npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@brngdsn/tacos

v0.2.1

Published

Token And Context Output Summarizer

Readme

🥑 Tacos - Token And Context Output Summarizer

Tacos Logo

Tacos is a CLI tool that recursively analyzes files and directories, estimating token counts and cost metrics for AI model inference. It supports modern Node.js (v20.8.0) and ECMAScript 2024, utilizing OpenAI's tokenizer for accurate token estimation.

📌 Features

  • 📂 Recursive File Traversal: Use -r or --recursive to analyze all files within directories.
  • 🔍 Token & Cost Estimation: Computes input/output costs based on AI model pricing.
  • 🎨 Colorized Output: Uses chalk to highlight token counts, costs, and cumulative values.
  • 🏗 Model Selection: Supports various models including GPT-4o, GPT-3.5, and OpenAI’s text embedding models.
  • 🚀 Extensible: Easily adaptable with additional models or pricing structures.

🚀 Installation

Ensure you have Node.js v20.8.0 installed (as defined in .nvmrc).

npm install -g @brngdsn/tacos

🛠 Usage

🔹 Basic Usage

tacos

This scans the current directory and displays file sizes, token counts, and estimated costs.

🔹 Recursive Traversal

tacos -r

or

tacos --recursive

This traverses directories recursively and shows cumulative token/cost summaries.

🔹 Recursive Collapse (Summarized)

tacos -x

or

tacos --recursive-collapse

Instead of listing all files, this aggregates directory contents into a single summarized entry.

🔹 Custom AI Models

tacos gpt-4o mini

Overrides the default AI model used for cost calculations.

🔹 Display Cost Table

tacos -c

Shows model pricing details.

📊 Output Example

Size       Name                      Tokens     Input Cost   Output Cost   
10.2KB     app.js                     2.1k       $0.0003      $0.0012
14.6KB     index.html                  3.2k       $0.0005      $0.0020
---------
17.8MB     [Cumulative]               450.2k     $0.0675      $0.2701
  • Cumulative Rows swap text/background colors.
  • Ignored files (from .gitignore, .tacosignore) are grayed out.
  • Directories are shown in blue.

🛠 Development

Clone the repository and install dependencies:

git clone https://github.com/brngdsn/tacos.git
cd tacos
npm install

Run locally:

node bin/tacos.js

Run with custom models:

node bin/tacos.js gpt-4o mini

📜 License

MIT License. See LICENSE for details.

📬 Contact & Issues


🥑 Made with Tacos