model-usage

Summarize CodexBar local cost logs into per-model breakdowns for Codex and Claude.

1|Updated Mar 6, 2026
One-click install
npx skills add https://github.com/zhcndoc/openclaw --skill model-usage-zhcndoc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/zhcndoc/openclaw/tree/main/skills/model-usage
Command: npx skills add https://github.com/zhcndoc/openclaw --skill model-usage-zhcndoc

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

CodexBar local cost logs can be hard to interpret at a glance; this Skill consolidates usage by model to reveal where costs accrue.

Core Features & Use Cases

  • Per-model cost summaries: aggregates model-wise costs from CodexBar logs.
  • Supports current-model view (top daily breakdown) or all-model totals for budgeting and optimization.
  • Use with local JSON outputs or raw CodexBar data to compare model usage across time.

Quick Start

Run the script to summarize your local codexbar cost data and view per-model costs.

Frequently Asked Questions about model-usage

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

FAQPage Schema
How do I summarize CodexBar local cost logs by model?

To summarize CodexBar local cost logs by model, you can use a script that parses local JSON logs to aggregate modelBreakdowns, providing per-model cost totals for Codex and Claude.

Can I view a cost breakdown for all models instead of just the current model?

Yes, you can view an all-model cost breakdown. The aggregation supports both a current-model view for top daily breakdowns and an all-model view for comprehensive budgeting and optimization.

What is the best way to analyze per-model usage costs from local JSON logs?

The best way to analyze per-model usage costs from local JSON logs is to run a script that validates inputs and aggregates the data, outputting either human-readable text or JSON with latest-day costs.

Does the per-model cost summary output JSON or human-readable text?

The per-model cost summary outputs both JSON and human-readable text. It validates your local JSON inputs and aggregates the data to produce per-model totals and latest-day costs.

Why do I need to aggregate modelBreakdowns from local CodexBar logs?

You need to aggregate modelBreakdowns from local CodexBar logs because the raw local cost data can be hard to interpret at a glance, and consolidating it reveals exactly where costs accrue.