model-usage

Summarize per-model CodexBar costs from local JSON logs.

Updated Apr 6, 2026

Search Tags:#json #data-analytics #cost-analysis #model-usage #codexbar #local-logs #ai-model-costs

Ready to run

npx skills add https://github.com/dakshrawat298-gif/SOL-ALPHA-GUARDIAN --skill model-usage-dakshrawat298-gif

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/dakshrawat298-gif/SOL-ALPHA-GUARDIAN/tree/main/packages/skills/skills/model-usage
Command: npx skills add https://github.com/dakshrawat298-gif/SOL-ALPHA-GUARDIAN --skill model-usage-dakshrawat298-gif

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

CodexBar cost data is often scattered across logs; this Skill analyzes local cost logs to deliver per-model cost summaries for Codex and Claude, enabling quick budgeting and model selection.

Core Features & Use Cases

Local-first cost aggregation: reads CodexBar cost JSON from your machine to produce per-model totals.
Current-model and full-breakdown views: switch between the latest model summary and a complete per-model cost breakdown.
Use cases: ideal for budgeting experiments, auditing model usage across projects, and comparing model efficiency.

Quick Start

Run the script with your local CodexBar cost data to see either the current-model cost or a full per-model breakdown.

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 AI costs from local JSON logs?▼

Per-model cost summaries are generated by reading local CodexBar JSON logs, parsing modelBreakdowns and daily entries to compute totals. This provides quick budgeting insights for Codex and Claude models without sending data externally.

Can I get a full per-model cost breakdown for Codex and Claude?▼

Yes, a full per-model breakdown for Codex and Claude is supported. The tool switches between the latest current-model summary and a complete per-model cost breakdown by computing totals from local JSON cost data.

Does the CodexBar cost analysis output JSON or plain text?▼

The CodexBar cost analysis can output either plain text or JSON. It reads your local cost data to compute per-model totals, allowing you to integrate the summarized results into your preferred format.

What is the best way to audit AI model usage costs locally?▼

Auditing AI model usage costs locally is done by aggregating scattered CodexBar cost logs. Reading local JSON cost data enables quick budgeting, auditing model usage across projects, and comparing model efficiency.

Do I need CodexBar installed to analyze local cost data?▼

CodexBar is a required dependency. The tool relies on reading the local JSON cost logs generated by CodexBar to compute per-model totals and generate accurate cost summaries.