skills.rest
Zavianx
ZavianxCOMMUNITY
Explore all skills by this author →
GitHub

model-usage

Summarize per-model usage costs from CodexBar logs for Codex and Claude.

121|17|Updated Apr 10, 2026
Search Tags:#cli#analysis#json#cost#model-usage#codexbar#local-logs
One-click install
npx skills add https://github.com/Zavianx/velaclaw --skill model-usage-zavianx
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/Zavianx/velaclaw/tree/main/skills/model-usage
Command: npx skills add https://github.com/Zavianx/velaclaw --skill model-usage-zavianx

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Quickly-analyze local CodexBar cost logs to reveal per-model expenditure for Codex and Claude, helping teams optimize model usage.

Core Features & Use Cases

  • Get per-model usage costs from CodexBar's local cost logs for Codex and Claude, including the current (most recent) model or a full model breakdown.
  • Flexible inputs and outputs: read JSON from a file or stdin and output in either human-readable text or JSON for automation.
  • Use case: identify which models drive the most cost across private deployments to guide optimization decisions.

Quick Start

Run the model_usage.py script to generate per-model cost summaries from CodexBar logs.

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 usage costs from CodexBar local logs?▼

You can summarize per-model usage costs from CodexBar local logs by running a script that reads JSON input from a file or stdin. It processes the data to return per-model expenditure breakdowns for Codex and Claude.

Can I filter model usage costs to only show recent data?▼

Yes, you can filter model usage costs to show recent data by applying an optional days filter. This allows you to limit the per-model cost summary to a specific recent timeframe from your local logs.

Does the tool support outputting cost summaries in JSON format for automation?▼

The tool supports outputting cost summaries in JSON format for automation, as well as human-readable plain-text. You can choose either format when generating per-model usage reports from your logs.

What is the difference between current-model and all-model views for cost analysis?▼

Current-model view isolates costs for the most recently used model, while all-model view provides a full breakdown of expenditure across every model. Both views use JSON input from CodexBar logs to calculate usage costs.

How do I analyze Codex and Claude costs from local JSON logs?▼

To analyze Codex and Claude costs, provide your local JSON logs via file or stdin to the analysis script. It calculates per-model usage costs to help identify which models drive the most expenditure across deployments.

What is the best way to identify which models drive the most cost in private deployments?▼

The best way to identify costly models is to generate a full per-model cost breakdown from your local logs. Analyzing these summaries helps guide optimization decisions for your private Codex and Claude deployments.

Related Skills

Explore More Data & Analytics Skills→
x402agentx402agent

model-usage

Summarize per-model cost usage from CodexBar JSON logs.

Community
Intermediate
susamnsusamn

model-usage

Generate per-model cost summaries from CodexBar CLI or JSON data.

Community
Intermediate
zhongjiszhongjis

jc

Convert command-line interface output into structured JSON for programmatic analysis.

Community
Basic
tygwantygwan
1

analytics

Aggregate and visualize CLI tool usage statistics from telemetry metrics.

Community
Intermediate