model-usage

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

Updated Apr 21, 2026
One-click install
npx skills add https://github.com/wuv-dreamguide/openclaw --skill model-usage-wuv-dreamguide
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/wuv-dreamguide/openclaw/tree/main/skills/model-usage
Command: npx skills add https://github.com/wuv-dreamguide/openclaw --skill model-usage-wuv-dreamguide

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Quickly understand how CodexBar usage translates into per-model costs by aggregating local cost logs, enabling cost-awareness and better budgeting for AI workloads.

Core Features & Use Cases

  • Current-model snapshot: identify the most expensive active model from the latest daily entry.
  • All-model breakdown: aggregate costs per model across a chosen time window.
  • Flexible outputs: present results as human-friendly text or machine-readable JSON for automation.

Quick Start

Run the model-usage script with your codexbar cost JSON to obtain a per-model cost summary.

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 costs from CodexBar logs?

You can aggregate per-model costs from CodexBar logs by running the model-usage script with your local JSON input. It parses modelBreakdowns from daily entries, identifies the current active model, and outputs a formatted cost summary as plain text or JSON.

What is the best way to get a quick cost snapshot for my current AI model?

To get a quick cost snapshot for your current AI model, use a script that identifies the most expensive active model from the latest daily log entry. This provides an immediate current-model cost breakdown without manually parsing the entire log history.

Can I filter per-model cost breakdowns by date when aggregating local logs?

Yes, you can filter per-model cost breakdowns by date when aggregating local logs. The summarization process supports optional date filtering to restrict the cost aggregation to a specific chosen time window for Codex and Claude models.

Does the model-usage script support JSON output for automation workflows?

Yes, the model-usage script supports JSON output for automation workflows. It can format the aggregated per-model usage and cost results as machine-readable JSON instead of human-friendly plain text, enabling seamless integration into automated pipelines.

Do I need a specific environment to parse CodexBar JSON logs locally?

You need a local environment with access to your CodexBar cost JSON logs to parse usage data. The script handles JSON inputs from local logs or CodexBar output directly, requiring no external dependencies to aggregate costs from the modelBreakdowns.