spendlisted

# Spend Optimize validated progress per token, not minimum tokens. A session can be expensive and appropriate, or cheap and wasteful — token count alone never decides which. This skill is the judgment layer on top of deterministic telemetry (`tools/telemetry/`, see its README). It must not spend model reasoning reconstructing facts that mechanism already measured or derived. It also must not treat that mechanism's output as proof of quality: telemetry establishes what happened, never whether it was good. ## Evidence order 1. **Reduce the current session's telemetry first**, if not already reduced: `node tools/telemetry/reduce.mjs <session_id>` (the running session's id is available from the statusLine payload's `session_id`, or from `.claude/telemetry/sessions/` if only one session is present). This is a deterministic script — running it costs no model tokens beyond issuing the command. 2. Read the printed record's three sections — `measured`, `derived`, `unknown` — and keep that separation in the final report. Do not present a `judged` conclusion as if the record itself proved it. 3. Only when the record is missing, empty, or missing a field this analysis actually needs, fall back to the platform's own `/usage` or `/context` report for that specific gap — never as a routine replacement for the record, and never by parsing the transcript yourself to recompute a total `reduce.mjs` (or `/usage`/`/context`) already gives you deterministically. `