model-usage

Summarize per-model CodexBar usage and costs from local JSON logs.

Updated Jan 16, 2026
One-click install
npx skills add https://github.com/czue/clawdbot --skill model-usage-czue
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/czue/clawdbot/tree/main/skills/model-usage
Command: npx skills add https://github.com/czue/clawdbot --skill model-usage-czue

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

CodexBar's local cost logs can be difficult to interpret at a glance. This Skill provides a concise per-model usage and cost breakdown to help budgeting and optimization decisions.

Core Features & Use Cases

  • Current model vs all-models: View costs for the currently active model or see totals across all models.
  • Local-first cost analysis: Operates on CodexBar's local JSON logs without external dependencies.
  • Flexible outputs: Outputs plain text for quick reads or structured JSON for automation and dashboards.
  • Use Case: Identify the model that drives the most cost in a day and adjust usage or configurations accordingly.

Quick Start

Summarize per-model CodexBar usage from the latest local cost log.

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 local logs?

To get a per-model cost breakdown from CodexBar local logs, read daily JSON entries and aggregate modelBreakdowns by model. This provides quick, model-level cost summaries for reporting or optimization.

What is the best way to track usage costs for the currently active model versus all models?

Tracking usage costs for the current versus all models involves aggregating local JSON cost logs using current or all modes. This outputs text or JSON, identifying which model drives the most daily cost.

Do I need external dependencies to analyze CodexBar cost logs?

No external dependencies are needed to analyze CodexBar cost logs. The analysis operates locally on JSON logs written by CodexBar, reading daily entries and aggregating modelBreakdowns without external tools.

Can I output CodexBar usage summaries as structured JSON for dashboards?

Yes, you can output CodexBar usage summaries as structured JSON for dashboards. The analysis supports flexible outputs, delivering plain text for quick reads or JSON for automation and dashboards.

How does local cost tracking help with budgeting and optimization decisions?

Local cost tracking helps with budgeting by providing concise per-model usage and cost breakdowns from JSON logs. It identifies the model driving the most cost, enabling you to adjust usage and configurations accordingly.