model-usage

Name: model-usage
Availability: InStock
Author: 0xKobold

Summarize CodexBar local cost usage per model from JSON logs.

4|2|Updated Mar 16, 2026

Search Tags:#CLI #json #cost-analysis #per-model #model-usage #codexbar #local-logs

Ready to run

npx skills add https://github.com/0xKobold/0xkobolds --skill model-usage-0xkobold

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/0xKobold/0xkobolds/tree/main/skills/model-usage
Command: npx skills add https://github.com/0xKobold/0xkobolds --skill model-usage-0xkobold

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

CodexBar's local cost usage data can be scattered across sources, making it hard to quickly understand per-model costs for Codex or Claude.

Core Features & Use Cases

Per-model cost summaries: generate current-model or full-model breakdowns from CodexBar's local logs.
Flexible outputs: view results in plain text or JSON, suitable for dashboards or reports.
Use Case: quickly compare which models drive the majority of cost in a given period for cost-optimization or budgeting.

Quick Start

Fetch codexbar cost JSON (or pass a JSON file) and run the bundled script to summarize usage by model.

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 cost usage from CodexBar local logs?▼

To summarize per-model cost usage from CodexBar local logs, you can run the bundled script with a fetched JSON log file. The script aggregates daily model breakdowns and exposes both current-model and all-model views via CLI flags.

Can I filter CodexBar cost analysis by date and output JSON?▼

Yes, you can filter CodexBar cost analysis by date and output JSON. The script supports optional date filtering and allows you to choose between plain text or JSON outputs, making it suitable for dashboards or reports.

Does this tool support both Codex and Claude usage data for cost reporting?▼

Yes, the tool supports both Codex and Claude usage data for cost reporting. It reads daily model breakdowns from the local JSON logs and applies the aggregation logic to generate per-model cost summaries for both.

What is the best way to compare which models drive the majority of my API costs?▼

The best way to compare which models drive the majority of your API costs is to generate a full per-model breakdown. This Skill aggregates costs per model from local logs, allowing you to quickly identify high-cost models for budgeting.

Do I need any external dependencies to run the per-model usage summarizer?▼

No, you do not need any external dependencies to run the per-model usage summarizer. The Skill has no dependencies and operates locally by reading the JSON logs provided to the bundled script.