model-usage

Analyze CodexBar local JSON logs to derive per-model usage costs.

Updated Feb 1, 2026
One-click install
npx skills add https://github.com/Sugamdeol/moltbot-with-pollinations.ai --skill model-usage-sugamdeol
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/Sugamdeol/moltbot-with-pollinations.ai/tree/main/skills/model-usage
Command: npx skills add https://github.com/Sugamdeol/moltbot-with-pollinations.ai --skill model-usage-sugamdeol

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Quickly understanding per-model costs from CodexBar local logs to enable cost-aware decisions.

Core Features & Use Cases

  • Current-model summary: identify the most expensive model in the latest daily entry.
  • All-model breakdown: aggregate costs by model across a chosen period for budgeting and optimization.
  • Output formats: generate human-readable text or JSON for dashboards and reports.

Quick Start

Run the bundled script to generate a per-model cost report 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 analyze per-model costs from local CodexBar logs?

To analyze per-model costs from local CodexBar logs, you can run a bundled script that reads local JSON-formatted daily entries for Codex and Claude. It processes these daily entries to derive per-model usage costs and generates a summary report.

How do I get a cost breakdown for all models across a specific period?

To get a cost breakdown for all models across a specific period, you can use the all-model breakdown feature. It aggregates costs by model across your chosen timeframe, reading from local JSON daily entries to support budgeting and optimization.

Can I export model usage cost reports as JSON for dashboards?

Yes, you can export model usage cost reports as JSON. The script supports both human-readable text and JSON output formats, allowing you to easily integrate the aggregated cost data into external dashboards and reporting systems.

Do I need the CodexBar CLI installed to analyze local usage logs?

Yes, you need the CodexBar CLI installed to analyze local usage logs. The script requires CodexBar CLI to be present in your environment so it can read the local JSON data and generate the per-model cost summaries.

What is the best way to find the most expensive model in my latest daily logs?

The best way to find the most expensive model in your latest daily logs is to use the current-model summary feature. It identifies the highest cost model from the most recent daily entry by analyzing your local CodexBar JSON logs.