fr-auditlisted

# fr-audit **Announce at start:** "I'm using fr-audit to audit <runs or sessions>." The numbers are not yours to compute. `fr usage` reads the harness's own session store, deduplicates it, classifies every tool call and splits the harness's own dollar figure. Your job is choosing what to compare and saying what the split means. Never add a figure by hand, never price tokens yourself, and never write `0` where the report says `—`. ## The engine | Command | Does | |---|---| | `fr usage collect --run <id>` | every session a run cursor records, normalized into `$HOME/.cache/fr/usage/` | | `fr usage collect --session <id> [--harness opencode\|hermes]` | one session (default harness: claude-code) | | `fr usage report --run <id> [--run <id>…] --format table` | per model, activity, sub-activity and step | | `fr usage report --session <id>… --format html -o <file>` | the same as one self-contained page | Both are read-only: they read a run cursor and the harness store, and write only under the cache. They run anywhere, even where the cursor is stale. `report` reads any session not yet collected live. Pass `--repo <path>` when the run's cursor lives in another checkout (active or archived cursors both resolve). ## Choosing what to compare - **One run:** `--run <id>`. The step table shows which pipeline step spent what. - **Before and after a process change:** collect a comparable run on each side (same shape of work, same harness, similar size). Report them separately, then si