model-usage

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

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/rebootix-research/viki-clow --skill model-usage-rebootix-research
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/rebootix-research/viki-clow/tree/main/skills/model-usage
Command: npx skills add https://github.com/rebootix-research/viki-clow --skill model-usage-rebootix-research

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill automatically summarizes per-model usage costs from CodexBar's local cost logs and the corresponding JSON payloads, giving you a clear view of where costs are incurred and how they trend over time.

Core Features & Use Cases

  • Generate per-model usage cost summaries from local CodexBar logs or cost JSON data for Codex and Claude.
  • Output results as plain text for quick reads or as JSON for automation and reporting pipelines.
  • Use it for budgeting, cost optimization, and stakeholder reporting on AI model usage.

Quick Start

Run the model_usage.py script against CodexBar cost JSON or local logs to generate per-model usage and cost summaries.

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 local CodexBar logs?

You can summarize per-model usage costs by processing CodexBar local logs and cost JSON data, applying filters to current models or full breakdowns with optional date-range filtering for human-readable text or JSON structured results.

Can I filter AI model usage cost summaries by a specific date range?

Yes, you can filter AI model usage cost summaries by a specific date range. The tool processes daily modelBreakdowns from CodexBar logs and applies optional date-range filtering to output the targeted cost data.

Does this tool support usage cost tracking for both Codex and Claude models?

Yes, this tool supports usage cost tracking for both Codex and Claude models. It applies to Codex and Claude usage data, reading cost JSON or fetching via CodexBar CLI to process and summarize the incurred costs.

What is the best way to export per-model usage cost data for reporting pipelines?

The best way to export per-model usage cost data for reporting pipelines is to output JSON structured results. The tool can process CodexBar cost JSON and return structured JSON instead of plain text for automation and reporting.

Do I need the CodexBar CLI installed to analyze local cost JSON logs?

No, you do not need the CodexBar CLI installed to analyze local cost JSON logs. The tool can directly read and process existing CodexBar cost JSON files or local logs to generate the per-model usage summaries.