model-usage

Summarize per-model usage and costs from CodexBar local JSON logs.

Updated Jan 28, 2026
One-click install
npx skills add https://github.com/tamireslaeao-prog/ONI_V30 --skill model-usage-tamireslaeao-prog
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/tamireslaeao-prog/ONI_V30/tree/main/moltbot-main/skills/model-usage
Command: npx skills add https://github.com/tamireslaeao-prog/ONI_V30 --skill model-usage-tamireslaeao-prog

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

Core Features & Use Cases

  • Per-model cost overview for CodexBar logs across Codex and Claude.
  • View the current model or a full per-model breakdown with optional time constraints.
  • Use Case: Review monthly per-model spend and identify dominance of a single model for optimization.

Quick Start

Run the bundled script to summarize per-model CodexBar costs by provider and mode using the included Python script.

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 usage costs from CodexBar local logs?

To summarize per-model usage costs from CodexBar local logs, run the bundled Python script against your local JSON logs. It parses daily cost entries and modelBreakdowns to compute totals, returning results in text or JSON formats.

What is the best way to get a per-model cost breakdown for Codex and Claude?

Getting a per-model cost breakdown for Codex and Claude involves parsing local CodexBar output to separate usage by provider. The script reads modelBreakdowns data to calculate and present distinct cost totals for each environment.

Can I view only the current model's usage instead of a full breakdown?

Yes, you can view only the current model's usage instead of a full breakdown. The script supports both current-model views and full per-model breakdowns, allowing you to isolate the most recent model's costs from the JSON logs.

Does the CodexBar cost analysis script work with missing JSON log data?

Yes, the CodexBar cost analysis script works with missing JSON log data by handling it gracefully. It parses available daily cost entries and modelBreakdowns without failing, ensuring you still get a usable per-model cost summary.

How do I identify which model is dominating my monthly spend?

To identify which model is dominating your monthly spend, generate a full per-model breakdown from your CodexBar logs. This review highlights cost distribution across Codex and Claude models to help pinpoint optimization opportunities.