model-usage

Summarize local AI model costs from CodexBar CLI logs.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/clsdavid/autocrab --skill model-usage-clsdavid
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/clsdavid/autocrab/tree/main/skills/model-usage
Command: npx skills add https://github.com/clsdavid/autocrab --skill model-usage-clsdavid

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps users understand and manage their AI model expenses by providing detailed breakdowns of usage and cost data from the CodexBar CLI.

Core Features & Use Cases

  • Per-Model Cost Summary: Generates reports on how much each AI model (Codex, Claude) is costing.
  • Current Model Analysis: Identifies the most recently used or most expensive model for a given day.
  • Historical Data: Can summarize usage over specified recent periods or provide a full historical breakdown.
  • Use Case: A developer wants to see which AI models are consuming the most budget this month. They can use this Skill to get a clear, model-by-model cost report.

Quick Start

Run the model_usage.py script to get a summary of Codex model costs for the current day.

Frequently Asked Questions about model-usage

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

FAQPage Schema
How do I track AI model costs and usage from CodexBar CLI logs?

By analyzing local CodexBar CLI logs, this Skill generates per-model cost summaries for AI providers like Codex and Claude. It identifies your most recently used or expensive models and provides historical breakdowns over specified date ranges.

Can I get a per-model cost breakdown for specific date ranges?

Yes, you can generate per-model cost breakdowns for specific date ranges. The Skill analyzes historical provider data from CodexBar logs, allowing you to filter usage and expenses by custom periods or focus on the most recent current model activity.

Does the AI cost analysis support both Codex and Claude provider data?

Yes, the AI cost analysis supports both Codex and Claude provider data. It parses local CLI logs from both providers to generate detailed per-model usage reports, helping you manage expenses across different platforms.

What is the best way to export AI model usage reports in JSON format?

The best way to export AI model usage reports in JSON format is to use the Skill's built-in output options. You can run the analysis script to generate per-model cost summaries and explicitly select JSON instead of standard text output.

Why do I need CodexBar CLI logs to analyze AI expenses?

You need CodexBar CLI logs because the Skill parses this local usage data as its primary input source. Without these logs, the script cannot extract the per-model cost and usage information required to generate your expense breakdowns.