model-usage

Summarize local AI model costs from CodexBar logs in text or JSON.

67|24|Updated Jan 31, 2026
One-click install
npx skills add https://github.com/openxjarvis/openclaw-python --skill model-usage-openxjarvis
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/openxjarvis/openclaw-python/tree/main/skills/model-usage
Command: npx skills add https://github.com/openxjarvis/openclaw-python --skill model-usage-openxjarvis

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 different AI models by summarizing usage data from CodexBar.

Core Features & Use Cases

  • Per-Model Cost Summary: View the cost breakdown for individual AI models (Codex, Claude).
  • Current Model Usage: Identify the most recently used model and its associated costs.
  • Historical Data: Analyze usage trends over time by summarizing all models or specific timeframes.
  • Use Case: A developer needs to report on the cost distribution of AI models used in a project. They can use this Skill to generate a clear summary of which models are consuming the most budget.

Quick Start

Run the model_usage 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 logs?

To track AI model costs, this Skill summarizes local cost usage per model from CodexBar logs, analyzing current or all-model usage for Codex and Claude providers. It generates a clear cost breakdown for your AI budget.

Do I need CodexBar installed to summarize Claude and Codex usage?

Yes, you need the CodexBar CLI installed and accessible in your system's PATH to summarize Claude and Codex usage. The Skill parses local logs generated by the CodexBar CLI to extract cost data.

Can I get AI billing data in JSON format for Codex and Claude models?

Yes, you can get AI billing data in JSON format. The Skill supports both text and JSON output formats, allowing you to easily integrate the summarized cost usage data into automated reports or scripts.

What is the best way to report on the cost distribution of AI models used in a project?

The best way to report on the cost distribution of AI models is using this Skill to summarize historical data. It analyzes usage trends over time, showing which models consume the most budget from your logs.

How do I identify the most recently used AI model and its associated costs?

You identify the most recently used AI model and its costs by analyzing current model usage. The Skill reads CodexBar logs to pinpoint the active model and summarize its specific billing details.