skills.rest
papachong
papachongCOMMUNITY
Explore all skills by this author →
GitHub

model-usage

Summarizes CodexBar cost logs into per-model usage and cost breakdowns.

2|Updated Apr 4, 2026
Search Tags:#python#cli#claude#model-usage#codexbar#cost-analytics
One-click install
npx skills add https://github.com/papachong/RHClaw --skill model-usage-papachong
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/papachong/RHClaw/tree/main/RHClaw-Desktop/src-tauri/skills/model-usage
Command: npx skills add https://github.com/papachong/RHClaw --skill model-usage-papachong

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Provide a simple, scriptable summary of per-model usage and cost from CodexBar local cost logs so engineers and operators can quickly see which model is currently driving spend or get a full model cost breakdown for billing and tuning.

Core Features & Use Cases

  • Per-model aggregation: Aggregates costs from daily modelBreakdowns into per-model totals.
  • Current-model detection: Picks the most recent top-cost model or falls back to the last model in modelsUsed, with an override to specify a model explicitly.
  • Flexible inputs & outputs: Reads CodexBar CLI output, a file, or stdin and emits human-readable text or structured JSON; supports provider selection (codex/claude), day-range filtering, and pretty JSON.
  • Use Case: Run after a daily cost snapshot to identify which model to prioritize for optimization or to generate a scriptable report for finance and engineering.

Quick Start

Use the bundled Python script to summarize CodexBar local cost JSON and report either the current top-cost model or a full per-model cost breakdown.

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 and cost from CodexBar local cost logs?▼

Summarize per-model usage and cost by running a Python script that aggregates CodexBar daily modelBreakdowns into per-model totals, supporting both Codex and Claude providers with human-readable text or structured JSON output.

How does current-model detection work for CLI cost breakdowns?▼

Current-model detection picks the most recent top-cost model from the cost logs or falls back to the last model in the modelsUsed list, with an option to override and specify a model explicitly.

Can I filter CodexBar cost analytics by provider and day range?▼

Yes, you can filter CodexBar cost analytics by selecting a provider (codex or claude) and specifying a day range to limit the per-model usage and cost summary scope.

What inputs does the model-usage cost summary script accept?▼

The model-usage cost summary script accepts CodexBar CLI output, a saved cost JSON file, or stdin input, requiring either CodexBar available on PATH or a directly provided cost JSON.

How do I generate structured JSON output for per-model cost reporting?▼

Generate structured JSON output by running the script with the pretty JSON option, which formats the per-model usage and cost aggregation into a scriptable report suitable for finance and engineering analysis.

What are the limitations of using CodexBar logs for model cost optimization?▼

Cost summarization is limited to CodexBar local cost logs for Codex and Claude providers and requires either CodexBar on PATH or a provided cost JSON input to function.

Related Skills

Explore More Software Engineering Skills→
borealBytesborealBytes
7

model-usage

Parse CodexBar JSON logs to aggregate per-model cost breakdowns.

Community
Intermediate
karaabd23-cryptokaraabd23-crypto
1

model-usage

Summarize per-model usage costs from CodexBar local cost logs.

Community
Intermediate
open-gsdopen-gsd
1.0k

agent-browser

Automate browser navigation, form filling, and data extraction via CLI.

Official
Advanced
spoonbobospoonbobo

model-usage

Summarize per-model cost usage from CodexBar local cost logs.

Community
Intermediate