model-usage

Name: model-usage
Availability: InStock
Author: johnnywhitemike

Summarize CodexBar local cost usage by model from cost JSON data.

Updated Apr 8, 2026

Search Tags:#usage analytics #codexbar #cli automation #model cost #per-model breakdown #json summarization

Ready to run

npx skills add https://github.com/JOHNNYWHITEMIKE/openclaw --skill model-usage-johnnywhitemike

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

CodexBar’s local cost data can be hard to translate into a clear, per-model cost picture, so this Skill helps you quickly understand which models you’ve been using and what they cost.

Core Features & Use Cases

Per-model cost summaries: Produces a cost-only breakdown by model from CodexBar local cost JSON logs.
Current model reporting: Identifies the most recent daily entry and selects the highest-cost model from that breakdown (with a fallback to the latest modelsUsed entry).
JSON or readable text output: Supports both human-friendly summaries and scriptable JSON output for dashboards or further analysis.
Use case: You want to answer “Which Codex/Claude model is costing me the most lately?” by summarizing your latest activity or generating an “all models” breakdown from CodexBar cost output.

Quick Start

Ask the AI to summarize your latest Codex model cost by running the model_usage script with provider codex in current mode.

Frequently Asked Questions about model-usage

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

FAQPage Schema

How do I get a per-model cost breakdown from CodexBar JSON logs?▼

You can generate a per-model cost breakdown from CodexBar JSON logs by running the model_usage script, which parses cost payloads and aggregates totals by model for text or JSON output.

How do I find which Claude or Codex model costs me the most recently?▼

You can identify your highest-cost Claude or Codex model by checking the latest daily entry in CodexBar data, selecting the highest-cost model from its modelBreakdowns, and falling back to the latest modelsUsed entry if needed.

Can I output CodexBar usage analytics as JSON for dashboards?▼

Yes, you can output CodexBar usage analytics as scriptable JSON, which allows you to feed per-model cost summaries directly into dashboards or further data analysis pipelines.

Does this per-model cost summarization require any external dependencies?▼

No, this per-model cost summarization requires no external dependencies, relying solely on built-in scripts to parse local CodexBar cost JSON data.

What happens if modelBreakdowns is missing from the latest CodexBar daily entry?▼

If modelBreakdowns is missing from the latest CodexBar daily entry, the Skill falls back to selecting the current model from the latest modelsUsed entry to ensure cost reporting continues.