Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

caveman-stats — Claude Code skill: what it does, how to install

Displays recorded output and cache-read tokens for Claude Code sessions or points to host native usage stats. Useful for tracking raw token consumption.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add JuliusBrussee/caveman --skill caveman-stats -a claude-code
Open on GitHub

What caveman-stats does

In Claude Code, running /caveman-stats triggers src/hooks/caveman-mode-tracker.js, which runs src/hooks/caveman-stats.js. The hook passes the usage report via hookSpecificOutput.additionalContext. The model prints it verbatim inside a code block without recalculating figures.

The report tracks output tokens, cache-read tokens, response counts, and active mode attribution. Caveman treats savings as unknown because transcripts lack baseline measurements without the tool. Flags like --all and --since 7d aggregate recent session counts, while --share exports observed usage. Historical estimated savings fields are ignored.

Gemini CLI prompts cannot read live session metrics, so the skill redirects users to /stats model or /stats session. Other environments fall back to native reports if present. Install this if you need honest token metrics without speculative savings badges.

What it helps with

  • inspect output and cache-read token counts for the active session
  • aggregate session token usage across the past week with --since 7d
  • route to native token stats commands in Gemini CLI
  • check mode attribution without speculative savings estimates

Example prompts for the agent

  • /caveman-stats
  • /caveman-stats --since 7d
  • /caveman-stats --share

How to install caveman-stats

1Skills CLI (Vercel)

npx skills add JuliusBrussee/caveman --skill caveman-stats -a claude-code

2Manually: put the files in place

~/.claude/skills/caveman-stats/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/caveman-stats/

From the same set22

The whole set →
caveman JuliusBrussee Cuts filler and polite greetings from agent responses while keeping technical facts and code exact. Stays active until turned off. Claude Code CX Codex Cursor +1 591,500installs caveman-commit JuliusBrussee Generates terse Conventional Commits messages focused strictly on intent. Ideal for keeping git history clean without boilerplate or AI signatures. Claude Code CX Codex Cursor +1 414,700installs caveman-review JuliusBrussee Generates terse, single-line code review comments with exact line numbers, problems, and fixes. Eliminates conversational filler in pull request reviews. Claude Code CX Codex Cursor +1 410,700installs caveman-compress JuliusBrussee Rewrites CLAUDE.md and todo files into terse caveman-speak so the model reads fewer input tokens. The source gets overwritten; a readable backup stays out of tree. Claude Code CX Codex Cursor +1 410,300installs caveman-help JuliusBrussee A quick reference for Caveman modes and commands in Claude Code and other supported hosts. Use it when you need to control response style or find related skills. Claude Code CX Codex Cursor +1 401,800installs cavecrew JuliusBrussee cavecrew delegates code searches, small edits, and diff reviews to three subagents. Use it when keeping the main agent's context lean matters. Claude Code CX Codex Cursor +1 357,900installs caveman-explore JuliusBrussee A read-only skill locates relevant files and line ranges in a repository. Use it for cold-start orientation or broad searches. Claude Code CX Codex Cursor +1 106,500installs caveman-learn JuliusBrussee This skill reads Caveman learn reports, proposes token-cost reductions, and asks for consent before each edit. Use it for heavy CLAUDE.md files or repeated context. Claude Code CX Codex Cursor +1 105,700installs

Similar

subagent-driven-development Jesse Vincent This skill runs an implementation plan through fresh subagents for independent tasks and reviews each result. Use it for multi-step work in one session. Claude Code CX Codex 237,746installs orchestration stablyai Coordinates supervised Orca workers with task DAGs, decision gates, and threaded messages. Fits workflows that split work across multiple agents. Claude Code CX Codex Cursor +1 349,200installs karpathy-guidelines multica-ai Guidelines that cut typical LLM coding mistakes: less overcomplication, surgical edits, verifiable outcomes. Claude Code CX Codex Cursor +1 42,500installs google-agents-cli-adk-code official Google A reference skill for building ADK agents with tools, callbacks, state, and workflows. Use it when an agent project needs concrete API patterns or code examples. Claude Code CX Codex Cursor +1 511,400installs google-agents-cli-deploy official Google Guides deploying AI agents to Agent Runtime, Cloud Run, or GKE with agents-cli. Helps configure CI/CD pipelines, manage secrets, and handle rollbacks. Claude Code CX Codex Cursor +1 510,700installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. Claude Code Claude.ai 414,180installs writing-for-agents Matt Pocock Guidance for writing skills and agent-facing documents. Use it when editing AGENTS.md, CLAUDE.md, or reference files reached from them. Claude Code 466,719installs media-use heygen-com Finds or generates media for HyperFrames videos, including voiceovers, music, cutouts, and color grades. Stores files locally in assets. Claude Code CX Codex Cursor +1 1,100,000installs

Questions about caveman-stats

How do I install caveman-stats in Claude Code?

Run npx skills add JuliusBrussee/caveman --skill caveman-stats -a claude-code in your terminal.

Does caveman-stats show money or token savings?

No. The skill deliberately reports savings as unknown because the transcript has no baseline run without Caveman to compare against.

How does caveman-stats behave in Gemini CLI?

Custom Gemini commands cannot read live session metrics. Instead, the skill instructs you to run /stats model or /stats session.

Source text

SKILL.md · Apache-2.0 
---
name: caveman-stats
description: >
  Show recorded output and cache-read token usage and mode attribution for
  the current Claude Code session, or locate the host's native usage report.
  Trigger: /caveman-stats.
---

In Claude Code, `src/hooks/caveman-mode-tracker.js` resolves `src/hooks/caveman-stats.js` next to itself and runs it on `/caveman-stats`. The hook does not block the prompt: it supplies the report through `hookSpecificOutput.additionalContext` with an instruction to print it verbatim inside a fenced code block. Do exactly that, and do not calculate, recompute or re-round the numbers yourself.

In Gemini CLI, direct the user to `/stats model` for current session token usage or `/stats session` for session statistics. Gemini custom commands are prompts; they cannot invoke the built-in command or read its live session metrics. Never read Claude Code transcripts as Gemini usage. In other hosts, use a native usage report if one is available; otherwise say that current session usage is unavailable. The Claude reader and its lifetime history apply only to Claude Code. Savings remain unknown in every host without a measured comparison.

The report shows recorded output and cache-read tokens, response counts, and mode attribution where available. Savings are unknown: the transcript has no measured comparison without Caveman. Do not infer saved tokens, percentages, dollars, rule overhead, or a net result from output counts or the current mode.

`--all` and `--since 7d` aggregate the latest recorded output count per session. `--share` reports observed usage with savings unknown. Historical `est_saved_*` fields are ignored; their original history rows remain on disk. The statusline shows the active mode without the retired savings badge.

Original/current memory-file pairs are reported by their measured byte sizes. Those file-size differences do not establish provider token or billing savings. See `docs/HONEST-NUMBERS.md`.

© JuliusBrussee · Apache-2.0 · JuliusBrussee/caveman

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor