skills.rest
kaivyy
kaivyyCOMMUNITY
Explore all skills by this author →
GitHub

model-usage

Summarize per-model LLM costs from CodexBar CLI JSON output.

20|7|Updated Feb 11, 2026
Search Tags:#ai#llm#billing#usage#cost#codexbar
One-click install
npx skills add https://github.com/kaivyy/kabot --skill model-usage-kaivyy
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/kaivyy/kabot/tree/main/kabot/skills/model-usage
Command: npx skills add https://github.com/kaivyy/kabot --skill model-usage-kaivyy

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill helps users understand and manage their spending on different Large Language Models (LLMs) by analyzing local cost logs generated by the CodexBar CLI.

Core Features & Use Cases

  • Per-Model Cost Summary: Provides a breakdown of costs associated with individual LLMs (e.g., Codex, Claude).
  • Current Model Identification: Identifies the most recently used or most expensive model from the latest cost entry.
  • Historical Analysis: Allows for summarizing costs over the last N days.
  • Use Case: A developer wants to know how much they spent on gpt-4-turbo versus claude-3-opus last month. They can use this Skill to get a clear, model-specific cost report.

Quick Start

Run the model usage script to get a summary of all model costs for the codex provider.

Frequently Asked Questions about model-usage

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I summarize LLM cost usage from CodexBar CLI logs?▼

You can summarize LLM cost usage by running the script to parse local CodexBar CLI JSON output, generating a breakdown of expenses per model. It analyzes financial tracking data to show costs for individual models like Codex and Claude.

What is the best way to track spending per LLM model like Claude or Codex?▼

Tracking spending per LLM model is done by applying the script to your local cost logs to produce a per-model cost summary. It identifies the most recently used or most expensive model from the latest cost entry.

Can I analyze historical LLM expenses for the last N days using local logs?▼

Yes, you can analyze historical LLM expenses by summarizing costs over the last N days from your local JSON output. This allows for financial tracking and optimization of LLM expenses over specific time periods.

Do I need the codexbar CLI installed to monitor LLM API costs?▼

Yes, you need the codexbar CLI to be installed and configured for local cost logging before using this Skill. The script specifically parses the JSON output generated by the codexbar CLI.

How does the script identify the most expensive LLM I am using?▼

The script identifies the most expensive LLM by reading the latest cost entry from the local CodexBar JSON output. This current model identification helps you understand which model is driving your highest expenses.

What format does my LLM billing data need to be in for cost analysis?▼

Your LLM billing data needs to be in the local JSON output format generated by the CodexBar CLI. The script parses this specific JSON structure to provide a clear, model-specific cost report.

Related Skills

Explore More Software Engineering Skills→
darblexdarblex

model-usage

Summarize local AI model costs from CodexBar CLI logs.

Community
Intermediate
gonzalezpazmonicagonzalezpazmonica
47

cost-management

Log timesheets, track budgets, forecast costs, and generate invoices.

Community
Advanced
me2Docme2Doc
6

model-usage

Parse CodexBar JSON logs to summarize local AI model costs.

Community
Intermediate
sentientspritesentientsprite

model-usage

Summarize local AI model costs from CodexBar CLI logs.

Community
Intermediate