Skip to content
Get packs

Caveman Stats Reporter

Shows recorded token usage for your Claude Code session without guessing savings

Source Download skill
Repository
JuliusBrussee/caveman
Stars
116,835
Licence
Apache-2.0
Files
1 file

What it does

When you type /caveman-stats in Claude Code, the agent prints a usage report that a companion hook script generates from recorded session data: output tokens, cache-read tokens, response counts, and which Caveman mode was active. It is designed to be honest: it does not estimate how many tokens were saved, and the agent is told not to calculate numbers itself. In other tools like Gemini CLI, it instead points you to that tool's built-in stats commands.

Great for

  • Claude Code users who want to see recorded token usage for a session
  • Developers curious how often Caveman modes were active across sessions
  • Anyone who wants usage numbers without inflated savings claims

Skip it if

  • Users who need actual token savings figures, since the skill states savings are unknown because there is no measured comparison without Caveman
  • Users of Gemini CLI or other hosts who expect live session metrics, since the skill can only direct them to native commands

Try asking

  • “/caveman-stats”
  • “/caveman-stats --all”
  • “/caveman-stats --since 7d”
  • “/caveman-stats --share”
Step-by-step guide: how to use Caveman Stats ReporterInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the Apache-2.0 licence and an attribution note.

    caveman-stats.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip caveman-stats.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip caveman-stats.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Run /caveman-stats --since 7d to aggregate recent sessions instead of only the current one
  • Read the savings-unknown note as intentional: the report avoids unmeasured savings claims
  • In Gemini CLI, use /stats model or /stats session for live usage instead

What's inside

  • SKILL.md

Redistributed unmodified from JuliusBrussee/caveman under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.