model-usage

Summarize local cost usage per AI model from CodexBar logs.

386k|81.1k|Updated Nov 24, 2025
One-click install
npx skills add https://github.com/openclaw/openclaw --skill model-usage-openclaw
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/openclaw/openclaw/tree/main/skills/model-usage
Command: npx skills add https://github.com/openclaw/openclaw --skill model-usage-openclaw

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill helps you understand and manage your AI model expenses by providing detailed local cost usage summaries for specific models.

Core Features & Use Cases

  • Per-Model Cost Summaries: Get a breakdown of costs associated with individual AI models (Codex or Claude).
  • Current Model Focus: Easily identify the cost of the most recently used model.
  • Historical Analysis: View usage 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 script to see a summary of costs for all models used by 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 for Codex and Claude locally?

You can track AI model costs locally by running this Skill to summarize cost usage per model from CodexBar logs. It analyzes current or all model usage for Codex and Claude providers, outputting the results as text or JSON.

Do I need CodexBar installed to analyze my AI model usage?

Yes, you need the CodexBar CLI installed and accessible in your system's PATH. The Skill parses local CodexBar logs to generate per-model cost summaries, so the CLI must be present to provide the source data.

Can I get a cost breakdown for individual AI models like gpt-4 or claude-3-opus?

Yes, this Skill provides per-model cost summaries, allowing you to get a detailed breakdown of costs associated with individual AI models. This helps you compare expenses across different models to optimize your AI budget.

What is the best way to view historical AI cost usage across all models?

The best way to view historical AI cost usage is to run the model usage script for all models. It analyzes usage over time from CodexBar logs, outputting a comprehensive cost summary for every model used.

How do I check the cost of the most recently used AI model?

You can check the cost of the most recently used AI model by requesting a current model focus summary. The Skill analyzes CodexBar logs to easily identify and output the costs associated with the latest active model.

Can I export AI cost analysis data as JSON?

Yes, the Skill can output AI cost analysis data as JSON. When you run the script to summarize local cost usage per AI model, you can select JSON as the output format for structured data integration.