skills.rest
hummbl-dev
hummbl-devCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

model-usage

Summarize local AI model usage costs from CodexBar CLI output.

Updated Aug 23, 2026
Search Tags:#codex#claude#cost tracking#model usage#codexbar#ai cost
One-click install
npx skills add https://github.com/hummbl-dev/hummbl-agent --skill model-usage-hummbl-dev
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/hummbl-dev/hummbl-agent/tree/main/skills/model-usage
Command: npx skills add https://github.com/hummbl-dev/hummbl-agent --skill model-usage-hummbl-dev

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill helps users understand and track their local AI model usage costs for services like Codex and Claude, providing clear breakdowns by model.

Core Features & Use Cases

  • Per-Model Cost Summary: Generates summaries of usage costs broken down by individual AI models.
  • Current vs. All Models: Supports fetching the cost for the most recently used model or a comprehensive breakdown of all models used.
  • Use Case: A developer wants to see how much they spent on gpt-4 versus claude-3-opus yesterday using the CodexBar CLI.

Quick Start

Run the model_usage script to see a summary of all Claude model costs.

Frequently Asked Questions about model-usage

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

FAQPage Schema
How do I track AI model usage costs for Codex and Claude locally?▼

Track AI model usage costs by summarizing local output from the CodexBar CLI. This process provides a clear breakdown of usage costs for individual models like gpt-4 and claude-3-opus.

Can I get a per-model cost summary for all my AI providers?▼

Yes, you can generate a per-model cost summary. The tool analyzes all models used or fetches the cost for just the most recently used model based on your local CLI logs.

Do I need the codexbar CLI installed to analyze AI cost data?▼

Yes, the codexbar CLI must be installed and configured for local cost logging. This Skill parses the usage data directly from that CLI's output to generate cost breakdowns.

What output formats are supported when summarizing local model usage?▼

Text and JSON output formats are supported when summarizing local model usage. This allows you to either read the cost breakdown directly or parse it programmatically.

What is the best way to compare gpt-4 versus claude-3-opus spending?▼

The best way to compare spending is to run a comprehensive cost summary of all models. This analyzes your local CodexBar logs to show exactly how much you spent per provider.

Why does the model usage script return no data for my AI costs?▼

The model usage script returns no data if the codexbar CLI is not properly configured for local cost logging. Ensure the CLI is actively tracking your Codex and Claude usage before running summaries.

Related Skills

Explore More Software Engineering Skills→
me2Docme2Doc
6

model-usage

Parse CodexBar JSON logs to summarize local AI model costs.

Community
Intermediate
spoonbobospoonbobo

model-usage

Summarize per-model cost usage from CodexBar local cost logs.

Community
Intermediate
tedtv1007-ctrltedtv1007-ctrl

model-usage

Summarizes CodexBar CLI JSON logs for per-model usage and cost data.

Community
Intermediate
ZESCODEZESCODE

ZES-cost-tracker

Tracks API token consumption and spending across LLM providers in ZES.

Community
Basic