model-usage

Summarizes CodexBar usage costs by model from local logs into text or JSON reports.

Updated Apr 5, 2026
One-click install
npx skills add https://github.com/balic-AI-ML-R-D-Resources/eliza_autonomous_agents --skill model-usage-balic-ai-ml-r-d-resources
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/balic-AI-ML-R-D-Resources/eliza_autonomous_agents/tree/main/packages/skills/skills/model-usage
Command: npx skills add https://github.com/balic-AI-ML-R-D-Resources/eliza_autonomous_agents --skill model-usage-balic-ai-ml-r-d-resources

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill helps teams quickly understand spending and utilization across models by summarizing CodexBar's local cost logs into per-model totals and day-by-day breakdowns.

Core Features & Use Cases

  • Per-model cost summaries: generate a concise cost view by model (e.g., codex-001, claude-2) from local logs.
  • Current vs. all-model views: prefer the most recent "current" model or get a full breakdown across all models.
  • Flexible input: works from local CodexBar JSON exports or piped JSON data and supports text or JSON outputs for integration.

Quick Start

Summarize CodexBar cost data by model from local logs for current 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 usage costs from local CodexBar logs?

To summarize per-model usage costs from local CodexBar logs, this Skill parses the local JSON output and aggregates usage by model. It processes Codex and Claude data to return concise text or JSON cost reports.

Can I get a day-by-day cost breakdown across all models from CodexBar exports?

Yes, you can get a day-by-day cost breakdown across all models from CodexBar exports. The Skill provides a full per-model breakdown across multiple days, returning detailed text or JSON reports for your aggregated data.

Does the tool work with piped JSON data or only local CodexBar files?

The tool works with both local CodexBar JSON exports and piped JSON data. This flexible input handling allows you to process usage logs directly from files or stream data through pipeline commands for immediate aggregation.

What is the difference between the current model view and the full per-model breakdown?

The current model view summarizes costs for only the most recent active model, while the full per-model breakdown aggregates spending across all models. You can choose either option based on your reporting needs and data scope.

Can I output the aggregated model usage report as JSON for integration?

Yes, you can output the aggregated model usage report as JSON for integration. The Skill supports both text and JSON output formats, allowing you to easily pass the summarized cost data to downstream systems or dashboards.

What data formats are supported when parsing CodexBar usage logs?

The Skill supports parsing local CodexBar JSON output files and piped JSON data streams. It extracts usage metrics and costs from these structured formats to aggregate totals by model and generate reports.