model-usage

Summarize per-model costs from CodexBar local cost logs.

1|Updated Feb 1, 2026
One-click install
npx skills add https://github.com/sarathi-aiml/openclaw-zero-trust --skill model-usage-sarathi-aiml
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/sarathi-aiml/openclaw-zero-trust/tree/main/skills/model-usage
Command: npx skills add https://github.com/sarathi-aiml/openclaw-zero-trust --skill model-usage-sarathi-aiml

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

CodexBar local cost logs are processed to provide per-model usage costs for Codex and Claude.

Core Features & Use Cases

  • Collect per-model costs from daily cost logs to see spending distribution across models.
  • Generate a current-model summary or a full breakdown across all models for budgeting and optimization.
  • Output results in plain text or JSON to feed dashboards and reports.

Quick Start

Run the bundled model_usage.py script against your CodexBar cost JSON to generate a per-model usage 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 costs from CodexBar local logs?

To summarize per-model costs, you run the bundled model_usage.py script against your CodexBar cost JSON. It aggregates modelBreakdowns and determines the current model from recent entries.

Can I get a full cost breakdown across all models for budgeting?

Yes, you can generate a full breakdown across all models from local cost logs. The script aggregates daily modelBreakdowns to show your total spending distribution.

How do I output CodexBar cost analysis results in JSON format?

You can output CodexBar cost analysis results in JSON format to feed dashboards and reports. The script supports both plain text and JSON output formats.

Do I need any external dependencies to analyze CodexBar cost logs?

No external dependencies are required to analyze CodexBar cost logs. The Skill operates independently using only bundled scripts and references.

What is the best way to see spending distribution between Codex and Claude?

The best way to see spending distribution is processing CodexBar local cost logs. The script collects per-model costs specifically for Codex and Claude usage.

How does the script determine the current model from recent entries?

The script determines the current model by reading recent entries in the CodexBar cost JSON. It then generates a summary specifically for that active model.