From caveman
Shows real token usage and estimated savings for the current Claude Code session by reading the session log directly. Triggered via `/caveman-stats`.
How this skill is triggered — by the user, by Claude, or both
Slash command
/caveman:caveman-statsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
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.
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.
npx claudepluginhub juliusbrussee/caveman --plugin caveman4plugins reuse this skill
First indexed Jun 4, 2026
Displays real token usage and estimated cost savings for the current Claude Code session by reading session logs directly. Invoke via /pordee-stats for accurate, non-AI computed stats.
Displays real token usage and estimated savings for current Claude Code session from session logs—no AI estimation. Invoke via `/genshijin-stats` for session stats, `--all` lifetime totals, `--share` summaries, or `--since` periods.
Tracks tokens, analyzes caching behavior, identifies bottlenecks in tool usage, and estimates costs to optimize Claude Code session performance and efficiency.