model-usage

Aggregate per-model CodexBar costs from local JSON logs into text or JSON summaries.

2.5k|423|Updated Mar 28, 2026
One-click install
npx skills add https://github.com/Bitterbot-AI/bitterbot-desktop --skill model-usage-bitterbot-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/Bitterbot-AI/bitterbot-desktop/tree/main/skills/model-usage
Command: npx skills add https://github.com/Bitterbot-AI/bitterbot-desktop --skill model-usage-bitterbot-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

CodexBar model-usage helps you quickly understand per-model costs and usage from local CodexBar logs, enabling cost-aware decision making for AI deployments.

Core Features & Use Cases

  • Summarize per-model costs by provider (codex or claude) from local cost JSON logs.
  • Determine the current top-cost model or get a full breakdown across all models.
  • Output in human-readable text or JSON, with options to filter by days and to see latest day costs.

Quick Start

Run the bundled script to summarize per-model CodexBar costs by 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 costs from local CodexBar logs?

To summarize per-model costs from local CodexBar logs, this Skill reads local JSON logs and aggregates per-model costs to provide a current-model view or a full breakdown across all models.

Can I filter model usage summaries by specific days?

Yes, you can filter model usage summaries by specific days. The Skill provides optional day filtering and can display the latest day costs when reading and aggregating local JSON logs.

Does the Skill support generating cost reports in JSON format?

Yes, the Skill supports generating cost reports in JSON format. It aggregates per-model costs from local logs and outputs the results in either human-readable text or JSON formats for reporting.

What is the best way to get a breakdown of Codex and Claude costs by model?

The best way to get a breakdown of Codex and Claude costs by model is to apply this Skill, which summarizes per-model cost usage by provider from local cost JSON logs for cost optimization.

Do I need external dependencies to analyze CodexBar cost data?

No, you do not need external dependencies to analyze CodexBar cost data. The Skill operates independently using bundled scripts and references to read and summarize local JSON logs.