model-usage

Summarize local AI model cost usage from CodexBar CLI logs.

5.1k|1.2k|Updated Feb 23, 2026
One-click install
npx skills add https://github.com/linuxhsj/openclaw-zero-token --skill model-usage-linuxhsj
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/linuxhsj/openclaw-zero-token/tree/main/skills/model-usage
Command: npx skills add https://github.com/linuxhsj/openclaw-zero-token --skill model-usage-linuxhsj

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 costs by providing detailed, per-model usage summaries directly from local logs.

Core Features & Use Cases

  • Per-Model Cost Breakdown: Analyze spending for specific AI models (Codex, Claude).
  • Current vs. All Models: Get a summary of the most recently used model or a comprehensive breakdown of all models.
  • Use Case: A developer wants to see how much of their budget is being spent on GPT-4 versus Claude Sonnet for different tasks, using local cost data.

Quick Start

Run the model_usage script to get a summary of the current most expensive model 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 locally from my command line?

To track AI model costs locally, you can use this Skill to summarize per-model usage data parsed directly from your local CodexBar CLI logs. It provides a detailed expense breakdown for Codex and Claude providers.

Do I need CodexBar CLI installed to analyze per-model usage data?

Yes, you need the CodexBar CLI installed and configured for local cost logging to analyze per-model usage data. This Skill parses the local logs generated by the CLI to calculate expense breakdowns.

What's the best way to get a cost breakdown for specific AI models like Claude?

The best way to get a cost breakdown for specific AI models like Claude is to run the model usage script, which summarizes local cost logging data to show spending details per provider.

Can I compare expenses between current and all used AI models?

Yes, you can compare expenses by generating a summary of the most recently used model or requesting a comprehensive breakdown of all models to evaluate your spending distribution.

Why does the model usage script only support Codex and Claude providers?

The model usage script applies cost analysis specifically to Codex and Claude providers because it parses local cost logs structured by the CodexBar CLI for these specific AI models.

What is local AI cost tracking and when do I need it?

Local AI cost tracking is the process of summarizing expense data from local logs to manage your budget. You need it when you want to understand how much you are spending per AI model without using external cloud billing dashboards.