Estimate prompt token counts and dollar costs across language models.
npx skills add https://github.com/JGalego/Bag-of-Tricks --skill tollbooth
Please help me install this Agent Skill. Skill: tollbooth Source: https://github.com/JGalego/Bag-of-Tricks/tree/main/tollbooth Command: npx skills add https://github.com/JGalego/Bag-of-Tricks --skill tollbooth
This Skill provides the cost estimation of prompts across various language models before they are sent, helping users manage their budgets and optimize their requests.
Estimate the cost of a prompt using the tollbooth skill with the following command: tollbooth --tokens-only "Your prompt here"
High-intent search queries and answers about installing and using this skill.
You can estimate prompt cost by calculating input and output token counts and projected dollar amounts across supported models. Use the command `tollbooth --tokens-only "Your prompt here"` to retrieve immediate token estimates before sending requests.
Prompt cost comparison across different language models is supported natively by this skill. It evaluates the same prompt against multiple models to display varying token counts and dollar costs, helping you identify the most budget efficient model for your specific request.
Yes, automated budgeting in Claude agent workflows is a core feature of this skill. It integrates directly into agent pipelines to provide real-time cost estimation, allowing you to manage and plan your AI budget automatically before prompts are dispatched.
The best way to plan an AI budget is using prompt cost estimation to project dollar costs and token counts before execution. This skill provides manual CLI estimation and automated budgeting capabilities to optimize requests and manage spending across models.
No external dependencies are required to run this prompt cost estimator. The skill operates independently using its built-in scripts, allowing you to estimate token counts and dollar costs without installing additional software packages.
Atrium-HermesConvert token usage data into dollar costs with per-skill and per-model breakdowns.
unju-aiRoute LLM tasks to cost-effective models while tracking budgets and caching prompts.
Xza85hrfRoute tasks across Opus, Sonnet, Haiku, Ollama Cloud, and Ollama Local to minimize token costs.
Cure-Consulting-GroupManage FinOps processes for Firebase and GCP projects with budgeting and cost allocation.
