@juliusbrussee/caveman-stats-caveman
πͺ¨ why use many token when few token do trick β Claude Code skill that cuts 65% of tokens by talking like caveman
| name | caveman-stats |
| description | > |
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 β 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 β 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).
Loading...
Select a file to preview
Analyzing security...
Checking scan reports and verification data.
Bill of Materials
Everything this skill can do β files, network, commands, and more.