model-usage

Aggregate per-model usage costs from CodexBar local JSON logs.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

CodexBar cost logs can be dense and hard to interpret at a glance; this skill aggregates per-model costs from local logs to provide quick cost visibility for Codex and Claude usage.

Core Features & Use Cases

  • Current model view: identify the most expensive active model on the latest data.
  • Full breakdown: summarize costs by model across a selected date range or all daily entries.
  • Automation-friendly outputs: produce human-readable text or structured JSON for downstream tooling.

Quick Start

Run the script to summarize per-model usage costs from CodexBar logs for the current model or all models.

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 CodexBar local logs?

To summarize per-model costs from CodexBar local logs, this skill reads local JSON log files, aggregates expenses by model, and outputs a formatted text or JSON summary for reporting and automation.

Can I get a cost breakdown for both Codex and Claude models in my logs?

Yes, the skill processes local JSON logs to aggregate and report usage costs for both Codex and Claude models, providing a complete by-model cost summary.

How do I find the most expensive active model in my current usage data?

To find the most expensive active model in your current usage data, run the skill to generate a current model snapshot that identifies the highest-cost model from the latest CodexBar log entries.

Does this tool output structured JSON for pipeline automation?

Yes, the skill outputs structured JSON suitable for pipeline automation. It reads local JSON logs and formats aggregated per-model cost results as JSON for integration with downstream tooling.

What is the best way to aggregate daily CodexBar logs by model?

The best way to aggregate daily CodexBar logs by model is to use a script that parses local JSON entries. This skill summarizes costs across all daily entries or a selected date range into a clear breakdown.