model-usage

Summarize AI model usage and costs from local CodexBar logs.

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

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 (Codex, Claude) by summarizing their usage from local logs.

Core Features & Use Cases

  • Per-Model Cost Summary: Get a breakdown of costs for each AI model used.
  • Current Model Identification: Identify the most recently used or most expensive model in the latest log entry.
  • Historical Usage: View total costs across all models or for specific models over time.
  • Use Case: A developer wants to optimize their AI spending. They use this Skill to see which models are consuming the most budget and identify opportunities for cost savings.

Quick Start

Run the following command to get a summary of all Codex model costs from your local logs.

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 usage and costs for Codex and Claude?

You can track AI model usage and costs by summarizing local CodexBar logs, which provides a per-model cost breakdown for Codex and Claude providers to help you monitor spending.

What is the best way to get a per-model cost breakdown from local logs?

The best way to get a per-model cost breakdown is to analyze the JSON data from local CodexBar logs, which summarizes current or all model usage and supports text or JSON output formats.

Do I need codexbar CLI installed to monitor AI spending?

Yes, you need the codexbar CLI installed and accessible in your system's PATH to parse local logs and summarize AI model usage and costs.

Can I identify my most expensive or most recently used AI model in logs?

Yes, you can identify the most recently used or most expensive model by analyzing the latest log entry from your local CodexBar JSON data.

How do I view historical AI usage costs across all models over time?

You can view historical AI usage costs by analyzing all model breakdowns from your local CodexBar logs, allowing you to see total costs across specific models over time.

Does AI cost monitoring support JSON output formats for log analysis?

Yes, AI cost monitoring supports both text and JSON output formats when summarizing model usage and costs from local CodexBar logs.