model-usage

Summarizes AI model usage and cost data from the CodexBar CLI per model.

3|Updated Feb 26, 2026

Search Tags:#ai #llm #billing #usage #cost #codexbar

Ready to run

npx skills add https://github.com/ybsa/sovereign-kernel --skill model-usage-ybsa

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/ybsa/sovereign-kernel/tree/main/crates/sk-tools/skills/model-usage
Command: npx skills add https://github.com/ybsa/sovereign-kernel --skill model-usage-ybsa

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 spending on AI models by providing detailed usage and cost summaries from the CodexBar CLI.

Core Features & Use Cases

Per-Model Cost Summaries: Get a breakdown of costs for individual AI models (Codex, Claude).
Current vs. All Models: View usage for the most recent session or a comprehensive history.
Flexible Input: Accepts direct CLI output or a JSON file as input.
Use Case: A developer wants to optimize their AI API budget. They use this Skill to identify which models are consuming the most resources, allowing them to adjust their usage or explore more cost-effective alternatives.

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?▼

Track AI model costs by summarizing usage and cost data locally through the CodexBar CLI. The script provides per-model cost breakdowns for specified providers like Codex or Claude from either current session or historical aggregation.

Can I view historical AI usage and cost data instead of just the current session?▼

Yes, you can view historical AI usage data. The Skill supports both current session summaries and comprehensive historical aggregation, allowing you to analyze total costs across all models over time.

Do I need the CodexBar CLI installed to get per-model cost breakdowns?▼

Yes, the CodexBar CLI must be installed and accessible in your environment to get per-model cost breakdowns. The Skill relies on this CLI to summarize AI usage and cost data locally.

What is the best way to analyze an AI API budget and identify high-cost models?▼

The best way to analyze an AI API budget is to use a cost summarization script to identify which models are consuming the most resources. This allows you to adjust usage or explore more cost-effective alternatives.

Can I use a JSON file as input for AI usage and cost summaries?▼

Yes, you can use a JSON file as input for AI usage and cost summaries. The Skill accepts flexible input formats, allowing you to pass either direct CLI output or a JSON file to process the data.