model-usage

Summarize per-model costs from CodexBar JSON logs.

4|2|Updated Feb 26, 2026
One-click install
npx skills add https://github.com/Clawdi-AI/openclaw --skill model-usage-clawdi-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/Clawdi-AI/openclaw/tree/main/skills/model-usage
Command: npx skills add https://github.com/Clawdi-AI/openclaw --skill model-usage-clawdi-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill helps you understand and manage the costs associated with using different AI models by summarizing usage data from CodexBar.

Core Features & Use Cases

  • Per-Model Cost Summary: Get a breakdown of costs for individual AI models (Codex, Claude).
  • Current Model Focus: Easily identify the most used or most expensive model for the current period.
  • Historical Analysis: View total costs across all models over time.
  • Use Case: A developer wants to know how much they spent on GPT-4 versus Claude 3 Opus last month to optimize their AI budget.

Quick Start

Run the model-usage skill to see the current model's cost breakdown for Codex.

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 from CodexBar logs?

To track AI model costs, this Skill parses CodexBar cost JSON output to summarize local usage expenses for Codex and Claude models. It provides a detailed breakdown to help you analyze spending and optimize your budget.

Can I get a cost breakdown for individual models like Claude and Codex?

Yes, you can get a per-model cost breakdown for Claude and Codex. The Skill summarizes local usage data to show expenses for individual models, helping you compare costs across different AI services.

What is the best way to analyze historical AI expenses across all models?

The best way to analyze historical AI expenses is by viewing total costs across all models over time. The Skill processes CodexBar JSON logs to deliver a comprehensive historical analysis of your spending.

How do I identify the most expensive AI model for the current period?

To identify the most expensive AI model for the current period, run the Skill to focus on current model costs. It evaluates CodexBar logs to highlight your highest-spending models during the active cycle.

Does this cost tracking method require any specific dependencies?

No specific dependencies are required to track costs. The Skill operates independently using scripts and references to parse existing CodexBar JSON output for your AI budget analysis.

Why do I need to parse CodexBar JSON output for budget optimization?

You need to parse CodexBar JSON output to extract accurate cost metrics for budget optimization. This process transforms raw local usage logs into structured per-model summaries, enabling precise expense tracking.