model-usage

Aggregate per-model costs from CodexBar logs with optional date filtering.

Updated Jan 29, 2026
One-click install
npx skills add https://github.com/DharambirAgrawal/Personal-Assistant --skill model-usage-dharambiragrawal
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/DharambirAgrawal/Personal-Assistant/tree/main/skills/model-usage
Command: npx skills add https://github.com/DharambirAgrawal/Personal-Assistant --skill model-usage-dharambiragrawal

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

CodexBar local cost logs are model-agnostic and hard to interpret at a model level. This skill aggregates per-model costs to reveal spending drivers and enable cost-aware decisions.

Core Features & Use Cases

  • Current-model summary: identify the current active model and its latest cost.
  • All-model breakdowns: totalize costs across all models for comprehensive usage insight.
  • Input flexibility: read from CodexBar CLI output or a JSON log file, with optional date filtering.

Quick Start

Run the script to generate a per-model cost summary from CodexBar, using the current model or all models as needed.

Frequently Asked Questions about model-usage

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

FAQPage Schema
How do I track per-model usage costs from CodexBar local logs?

To track per-model usage costs from CodexBar local logs, you can aggregate modelBreakdowns to reveal spending drivers. This skill processes current-model summaries and full-model breakdowns from JSON files or CLI output.

Can I filter CodexBar cost logs by date to isolate specific model spending?

Yes, you can filter CodexBar cost logs by date to isolate specific model spending. The skill supports optional date filtering to narrow down current-model summaries and all-model breakdowns.

Does this skill require the CodexBar CLI to be installed to parse JSON cost logs?

Yes, this skill requires the CodexBar CLI to be installed to parse JSON cost logs effectively. It operates on both CodexBar CLI output and local JSON log files to aggregate model-level costs.

What is the best way to export aggregated model usage costs for integration?

The best way to export aggregated model usage costs for integration is to output the results as JSON. The skill generates either human-readable text or JSON output from the aggregated modelBreakdowns data.

Which AI providers are supported when calculating per-model usage costs locally?

When calculating per-model usage costs locally, the supported AI providers are codex and claude. The skill aggregates local cost logs to identify spending drivers across these specific provider models.