caveman-stats

Analyze Claude Code JSONL session logs to calculate token usage and cost savings.

2|Updated Apr 16, 2026
One-click install
npx skills add https://github.com/AlbertLin821/AIYO_new --skill caveman-stats-albertlin821
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: caveman-stats
Source: https://github.com/AlbertLin821/AIYO_new/tree/main/.agents/skills/caveman-stats
Command: npx skills add https://github.com/AlbertLin821/AIYO_new --skill caveman-stats-albertlin821

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill provides transparent, accurate reporting of token consumption and cost savings for Claude Code sessions, eliminating the guesswork associated with AI-generated usage estimates.

Core Features & Use Cases

  • Direct Log Analysis: Reads raw JSONL session logs to report exact input and output token counts.
  • Savings Calculation: Computes the difference between actual usage and estimated baseline usage to quantify efficiency gains.
  • Use Case: Developers can use this to monitor the cost-effectiveness of their coding sessions and track the cumulative impact of using the caveman-mode-tracker.

Quick Start

Type the slash command caveman-stats into the chat interface to display your current session token usage and estimated savings.

Frequently Asked Questions about caveman-stats

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

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

Token usage and cost tracking in Claude Code sessions is done by analyzing raw JSONL session log files to calculate exact input and output token counts. This eliminates the need for model-based estimations.

How do I calculate token savings for AI-assisted development workflows?

Token savings for AI-assisted development workflows are calculated by computing the difference between actual usage and estimated baseline usage. This quantifies efficiency gains and tracks cost-effectiveness.

Does caveman-stats require direct access to session log files?

Yes, caveman-stats requires direct access to local JSONL session log files to ensure data accuracy. This approach bypasses model-based estimations by reading raw session data.

How do I monitor the cost-effectiveness of my coding sessions?

You can monitor the cost-effectiveness of coding sessions by using a slash command to analyze session logs. This displays current token consumption and estimated savings in real-time.

What is the difference between direct log analysis and model-based token estimation?

Direct log analysis reads raw JSONL session logs to report exact token counts, whereas model-based token estimation uses approximations. Direct analysis provides transparent and accurate reporting.