model-usage

Aggregate per-model costs from CodexBar local JSON logs.

588|41|Updated May 13, 2026
One-click install
npx skills add https://github.com/zai-org/Synapse --skill model-usage-zai-org
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/zai-org/Synapse/tree/main/.setup/skills/clawhub/skills/model-usage
Command: npx skills add https://github.com/zai-org/Synapse --skill model-usage-zai-org

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Quickly derive per-model cost insights from CodexBar's local logs, so you can understand spending without external services.

Core Features & Use Cases

  • Current model view: identify the most expensive model on the latest daily entry.
  • All-model breakdown: aggregate costs by model across recent days for budgeting and optimization.
  • Local data-first: operates on the JSON logs generated by CodexBar on your machine.

Quick Start

Run the provided script to summarize per-model usage costs from CodexBar's local cost logs.

Frequently Asked Questions about model-usage

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I aggregate per-model usage costs from local JSON logs?

To aggregate per-model usage costs from local JSON logs, the tool parses CodexBar daily cost entries, groups spending by model, and outputs a full breakdown for budgeting and optimization without external services.

Can I find the most expensive model in my latest CodexBar cost entry?

Yes, you can find the most expensive model in your latest CodexBar cost entry. The tool identifies the current top model cost by reading the latest daily log locally and highlighting the highest spender.

Does this tool work with both Claude and Codex local cost logs?

Yes, the tool works with both Claude and Codex local cost logs. It reads the JSON logs generated by CodexBar on your machine and summarizes per-model usage costs for both platforms locally.

How do I filter daily model breakdowns by date when summarizing usage costs?

You can filter daily model breakdowns by date when summarizing usage costs. The tool applies optional date filtering to the local JSON logs before aggregating costs by model and outputting the selected text or JSON format.

What is the best way to analyze CodexBar local logs without external services?

The best way to analyze CodexBar local logs without external services is using a local data-first approach. This tool parses JSON logs directly on your machine to output text or JSON per-model cost summaries.