@juliusbrussee/caveman-stats-caveman

πŸͺ¨ why use many token when few token do trick β€” Claude Code skill that cuts 65% of tokens by talking like caveman

View in AI SkillSafe app
Scanned Β· no findings
0 downloads
0 stars
0 demos
SKILL.md
namecaveman-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).

Embed badges

Add these to your README to show the skill's verification status.

SkillSafe verified badge
Verified badge
[![SkillSafe verified badge](https://api.skillsafe.ai/v1/badge/@juliusbrussee/caveman-stats-caveman/verified)](https://skillsafe.ai/skill/@juliusbrussee/caveman-stats-caveman/)
Installs badge
Installs badge
[![Installs badge](https://api.skillsafe.ai/v1/badge/@juliusbrussee/caveman-stats-caveman/installs)](https://skillsafe.ai/skill/@juliusbrussee/caveman-stats-caveman/)
Scan badge
Scan badge
[![Scan badge](https://api.skillsafe.ai/v1/badge/@juliusbrussee/caveman-stats-caveman/scan)](https://skillsafe.ai/skill/@juliusbrussee/caveman-stats-caveman/)
Eval pass rate badge
Eval pass rate
[![Eval pass rate badge](https://api.skillsafe.ai/v1/badge/@juliusbrussee/caveman-stats-caveman/eval)](https://skillsafe.ai/skill/@juliusbrussee/caveman-stats-caveman/)