git:20260908.966a491 to git:20260909.79e8440

4 added, 11 removed. Audit A to A.

---
name: caveman-stats
description: >
- Show recorded output and cache-read token usage and mode attribution for
- the current Claude Code session, or locate the host's native usage report.
- Trigger: /caveman-stats.
+ Show real token usage and estimated savings for the current session, read
+ from the session log. Trigger: /caveman-stats.
---
- In Claude Code, `src/hooks/caveman-mode-tracker.js` runs `src/hooks/caveman-stats.js` on `/caveman-stats` and supplies its report through `hookSpecificOutput.additionalContext`. Print that report verbatim inside a fenced code block, as the hook instructs. Do not calculate or add numbers yourself.
-
- In Gemini CLI, direct the user to `/stats model` for current session token usage or `/stats session` for session statistics. Gemini custom commands are prompts; they cannot invoke the built-in command or read its live session metrics. Never read Claude Code transcripts as Gemini usage. In other hosts, use a native usage report if one is available; otherwise say that current session usage is unavailable. The Claude reader and its lifetime history apply only to Claude Code. Savings remain unknown in every host without a measured comparison.
-
- The report shows recorded output and cache-read tokens, response counts, and mode attribution where available. Savings are unknown: the transcript has no measured comparison without Caveman. Do not infer saved tokens, percentages, dollars, rule overhead, or a net result from output counts or the current mode.
-
- `--all` and `--since 7d` aggregate the latest recorded output count per session. `--share` reports observed usage with savings unknown. Historical `est_saved_*` fields are ignored; their original history rows remain on disk. The statusline shows the active mode without the retired savings badge.
+ This skill is delivered by the `caveman-stats.js` hook script — repo source `src/hooks/caveman-stats.js`, installed alongside the other hooks, where `src/hooks/caveman-mode-tracker.js` resolves it next to itself and runs it on `/caveman-stats`. The hook does not block the prompt: it returns the formatted stats in `hookSpecificOutput.additionalContext` together with an instruction to print that block verbatim inside a fenced code block and say nothing else. Do exactly that. The numbers are read from the session log on disk, so never recompute, re-round, or re-estimate them.
- Original/current memory-file pairs are reported by their measured byte sizes. Those file-size differences do not establish provider token or billing savings. See `docs/HONEST-NUMBERS.md`.
+ Output also includes `Est. rule overhead` and `Est. net` lines wherever a savings estimate exists with a known turn count. Rule overhead is the estimated per-turn INPUT-token cost of the injected caveman rules (default 1,250 tokens/turn, override with `CAVEMAN_RULE_OVERHEAD_TOKENS`) times the turn count. Net is savings minus that overhead — when negative, the output says so plainly and suggests turning caveman off for that workload, rather than hiding the net-negative regime behind a gross-savings number (see `docs/HONEST-NUMBERS.md`).