model-usage

Identify per-model cost usage from CodexBar logs with optional date filtering.

Updated Feb 4, 2026
One-click install
npx skills add https://github.com/SennTse/openclaw-backup --skill model-usage-senntse
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/SennTse/openclaw-backup/tree/main/skills/model-usage
Command: npx skills add https://github.com/SennTse/openclaw-backup --skill model-usage-senntse

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

CodexBar logs local usage data and this skill provides per-model cost summaries for Codex and Claude, enabling quick visibility into which models drive spend and where optimization is possible.

Core Features & Use Cases

  • Per-model cost summaries: current-model selection and full model breakdowns to understand cost distribution.
  • Flexible inputs and outputs: reads local JSON logs or stdin and outputs text or JSON for seamless integration.
  • Use case: generate monthly per-model cost reports for leadership dashboards.

Quick Start

Use the included script to generate a per-model usage summary by supplying CodexBar cost data for the desired provider and mode.

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 CodexBar cost usage from local logs?

You can summarize per-model CodexBar cost usage by running the included script against local JSON logs or stdin input. It identifies per-model spend directly from local logs to show which models drive costs.

What is the best way to generate a monthly per-model cost report for Codex and Claude usage?

The best way to generate a monthly per-model cost report is to parse CodexBar logs with this skill, applying optional date filtering. It outputs a complete model-cost report in text or JSON format suitable for leadership dashboards.

Do I need the CodexBar CLI installed to analyze local model usage costs?

Yes, you need the CodexBar CLI installed to analyze local model usage costs. This skill requires the CodexBar CLI to access local logs and extract per-model cost data for current-model and all-model breakdowns.

Can I filter model cost summaries by specific dates when reading CodexBar logs?

Yes, you can filter model cost summaries by specific dates when reading CodexBar logs. This skill supports optional date filtering to narrow down the per-model cost usage data for both current-model and all-model breakdowns.

What output formats are supported for per-model cost summaries from CodexBar logs?

Supported output formats for per-model cost summaries include text and JSON. This allows you to output a concise current-model summary or a complete model-cost report for seamless integration into other systems.

Why does my per-model cost breakdown only show the current model instead of all models?

Your per-model cost breakdown only shows the current model because the skill defaults to a concise current-model summary. You can request a complete model-cost report to see the full all-model breakdown from your CodexBar logs.