rsi-auditlisted

# RSI Audit This skill parses recent Claude session transcripts and emits a ranked report of token-reduction opportunities. It **writes no routing policy and no product files**: it creates no GitHub issues, writes no control artifacts, and edits no workflow files — the user decides what to act on from the report. It DOES write to the graph: step 6 lands the top-ranked opportunities as ledger tactics through `dispatch-eval-finding`, a find-or-create write to the evaluation-finding ledger (`tactic-eval-finding-<slug>` nodes) — a different graph surface than routing policy, so it does not loosen the bound in the previous sentence. The only other exception is step 9's closing remediation, which is **attended-only** and touches exactly one file, `.claude/settings.json`, which the human reviews and commits; nothing else this skill does writes anything but the report, the ledger, and that one settings file. (The learned phase→model routing policy this skill used to write was retired in #2872: the phase orchestrator is now always Sonnet, and Opus tiering lives at the `agent()`/subagent layer inside each phase's Workflow, not in an audit-written policy.) Two cost figures appear in the output: - **`price_proxy_usd`** — a uniform Opus-list-price rate applied to every token regardless of the actual model. Holding price constant isolates token count, so this figure ranks opportunities by relative magnitude. It is **not** the actual bill. - **`cost_usd`** — the truthful per-model bill. E