Calculate per-model usage costs from CodexBar local logs.
npx skills add https://github.com/zhanbei1/OpenOcta --skill model-usage-zhanbei1
Please help me install this Agent Skill. Skill: model-usage Source: https://github.com/zhanbei1/OpenOcta/tree/main/src/skills/model-usage Command: npx skills add https://github.com/zhanbei1/OpenOcta --skill model-usage-zhanbei1
Organizations need clear, model-level cost visibility from CodexBar's local logs to track spending and optimize prompts.
Run the model_usage.py script with a provider (codex or claude) and an input source to generate a per-model cost summary.
High-intent search queries and answers about installing and using this skill.
You can calculate per-model usage costs from CodexBar local logs by running the model_usage.py script with a provider and input source. It analyzes daily modelBreakdowns to output a per-model cost summary.
Getting a full per-model cost breakdown for Codex and Claude providers involves running the model_usage.py script with the --mode parameter. This analyzes daily modelBreakdowns to output total costs per model.
Yes, you need the CodexBar CLI installed and access to local cost logs to analyze model usage costs. The script processes these local JSON logs to compute per-model spending.
Yes, you can read CodexBar cost logs from a local file by passing the --input parameter to the model_usage.py script. This allows flexible data sourcing for your cost reporting.
You identify the most expensive active model from recent logs by executing the model_usage.py script with the appropriate provider. It exposes the current model cost directly from recent local entries.
aresbitAnalyze CodexBar cost logs to report per-model usage and costs.
WellFitCommunityMonitor AI spending and usage across MCP and automation skills.
dingdyanSummarize per-model costs from CodexBar JSON logs with text or JSON output.
ammonfifeQuery cloud billing APIs from 13 providers and generate a unified JSON cost report.
