model-usage

Summarize per-model cost usage data from CodexBar logs.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/fame0528/Savant-dead --skill model-usage-fame0528
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/fame0528/Savant-dead/tree/main/skills/model-usage
Command: npx skills add https://github.com/fame0528/Savant-dead --skill model-usage-fame0528

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 by providing detailed usage summaries from local logs.

Core Features & Use Cases

  • Per-Model Cost Summaries: Get a breakdown of expenses for specific AI models (Codex, Claude).
  • Current Model Focus: Identify the most recently used model and its associated costs.
  • Historical Analysis: View usage data for all models over a specified period.
  • Use Case: Developers and project managers can use this to monitor API spending, optimize model selection, and allocate budgets more effectively.

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 from local CLI logs?

You can track AI model costs by summarizing local usage data per model directly from CodexBar logs. This process analyzes current or historical expenses for Codex and Claude providers to help you monitor API spending.

What is the best way to analyze per-model API expenses for Codex and Claude?

The best way to analyze per-model API expenses is to parse local cost usage data from CodexBar logs. This provides a detailed breakdown of current and historical spending for Codex and Claude models.

Do I need CodexBar installed to analyze historical AI model usage data?

Yes, you need the CodexBar CLI installed and properly configured for local cost tracking. The tool depends entirely on CodexBar logs to summarize and analyze historical per-model usage data.

Can I identify my most recently used AI model and its associated costs?

Yes, you can identify your most recently used AI model and its associated costs. The tool focuses on current model usage by parsing local logs to highlight the latest active model and its expenses.

What limitations exist when monitoring API spending with local log analysis?

A key limitation is that cost tracking is restricted to data available in local CodexBar logs. It cannot analyze expenses for AI providers or models unless they are explicitly logged by the CodexBar CLI.

How do I get a breakdown of expenses for all AI models over a specific period?

You can get a breakdown of expenses over a specific period by running the model usage script to parse historical data. This summarizes all per-model usage records logged by CodexBar within that timeframe.