model-usage

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

5|Updated Apr 8, 2026
One-click install
npx skills add https://github.com/JansenAnalytics/claudex --skill model-usage-jansenanalytics
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/JansenAnalytics/claudex/tree/main/skills/model-usage
Command: npx skills add https://github.com/JansenAnalytics/claudex --skill model-usage-jansenanalytics

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Quickly summarize per-model usage and costs from CodexBar’s local logs, giving you visibility into which models incur the most spend without needing external dashboards.

Core Features & Use Cases

  • Retrieve the current model's cost from CodexBar's logs, or generate an all-model breakdown for budgeting and optimization.
  • Produce human-readable summaries or machine-friendly JSON outputs for dashboards and automation.
  • Use cases include cost auditing, model-usage reporting, and automation hooks in CI or monitoring pipelines.

Quick Start

Run the bundled Python script to generate a per-model cost summary from CodexBar’s local cost log.

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 and costs from local CLI logs?

You can summarize per-model usage costs by running a bundled Python script that reads local JSON cost data or CLI output, formatting model-level summaries for reporting or automation.

What is the best way to generate a per-model cost breakdown for budgeting?

Generating a per-model cost breakdown involves parsing local CodexBar logs to produce a full-model breakdown, giving you visibility into which models incur the most spend without external dashboards.

Can I get machine-readable JSON outputs for cost auditing from local logs?

Yes, you can produce machine-friendly JSON outputs from local logs for cost auditing, model-usage reporting, and automation hooks in CI or monitoring pipelines.

Does this approach require external dashboards to monitor model costs?

No, it does not require external dashboards because the script reads local JSON cost data or CLI output directly to provide a concise, model-level summary suitable for reporting.

How do I retrieve the current model's cost from CodexBar logs?

To retrieve the current model's cost, you apply the script to CodexBar's local logs, which reads the cost data and formats results for downstream usage.