model-usage

Summarize per-model CodexBar costs from local JSON logs or live CLI data.

2|Updated Feb 15, 2026
One-click install
npx skills add https://github.com/mmcmedia/openclaw-agents --skill model-usage-mmcmedia
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/mmcmedia/openclaw-agents/tree/main/skills/model-usage
Command: npx skills add https://github.com/mmcmedia/openclaw-agents --skill model-usage-mmcmedia

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Identify and summarize costs by AI model from CodexBar's local cost logs to understand which models drive the highest usage and expense.

Core Features & Use Cases

  • Local cost aggregation: parse CodexBar's JSON logs to produce per-model cost summaries.
  • Current vs all-model views: view the current top-cost model or an overall model cost breakdown.
  • Flexible inputs: support file-based JSON or live data via CodexBar CLI.

Quick Start

Run the included script to output a per-model cost summary from your local CodexBar logs.

Frequently Asked Questions about model-usage

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

FAQPage Schema
How do I summarize per-model AI costs from local CodexBar logs?

To summarize per-model AI costs from local CodexBar logs, use the included script to parse JSON log files and output a per-model cost breakdown. This aggregates daily usage data to show which models drive the highest expenses.

Can I aggregate Codex and Claude usage spending using live CLI data instead of files?

Yes, you can aggregate Codex and Claude usage spending using live CLI data. The tool supports flexible inputs, allowing you to parse either file-based JSON logs or live data via the CodexBar CLI to generate per-model totals.

What is the best way to track which AI model drives the highest expense in my logs?

The best way to track which AI model drives the highest expense is to use this tool to aggregate local cost logs. It identifies and summarizes costs by AI model, providing an overall model cost breakdown to pinpoint your top spending areas.

Does the model-usage script output data in JSON format or just text?

The script outputs data in both JSON and text formats. After parsing your CodexBar logs, it can output per-model totals in either format, allowing you to integrate the cost summaries into other analytics workflows or read them directly.

Do I need any external dependencies to parse CodexBar JSON logs for cost aggregation?

You do not need any external dependencies to parse CodexBar JSON logs for cost aggregation. The tool operates locally using the included scripts and references without requiring additional packages or external API connections.