model-usage

Summarize CodexBar local cost usage by model from JSON payloads.

Updated Mar 19, 2026
One-click install
npx skills add https://github.com/jason9693/Open-Jordy --skill model-usage-jason9693
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/jason9693/Open-Jordy/tree/main/openjordy/skills/model-usage
Command: npx skills add https://github.com/jason9693/Open-Jordy --skill model-usage-jason9693

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

CodexBar local cost data is often scattered across logs; this skill consolidates per-model usage and costs into a concise, actionable summary for budgeting and decision making.

Core Features & Use Cases

  • Per-model cost summaries: summarize costs by each model for current or all-time views across Codex and Claude.
  • Flexible inputs and views: generate current-model summaries or full-model breakdowns from local logs or a JSON payload, with optional date filtering.
  • Real-world use: quickly compare model-level spending to identify cost drivers and optimize usage in AI workflows.

Quick Start

Run the script to generate a per-model usage cost summary from 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 aggregate per-model AI usage costs from local logs?

To aggregate per-model AI usage costs from local logs, parse the JSON payload for modelBreakdowns and tally the costs per model. This consolidates scattered CodexBar data into a concise summary for budgeting.

Can I filter CodexBar cost summaries by a specific date range?

Yes, you can filter CodexBar cost summaries by a specific date range. The aggregation supports optional day-range filtering to narrow down current-model or full-model tallies across Codex and Claude.

What is the best way to compare spending between Codex and Claude models?

The best way to compare spending between Codex and Claude models is to generate a full-model breakdown. This aggregates local cost usage data per model, presenting a clear comparison to identify cost drivers.

Does this tool require a specific JSON payload format to parse model costs?

Yes, parsing model costs requires a JSON payload containing modelBreakdowns. The tool extracts and aggregates costs per model from this specific structure within your CodexBar local logs or direct input overrides.

Can I output the aggregated model usage data as JSON instead of text?

Yes, you can output the aggregated model usage data as JSON instead of text. The tool supports presenting the final per-model cost aggregation in either textual or JSON format according to your specified flags.