model-usage

Summarize CodexBar local cost usage by model from JSON logs.

1|Updated Mar 6, 2026
One-click install
npx skills add https://github.com/isaaceliape/FASE --skill model-usage-isaaceliape
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/isaaceliape/FASE/tree/main/skills/model-usage
Command: npx skills add https://github.com/isaaceliape/FASE --skill model-usage-isaaceliape

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

CodexBar local cost data is spread across logs; this skill aggregates per-model usage and cost to provide clear visibility into model-level spending for Codex and Claude.

Core Features & Use Cases

  • Current-model cost snapshot from CodexBar logs for quick budgeting and monitoring.
  • All-model cost breakdown by model to compare usage and identify spend drivers.
  • Flexible input: read from local CodexBar JSON logs or stdin and output text or JSON for automation.

Quick Start

Process CodexBar cost 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 cost usage from CodexBar JSON logs?

To summarize per-model cost usage, the skill reads local CodexBar JSON logs and aggregates modelBreakdowns by modelName. It outputs text or JSON containing totals, latest-day costs, and per-model results.

What is the best way to get a cost breakdown by model for Codex and Claude contexts?

Generating a cost breakdown by model involves reading daily JSON log entries and aggregating the data. This provides visibility into model-level spending across Codex and Claude contexts for budgeting.

Can I output JSON summaries instead of text for CodexBar logs?

Yes, you can output JSON summaries instead of text. The skill supports flexible input from local logs or stdin and formats aggregated per-model usage and cost results as structured JSON for automation.

Does the cost summary handle missing data in local JSON logs?

Yes, the cost summary handles missing data gracefully. When aggregating daily entries and modelBreakdowns from local JSON logs, the process accounts for gaps to ensure accurate per-model cost totals without failing.

Do I need the codexbar dependency to monitor model-level spending?

Yes, you need the codexbar dependency to monitor model-level spending. The skill specifically reads local CodexBar cost data to aggregate per-model usage, making it essential for generating current and full breakdown summaries.