model-usage

Generate per-model cost summaries from CodexBar CLI or JSON data.

Updated May 28, 2026
One-click install
npx skills add https://github.com/susamn/skills --skill model-usage-susamn
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/susamn/skills/tree/main/model-usage
Command: npx skills add https://github.com/susamn/skills --skill model-usage-susamn

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Manually tracking per-model usage and cost data for Codex or Claude from CodexBar local logs is time-consuming and error-prone, especially when you need to identify your most frequently used model or total spend across all models.

Core Features & Use Cases

  • Per-Model Cost Summarization: Pulls cost data from CodexBar CLI or exported JSON files to generate accurate per-model usage and spend reports.
  • Flexible Summary Modes: Supports both "current model" (most recent highest-cost model) and "all models" full breakdown views for Codex or Claude providers.
  • Multiple Output Formats: Exports results as plain text for quick viewing or structured JSON for integration into billing dashboards and spreadsheets.
  • Use Case: For developers or teams using Codex or Claude for AI-assisted coding, this skill eliminates manual log parsing to quickly identify highest-spend models and track usage trends for budget optimization.

Quick Start

Request a summary of your current most expensive Codex model's cost from your local CodexBar logs, or ask for a full breakdown of all Claude model usage costs from an exported cost JSON file.

Frequently Asked Questions about model-usage

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I track per-model usage costs for Codex and Claude from CodexBar logs?

Per-model usage costs for Codex and Claude are tracked by parsing CodexBar local cost logs or exported JSON files to generate accurate spend summaries. This approach eliminates manual log parsing and identifies your highest-cost models.

What is the best way to get a per-model cost breakdown for AI services?

The best way to get a per-model cost breakdown is to script the extraction of cost data from CodexBar CLI output or exported JSON. This generates a full breakdown view of all models, avoiding the human error associated with manual tracking.

Can I export AI model usage summaries as JSON for billing dashboards?

Yes, you can export AI model usage summaries as structured JSON for integration into billing dashboards. This structured output allows automated ingestion of per-model cost data and usage metrics into spreadsheets or budget optimization reports.

Does CodexBar usage tracking support both current and historical model cost views?

Yes, CodexBar usage tracking supports both current model and all models views. The current model view summarizes your most recent highest-cost model, while the all models view provides a full breakdown of usage costs across Codex or Claude providers.

How do I identify my most expensive AI model for budget optimization?

You can identify your most expensive AI model for budget optimization by summarizing per-model usage costs from CodexBar logs. Requesting a current model summary instantly highlights your highest-spend model without manually parsing cost data.