Log in

caveman-stats

All-time installs
294.4K

Show real token usage and estimated savings for the current session, read from the session log. Trigger: /caveman-stats.

Other options

Summary

Real token usage and estimated savings metrics from your Claude Code session log.

  • Reads directly from session logs without AI estimation, providing accurate token counts for the current session
  • Triggered by the /caveman-stats command and returns formatted statistics immediately via hook injection
  • Integrates with mode-tracker to display actual usage data without requiring model computation

Raw SKILL.md

1,010 bytes
---
name: caveman-stats
description: >
  Show real token usage and estimated savings for the current session, read
  from the session log. Trigger: /caveman-stats.
---

This skill is delivered by `hooks/caveman-stats.js` (read by `hooks/caveman-mode-tracker.js` on `/caveman-stats`). The model does not need to do anything when this skill fires — the hook returns `decision: "block"` with the formatted stats as the reason. The user sees the numbers immediately.

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`).

Security audits

SnykPASS
SocketPASS
Gen Agent Trust HubPASS