model-usage

Summarize CodexBar JSONL cost logs for Codex and Claude providers.

Updated Jun 18, 2026
One-click install
npx skills add https://github.com/wangqianCAI/OBI --skill model-usage-wangqiancai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/wangqianCAI/OBI/tree/main/skills/model-usage
Command: npx skills add https://github.com/wangqianCAI/OBI --skill model-usage-wangqiancai

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill addresses the difficulty of tracking and summarizing local AI model usage costs, which are often buried in fragmented JSONL log files generated by CodexBar.

Core Features & Use Cases

  • Cost Aggregation: Automatically parses local cost logs to provide a clear breakdown of spending by model.
  • Flexible Reporting: Supports both current model snapshots and comprehensive historical summaries for Codex and Claude providers.
  • Use Case: A developer can use this tool to generate a monthly report of their AI API spending, identifying which specific models are consuming the most budget.

Quick Start

Use the model-usage skill to summarize all model costs for the Claude provider in JSON format.

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 AI model cost logs from CodexBar?

To summarize local AI model cost logs, this Skill parses JSONL files generated by CodexBar to aggregate token and cost data. It provides granular spending insights by parsing these local logs to show exactly how much budget specific AI providers consume.

Can I generate a spending breakdown for specific AI providers like Claude and Codex?

Yes, you can generate a spending breakdown for specific AI providers like Claude and Codex. The Skill operates on local JSONL log files to aggregate token usage and cost data, supporting both current model snapshots and comprehensive historical summaries.

What is the best way to track API spending per model from JSONL files?

Tracking API spending per model from JSONL files involves automatically parsing the local cost logs to provide a clear breakdown. This approach aggregates token and cost data, allowing developers to identify which specific models are consuming the most budget.

Do I need Python 3 and CodexBar installed to analyze AI usage costs?

Yes, you need Python 3 and the CodexBar CLI installed to analyze AI usage costs. The Skill requires the CodexBar CLI to be installed and accessible in the system environment to parse the JSONL log files and generate the cost reports.

How does aggregating token and cost data help with budget monitoring?

Aggregating token and cost data helps with budget monitoring by transforming fragmented JSONL log files into clear spending insights. This allows developers to generate monthly reports of their AI API spending and identify exactly which models are consuming the most budget.