model-usage

Compute per-model cost summaries from CodexBar local cost logs.

2|1|Updated Jan 28, 2026

Search Tags:#usage-tracking #cost-analysis #json-output #per-model #model-usage #codexbar #local-logs

Ready to run

npx skills add https://github.com/zhangziliang04/moltbot_deepseek --skill model-usage-zhangziliang04

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/zhangziliang04/moltbot_deepseek/tree/main/skills/model-usage
Command: npx skills add https://github.com/zhangziliang04/moltbot_deepseek --skill model-usage-zhangziliang04

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Users need clear visibility into how much each model costs in CodexBar's local logs, so finance and engineering can monitor usage and optimize spending.

Core Features & Use Cases

Per-model cost summaries for Codex and Claude, including the current top-cost model or a full breakdown by model.
Flexible input: reads from local CodexBar logs or a provided JSON payload; outputs human-readable text or JSON.
Use Case: Enable budgeting and auditing of model usage across teams and projects.

Quick Start

Summarize per-model CodexBar costs from the local cost logs for quick budgeting insights.

Frequently Asked Questions about model-usage

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

FAQPage Schema

How do I compute per-model cost summaries from CodexBar local logs?▼

Per-model cost summaries from CodexBar logs are computed by parsing daily modelBreakdowns and modelsUsed data structures to aggregate total costs per model. The process selects the latest date entries to output either a human-readable summary or a structured JSON object detailing model-level expenses.

What is the best way to analyze model usage costs for Codex and Claude?▼

The best way to analyze model usage costs for Codex and Claude is parsing local cost logs to extract per-model expense data. This method aggregates usage datasets to provide a full breakdown by model or identify the current top-cost model for budgeting and auditing tasks.

Can I output cost analysis results as a JSON object instead of plain text?▼

You can output cost analysis results as a JSON object containing total costs per model. The computation parses local log data and supports flexible output formats, allowing generation of either a human-readable text summary or a structured JSON payload for reporting.

Does the per-model usage breakdown require a specific JSON payload structure?▼

The per-model usage breakdown requires a JSON-like structure containing daily modelBreakdowns and modelsUsed fields. The Skill reads directly from local CodexBar logs formatted with these fields, or accepts a provided JSON payload matching this structure to compute accurate cost summaries.

Why does my cost breakdown only show the latest date from the local logs?▼

The cost breakdown shows the latest date because the computation logic automatically selects the most recent date entries from the modelBreakdowns data when summarizing. This selection ensures the summary reflects current model usage and expenses without duplicating historical daily aggregates.