model-usage

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

1|Updated Apr 10, 2026
One-click install
npx skills add https://github.com/pertain99/openclaw-better --skill model-usage-pertain99
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/pertain99/openclaw-better/tree/main/skills/model-usage
Command: npx skills add https://github.com/pertain99/openclaw-better --skill model-usage-pertain99

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

CodexBar's local cost logs can be difficult to interpret at a glance; this Skill aggregates per-model costs and provides a clear view of model-level spend and trends to support budgeting and optimization.

Core Features & Use Cases

  • Retrieve per-model usage costs for Codex or Claude from local logs.
  • Choose between the current (latest daily) data or a full model breakdown for deeper analysis.
  • Output results as readable text or structured JSON for automation, dashboards, or reporting.

Quick Start

Run the script with --provider codex --mode current to view the latest per-model costs, or with --mode all to see a full 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 aggregate per-model usage costs from CodexBar local logs?

Aggregate per-model usage costs by running the script with --provider codex --mode current for the latest daily data, or --mode all for a full model breakdown. It reads local cost logs and parses daily modelBreakdowns to summarize costs by model.

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

Yes, retrieve per-model cost breakdowns for Codex and Claude by specifying the --provider argument. The script reads local CodexBar logs to aggregate and display costs for the selected provider.

What is the best way to integrate per-model spend data into a reporting dashboard?

Output aggregated per-model cost results as structured JSON to integrate spend data into dashboards. The script supports JSON output for piping the full model breakdown into automated reporting systems.

Do I need the CodexBar CLI installed to parse model cost logs?

You need CodexBar installed as a dependency. The Skill accepts input from a JSON file or the CodexBar CLI, allowing you to parse local cost logs directly from a saved file or by invoking the CLI.

How does parsing daily modelBreakdowns help with API budget optimization?

Parsing daily modelBreakdowns aggregates costs by model to reveal spend and trends. This detailed breakdown supports budgeting and optimization by highlighting exactly where API costs accumulate per model.