model-usage

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

14|5|Updated Mar 12, 2026
One-click install
npx skills add https://github.com/openclaw-easy/openclaw-easy-desktop --skill model-usage-openclaw-easy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/openclaw-easy/openclaw-easy-desktop/tree/main/openclaw/skills/model-usage
Command: npx skills add https://github.com/openclaw-easy/openclaw-easy-desktop --skill model-usage-openclaw-easy

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill provides a quick, local view of per-model usage and costs derived from CodexBar logs, helping you monitor AI spending without cloud access.

Core Features & Use Cases

  • Per-model cost summaries from CodexBar's local logs for Codex and Claude.
  • Current-model focus or full breakdown to support budgeting and optimization.
  • Automation-friendly outputs in text or JSON for dashboards and automation scripts.

Quick Start

Run the script to summarize per-model usage from your CodexBar local logs, choosing current-model focus or a full model breakdown.

Frequently Asked Questions about model-usage

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

FAQPage Schema
How do I track per-model AI usage and costs locally from CodexBar logs?

You can track per-model AI usage and costs locally by reading CodexBar's local JSONL log data. This skill summarizes expenses for Codex or Claude models, supporting budget tracking without cloud access.

Does this tool support summarizing costs for both Codex and Claude models?

Yes, it supports summarizing costs for both Codex and Claude models. It reads local JSONL cost data via CodexBar and can output either a current-model focus or a full per-model breakdown.

Can I get JSON output for automating per-model cost summaries in dashboards?

Yes, you can get JSON output for automating per-model cost summaries in dashboards. The skill outputs structured JSON or human-readable text from local logs for automation scripts.

What is the best way to view a complete per-model breakdown of AI spending?

The best way to view a complete per-model breakdown of AI spending is to run the script against CodexBar local logs, choosing the full model breakdown option for budget tracking and cost optimization.

Do I need cloud access to monitor my AI model usage and cost data?

No, you do not need cloud access to monitor your AI model usage and cost data. The skill provides a quick, local view of per-model usage and costs derived directly from CodexBar logs.