that pair is the input, not an assumption. Model names, prices, effort levels *and the pages that document them* all change over time, so this skill deliberately hardcodes none of them. Search the web for that vendor's **official, current** documentation at the moment of asking (the models overview with pricing, plus whatever the vendor calls its reasoning dial: effort, extended thinking, reasoning budget) an