skills.rest
SafeAI-Lab-X
SafeAI-Lab-XCOMMUNITY
Explore all skills by this author →
GitHub

model-usage

Aggregate per-model usage costs from CodexBar local logs into JSON or text summaries.

1.0k|59|Updated Mar 20, 2026
Search Tags:#json#ai-models#cost#text-output#model-usage#codexbar#local-logs
One-click install
npx skills add https://github.com/SafeAI-Lab-X/ClawKeeper --skill model-usage-safeai-lab-x
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/SafeAI-Lab-X/ClawKeeper/tree/main/legacy/clawkeeper-watcher/skills/model-usage
Command: npx skills add https://github.com/SafeAI-Lab-X/ClawKeeper --skill model-usage-safeai-lab-x

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

CodexBar usage data is often scattered across logs; this skill consolidates per-model cost data to provide clear visibility into spending and model usage.

Core Features & Use Cases

  • Current-model cost summary: quickly identify the most expensive model in use.
  • All-models cost breakdown: aggregate costs across Codex and Claude models from local logs.
  • Flexible output: text and JSON formats for reporting and automation.
  • Use Case: a data team wants to monitor AI costs across models to optimize provider selection and usage.

Quick Start

Run the model_usage script against your CodexBar cost JSON or local logs to obtain per-model usage and cost summaries.

Frequently Asked Questions about model-usage

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

FAQPage Schema
How do I summarize per-model AI costs from local logs?▼

To summarize per-model AI costs from local logs, run the model_usage script against your CodexBar cost JSON outputs or CLI queries to aggregate daily breakdowns and produce structured per-model cost views.

Can I get a cost breakdown for individual Codex and Claude models?▼

Yes, you can get an all-models cost breakdown that aggregates usage and spending across both Codex and Claude models from your local logs, outputting the results in either structured JSON or plain text format.

How do I identify the most expensive AI model in use from my usage data?▼

You can identify the most expensive AI model by generating a current-model cost summary, which reads daily breakdowns from CodexBar local logs and aggregates the total spending by model.

Does this tool require the CodexBar CLI to read usage data?▼

Yes, the tool requires access to the CodexBar CLI to read daily breakdowns and aggregate cost data from your local logs into a per-model usage summary.

What is the best way to output AI model usage data for automation?▼

The best way to output AI model usage data for automation is to use the JSON format option, which structures the aggregated per-model cost data for direct integration into reporting pipelines.

Related Skills

Explore More Data & Analytics Skills→
aresbitaresbit
46

model-usage

Analyze CodexBar cost logs to report per-model usage and costs.

Community
Advanced
ScientiaCapitalScientiaCapital
28

cost-metering

Track Claude API costs across sessions with budget alerts and model routing.

Community
Advanced
jesse-blackjesse-black
1

rendercv

Generate Typst-rendered CVs from YAML into PDF, HTML, Markdown, and PNG.

Community
Intermediate
Cure-Consulting-GroupCure-Consulting-Group

finops

Manage FinOps processes for Firebase and GCP projects with budgeting and cost allocation.

Official
Advanced