caveman-stats

Track real-time token usage and savings from Claude Code session logs.

1|Updated Aug 16, 2023
One-click install
npx skills add https://github.com/monlor/dotfiles --skill caveman-stats-monlor
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: caveman-stats
Source: https://github.com/monlor/dotfiles/tree/main/config/ai/agents/skills/caveman-stats
Command: npx skills add https://github.com/monlor/dotfiles --skill caveman-stats-monlor

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The caveman-stats skill addresses the need for accurate tracking of token usage and savings in Claude Code sessions, providing real data without estimation.

Core Features & Use Cases

  • Real Token Tracking: Provides actual input/output token usage statistics from the Claude Code session log.
  • Estimated Savings: Reports the estimated savings versus a non-caveman baseline, directly from the session log.
  • Immediate Output: Integrates with the caveman-mode-tracker hook to display the stats immediately after the /caveman-stats command is used.

Quick Start

/caveman-stats

Frequently Asked Questions about caveman-stats

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I track real token usage in Claude Code sessions?

You can track real token usage in Claude Code sessions by using a skill that analyzes session logs to provide actual input and output token statistics, requiring integration with the caveman-mode-tracker hook.

Can I view estimated token savings for my Claude Code sessions?

Yes, you can view estimated token savings by analyzing your session logs. The system calculates and reports your savings versus a non-caveman baseline directly from the log data.

How do I get immediate token analytics after a Claude Code session?

To get immediate token analytics, you can run the /caveman-stats command. It integrates with the caveman-mode-tracker hook to display real-time token usage and savings statistics instantly.

Do I need direct access to session logs to track Claude Code token usage?

Yes, direct access to session logs is required. The tracking mechanism parses these logs to extract actual token usage data and calculate estimated savings without relying on estimations.

What is the difference between real token tracking and estimated token usage?

Real token tracking extracts actual input and output token counts directly from the Claude Code session log, whereas estimated usage relies on projections rather than parsing the raw log data.

How does the caveman-mode-tracker hook work with session analytics?

The caveman-mode-tracker hook works by integrating with the session log analysis to trigger immediate output. When the /caveman-stats command runs, it displays the token statistics right away.