model-usage

Summarize local AI model costs from CodexBar JSON logs.

3.1k|368|Updated Feb 26, 2026
One-click install
npx skills add https://github.com/openocta/openocta --skill model-usage-openocta
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/openocta/openocta/tree/main/src/embed/skills/model-usage
Command: npx skills add https://github.com/openocta/openocta --skill model-usage-openocta

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 a clear breakdown of costs associated with different models used by CodexBar.

Core Features & Use Cases

  • Per-Model Cost Summary: Generates reports detailing the cost incurred by each AI model (e.g., Codex, Claude).
  • Current Model Identification: Identifies the most recently used or most expensive model for a given day.
  • Data Input Flexibility: Accepts input directly from the codexbar cost command or from a JSON file.
  • Use Case: A developer wants to optimize their AI spending and needs to know which specific models are consuming the most budget. This Skill provides that granular insight.

Quick Start

Run the python script to get a summary of current model costs 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 usage logs?

To track AI model costs, you can run this Skill to summarize local cost usage from CodexBar logs. It processes inputs from the `codexbar cost --format json` command or a specified JSON file to output per-model cost breakdowns.

Can I get a cost breakdown by individual AI model for Codex and Claude?

Yes, you can get a comprehensive cost breakdown by AI model for Codex and Claude. The Skill processes your JSON usage logs to generate a detailed report of costs incurred by each specific model.

How do I identify the most expensive or recently used AI model for the day?

You can identify the most recently used or most expensive AI model for a given day by running the Skill. It analyzes your CodexBar cost logs to pinpoint the current model consuming your budget.

Does this cost analysis tool require a specific input format?

Yes, this cost analysis requires input from the `codexbar cost --format json` command or a specified JSON file. It processes this structured data to output results in either text or JSON format.

What is the best way to optimize AI spending using local usage logs?

The best way to optimize AI spending is to use this Skill for granular cost analysis. It provides a clear breakdown of expenses associated with different models used by CodexBar, helping you identify budget-consuming models.