Update README.md
Signed-off-by: Geoff Seemueller <28698553+geoffsee@users.noreply.github.com>
This commit is contained in:
30
README.md
30
README.md
@@ -1,25 +1,21 @@
|
||||
# toak
|
||||
it's no joke
|
||||
# code-tokenizer
|
||||
|
||||
|
||||
[](https://www.npmjs.com/package/toak)
|
||||

|
||||

|
||||
[](https://www.gnu.org/licenses/agpl-3.0.html)
|
||||
|
||||
## Overview
|
||||
|
||||
`toak` is an intentionally simple yet powerful tool that processes git repository files, cleans code, redacts sensitive information, and generates markdown documentation with token counts using the Llama 3 tokenizer.
|
||||
`toak` is a cli tool, nameed for phonetics, that processes git repository files, cleans code, redacts sensitive information, and generates a `prompt.md` with token counts using the Llama 3 tokenizer.
|
||||
|
||||
```shell
|
||||
$ cd your-git-repo
|
||||
$ npx toak
|
||||
```
|
||||
|
||||

|
||||

|
||||
|
||||
## Philosophy
|
||||
1. _Human-first_ technologies for a better future.
|
||||
2. If you don't like the name...good.
|
||||
---
|
||||
|
||||
## Features
|
||||
|
||||
@@ -29,14 +25,10 @@ $ npx toak
|
||||
- Redacts sensitive information (API keys, tokens, JWT, hashes)
|
||||
- Counts tokens using llama3-tokenizer-js
|
||||
- Supports nested .toak-ignore files
|
||||
|
||||
### Token Cleaning
|
||||
- Removes single-line and multi-line comments
|
||||
- Strips console.log statements
|
||||
- Removes import statements
|
||||
- Cleans up whitespace and empty lines
|
||||
|
||||
### Security Features
|
||||
- Redacts API keys and secrets
|
||||
- Masks JWT tokens
|
||||
- Hides authorization tokens
|
||||
@@ -45,16 +37,8 @@ $ npx toak
|
||||
|
||||
## Requirements
|
||||
|
||||
- Node.js (>=14.0.0)
|
||||
- Git repository
|
||||
- Bun runtime (for development)
|
||||
|
||||
## Installation
|
||||
|
||||
```bash
|
||||
npm install toak
|
||||
```
|
||||
|
||||
- npm/bun/yarn/pnpm
|
||||
|
||||
## Usage
|
||||
|
||||
### CLI
|
||||
|
Reference in New Issue
Block a user