model-usage

Summarize local AI model costs using the CodexBar CLI.

Updated Jan 20, 2026
One-click install
npx skills add https://github.com/Team-Hireal/RealChat --skill model-usage-team-hireal
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/Team-Hireal/RealChat/tree/main/openclaw/skills/model-usage
Command: npx skills add https://github.com/Team-Hireal/RealChat --skill model-usage-team-hireal

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 AI models like Codex and Claude by providing detailed usage summaries.

Core Features & Use Cases

  • Per-Model Summaries: Get a breakdown of costs for each AI model used.
  • Current Model Focus: Easily identify the most recently used model and its associated costs.
  • Full Model Breakdown: View a comprehensive list of all models and their total costs.
  • Use Case: A developer needs to report on the cost implications of using different AI models for a project. This Skill can generate a report showing which models were used most and their respective expenses.

Quick Start

Run the model_usage script to get a summary of current 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 cost usage for Codex and Claude?

You can track AI model cost usage by running the model_usage script, which summarizes local cost data for models like Codex and Claude using the CodexBar CLI. It provides per-model cost breakdowns for your project reporting.

How do I get a per-model cost breakdown for all AI models used?

To get a per-model cost breakdown, run the model_usage script to generate a full model breakdown. This summarizes total costs across all configured AI models, outputting the comprehensive cost report in either text or JSON format.

Do I need CodexBar CLI installed to report AI billing costs?

Yes, you need the CodexBar CLI installed and properly configured for local cost logging to report AI billing costs. The Skill relies entirely on CodexBar to retrieve and summarize the local usage data for your models.

Can I output AI model usage reports in JSON format?

Yes, you can output AI model usage reports in JSON format. The Skill supports both text and JSON output formats, allowing you to easily integrate the current or all-model cost summaries into automated reporting pipelines.

What is the best way to identify the most recently used AI model and its cost?

The best way to identify the most recently used AI model and its cost is to use the current model focus feature. This generates a summary highlighting the latest active model and its specific associated expenses from your local logs.

Why are my AI model usage costs not showing up in the report?

AI model usage costs may not show up if the CodexBar CLI is not installed or configured for local cost logging. Ensure your environment is properly set up to capture local usage data for models like Codex and Claude before running the script.