model-usage

Summarize per-model AI costs from CodexBar logs.

Updated Mar 10, 2026
One-click install
npx skills add https://github.com/JiayueMeng128/OpenClaw2Androidtrying --skill model-usage-jiayuemeng128
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/JiayueMeng128/OpenClaw2Androidtrying/tree/main/openclaw/skills/model-usage
Command: npx skills add https://github.com/JiayueMeng128/OpenClaw2Androidtrying --skill model-usage-jiayuemeng128

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires codexbar, and 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 costs associated with different models.

Core Features & Use Cases

  • Per-Model Cost Summary: View the total cost incurred by each AI model used.
  • Current Model Focus: Identify the most recent or most expensive model in the latest usage data.
  • Data Input Flexibility: Accepts data directly from the CodexBar CLI or from a JSON file.
  • 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 all model costs for the codex provider.

Frequently Asked Questions about model-usage

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

FAQPage Schema
How do I summarize AI model costs per provider from local logs?

You can summarize AI model costs by running the model_usage script, which reads CodexBar local logs and provides per-model cost breakdowns for specified providers like Codex or Claude. It outputs the total cost incurred by each model used.

What is the best way to compare AI model usage costs between different models?

To compare AI model usage costs, the Skill generates a per-model breakdown from your CodexBar data, allowing you to see expenses side-by-side for models like gpt-4 versus claude-3-opus to help optimize your AI budget.

Does this AI cost analysis tool require CodexBar to be installed?

Yes, this AI cost analysis requires the CodexBar CLI to be installed and accessible on your system's PATH to read the local logs needed for generating per-model cost summaries.

Can I get AI model cost summaries in JSON format instead of text?

Yes, you can get AI model cost summaries in JSON format. The Skill offers options for both text and JSON output formats to integrate with your existing developer tools and billing analysis workflows.

How do I find the cost of the current or most recent AI model I used?

To find the cost of the current or most recent AI model, the Skill supports identifying the current or most expensive model in your latest usage data directly from the CodexBar logs.