skills.rest
brikkoAI
brikkoAIOFFICIAL
Explore all skills by this author →
WebsiteGitHub

model-usage

Parse CodexBar local cost logs into per-model LLM spending summaries.

1|Updated May 3, 2026
Search Tags:#codex#claude#cost-tracking#model-usage#codexbar#cost-breakdown#llm-cost
One-click install
npx skills add https://github.com/brikkoAI/brikko-studio --skill model-usage-brikkoai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: model-usage
Source: https://github.com/brikkoAI/brikko-studio/tree/main/packages/core/skills/model-usage
Command: npx skills add https://github.com/brikkoAI/brikko-studio --skill model-usage-brikkoai

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Manually sifting through CodexBar local cost logs to track per-model LLM spending is time-consuming and error-prone, especially when managing usage across multiple providers like Codex and Claude.

Core Features & Use Cases

  • Per-Model Cost Summaries: Generate either a summary of your current most-used model's cost or a full breakdown of all models and their total spending from local logs.
  • Flexible Input & Output: Support for filtering results to recent days, with options to output data in plain text or structured JSON format.
  • Use Case: Engineering teams using multiple AI coding tools can use this skill to quickly identify high-cost models and optimize their AI spending without manual log parsing.

Quick Start

Use the model-usage skill to pull a full per-model cost breakdown for your Codex and Claude usage from your local 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 track per-model LLM cost breakdowns for Codex and Claude?▼

To track per-model LLM cost breakdowns for Codex and Claude, you can automatically parse local CodexBar cost logs to generate current model summaries or full historical spending views without manual effort.

Do I need CodexBar installed to analyze Claude and Codex usage costs?▼

Yes, you need the CodexBar CLI installed and accessible on your system PATH to fetch local cost log data required for analyzing Claude and Codex provider spending.

Can I filter LLM cost tracking results to recent days and output as JSON?▼

You can filter LLM cost tracking results to recent days and output the per-model cost breakdown data in either plain text or structured JSON format for further analysis.

What is the best way to identify high-cost AI models from local logs?▼

The best way to identify high-cost AI models from local logs is to generate a full historical model breakdown that aggregates total spending across all models, helping engineering teams optimize AI spending.

Does manual log parsing fail to provide accurate per-model spending tracking?▼

Manual log parsing for per-model spending tracking is time-consuming and error-prone, especially when managing usage across multiple providers like Codex and Claude, whereas automated parsing eliminates these issues.

Related Skills

Explore More Software Engineering Skills→
storyclaw-officialstoryclaw-official

model-usage

Summarize local AI model costs from CodexBar CLI JSON logs.

Official
Intermediate
openclaw-easyopenclaw-easy
14

model-usage

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

Community
Intermediate
shepard-systemshepard-system
70

obs-cost

Monitor AI coding assistant costs and token usage across providers.

Official
Intermediate
kubonykubony
10

gcp-usage

Reports and analyzes GCP API usage and costs from BigQuery billing_export data.

Community
Intermediate