model-usage

Summarize local AI model usage costs from CodexBar CLI output.

3|1|Updated Feb 23, 2026
One-click install
npx skills add https://github.com/SeanHogg/coderClaw --skill model-usage-seanhogg
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/SeanHogg/coderClaw/tree/main/product/skills/model-usage
Command: npx skills add https://github.com/SeanHogg/coderClaw --skill model-usage-seanhogg

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 (Codex, Claude) by providing a clear breakdown of usage and expenses based on local logs.

Core Features & Use Cases

  • Per-Model Cost Summary: Get a detailed breakdown of costs for each AI model used.
  • Current Model Identification: Automatically identify the most recently used model and its associated costs.
  • Data Input Flexibility: Accepts input directly from the CodexBar CLI or from a JSON file.
  • Use Case: Monitor your spending on different LLMs to optimize your AI budget and identify which models are most cost-effective for your tasks.

Quick Start

Run the model_usage script to get a summary of all Codex model costs.

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 a script that summarizes usage expenses from CodexBar CLI output. This provides a clear breakdown of costs for Codex and Claude models based on your local logs.

What is needed to summarize LLM usage from CodexBar?

To summarize LLM usage, you need the CodexBar CLI installed and accessible in your system's PATH. The tool processes output directly from the CLI or accepts a JSON file as input.

Can I output a per-model cost breakdown in JSON format?

Yes, you can output a per-model cost breakdown in JSON format. The tool analyzes current or all model breakdowns and supports both text and JSON output formats.

How do I identify my most recently used AI model and its expenses?

You can identify your most recently used AI model and its expenses by requesting a current model breakdown. The tool automatically identifies the latest model used and summarizes its associated costs.

Does this tool work without an internet connection to analyze AI costs?

Yes, this tool analyzes AI costs locally without an internet connection. It parses local usage logs generated by the CodexBar CLI to calculate expenses for models like Codex and Claude.