model-usage

Summarize Codex and Claude model usage costs from local JSON logs.

Updated Mar 31, 2026
One-click install
npx skills add https://github.com/nuno7lopes/alisio --skill model-usage-nuno7lopes
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/nuno7lopes/alisio/tree/main/skills/model-usage
Command: npx skills add https://github.com/nuno7lopes/alisio --skill model-usage-nuno7lopes

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires codexbar, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill simplifies the process of summarizing the usage costs of Codex or Claude models by extracting and analyzing data from local cost logs.

Core Features & Use Cases

  • Usage Cost Summary: Generate a summary of per-model usage costs.
  • Model-Level Usage/Cost Data: Triggered when needing specific model-level data or for scriptable summary generation.
  • Supports Multiple Models: Provides cost summaries for Codex and Claude models.

Quick Start

To get a summary of current model usage for Codex, use:

python scripts/model_usage.py --provider codex --mode current

Frequently Asked Questions about model-usage

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

FAQPage Schema
How do I summarize local usage costs for Claude and Codex models?

You can summarize local usage costs for Claude and Codex models by running a Python script that parses local cost logs and JSON data to generate a per-model usage cost summary.

What's the best way to extract per-model cost data from local logs?

The best way to extract per-model cost data is using a Python script that parses local JSON cost logs, providing a scriptable summary of usage costs for financial analysis and AI model monitoring.

Do I need the codexbar CLI to retrieve AI model cost data?

Yes, you need the codexbar CLI installed because the cost data retrieval and usage summary generation rely on a CodexBar-based workflow to access the local cost logs.

Can I check current usage costs for Codex models using a script?

Yes, you can check current usage costs for Codex models by executing the Python script with specific provider and mode arguments to retrieve and summarize the latest cost data.

Does this approach support generating cost summaries for multiple AI providers?

Yes, the approach supports generating cost summaries for multiple AI providers by accepting a provider argument, allowing you to extract and analyze usage costs for both Codex and Claude models.