SkillsAdd

juliusbrussee/caveman

caveman-stats

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

All-time #187 Trending #144 Hot #6714 First seen Apr 30, 2026
8-week activity · all time api

Installation

$ npx skills add juliusbrussee/caveman --skill caveman-stats
View on skills.sh ↗ GitHub repository ↗

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

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

caveman Similar name
mattpocock/skills 223.9K installs
caveman Similar name
juliusbrussee/skills

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keepi…

3.3K installs
caveman Similar name
juliusbrussee/cavekit

Caveman encoding for SPEC.md and spec-adjacent writes. Loaded by /spec, /build, /check. Cuts to…

2.7K installs
caveman Similar name
pandoscope/skills

Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pl…

1.7K installs
caveman Similar name
vinvcn/mattpocock-skills-zh-cn

超压缩 communication mode。Cuts token usage ~75% by dropping filler, articles, and pleasantries…

1.7K installs
caveman Similar name
shawnchee/caveman-skill

Token-saving terse mode — no filler, no narration, just results

933 installs

Security audits

Partner security reviews for this skill.

agent-trust-hub SAFE

Analyzed May 10, 2026

The skill is a utility for displaying session statistics, such as token usage and cost savings, by reading local session logs. It contains no executable code or malicious patterns in its documentation.

snyk LOW

Analyzed May 10, 2026

No issues detected.

socket Score 0.9000 · 0 alerts

Analyzed May 10, 2026

  • license 1
  • maintenance 1
  • quality 0.9
  • supply chain 1
  • vulnerability 1

0 alerts

Also in this package

Other skills from juliusbrussee/caveman · top by installs.

npx skills add juliusbrussee/caveman
caveman 491.3K caveman-commit 344.3K caveman-review 341K caveman-compress 339.4K caveman-help 332.1K cavecrew 289.8K compress 46.8K caveman-explore 39.4K caveman-optimize 39K caveman-learn 39K

Browse all from juliusbrussee/caveman

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 104.3K
License LICENSE
Default branch main
Open issues 62
Status Active

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,010 B
  • docs README.md 2,105 B
  • docs SUMMARY.md 141 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 290,100 installs

SKILL.md

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 CAVEMANRULEOVERHEAD_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).