Rhet Turnbull RhetTbull

Beast Mode

Beast Mode is a custom chat mode for VS Code agent that adds an opinionated workflow to the agent, including use of a todo list, extensive internet research capabilities, planning, tool usage instructions and more. Designed to be used with 4.1, although it will work with any model.

Below you will find the Beast Mode prompt in various versions - starting with the most recent - 3.1

Installation Instructions

Go to the "agent" dropdown in VS Code chat sidebar and select "Configure Modes".
Select "Create new custom chat mode file"

<core_identity> You are an assistant called Cluely, developed and created by Cluely, whose sole purpose is to analyze and solve problems asked by the user or shown on the screen. Your responses must be specific, accurate, and actionable. </core_identity>

<general_guidelines>

NEVER use meta-phrases (e.g., "let me help you", "I can see that").
NEVER summarize unless explicitly requested.
NEVER provide unsolicited advice.
NEVER refer to "screenshot" or "image" - refer to it as "the screen" if needed.
ALWAYS be specific, detailed, and accurate.

macOS Live Text has a very good quality/speed tradeoff.

Compared to Tesseract, it has much higher quality and is up to 3x as fast.

🖥️ See Demo

3.5 fps, Paperwhite 3
@adtac_

step 1: jailbreak your Kindle

mobileread.com is your best resource here, follow the instructions from the LanguageBreak thread

I didn't really follow the LanguageBreak instructions because I didn't care about most of the features + I was curious to do it myself, but the LanguageBreak github repo was invaluable for debugging

	#!/usr/bin/env bash

	# venv.sh - Initialize a uv-based venv for a Python repo with direnv integration

	set -e

	# Remove .python-version if it exists
	if [ -f ".python-version" ]; then
	echo "🧹 Removing existing .python-version"
	rm .python-version

	# /// script
	# requires-python = ">=3.12"
	# dependencies = [
	# "pyobjc-core",
	# "pyobjc-framework-CoreLocation",
	# "click"
	# ]
	# ///
	"""Basic geocoding using CoreLocation on macOS."""

	# /// script
	# dependencies = [
	# "pyobjc-core",
	# "pyobjc-framework-CoreLocation"
	# ]
	# ///
	"""Get named timezone for a location on macOS using CoreLocation

	To use this script, you need to have pyobjc-core and pyobjc-framework-CoreLocation installed:

	import Foundation
	import Photos

	func requestPhotoLibraryAccess(completion: @escaping (Bool) -> Void) {
	PHPhotoLibrary.requestAuthorization { status in
	completion(status == .authorized)
	}
	}

	func fetchFavoritePhotos(startDate: Date) -> PHFetchResult<PHAsset> {

	-- Export images from Photos via automated GUI manipulation
	-- It's an unsavory approach, but no other means of automation seems to yield higher quality edited image exports (so far)
	-- Arguments are passed in their order of appearance in the GUI, and expect values exactly matching the UI strings in Photos.app
	-- Accepts an individual photo UUID, or an album UUID (use osxphotos query to look up UUIDs)

	on run { uuid, exportDirectory, photoKind, jpegQuality, tiffBitDepth, colorProfile, photoSize, maxSizeType, maxSizeValue, includeMetadata, includeLocation , fileName, sequentialPrefix, subfolderFormat}

	tell application "System Events"
	set wasRunning to (name of processes) contains "Photos"
	end tell

	import mmap


	def get_last_lines(path: str, count: int) -> list[str]:
	"""Get count last lines from a file."""
	with open(path, "r+b") as text_file:
	text_mmap = mmap.mmap(text_file.fileno(), 0, mmap.ACCESS_READ)
	position = len(text_mmap)
	while count and (position := text_mmap.rfind(b"\n", 0, position)) != -1:
	count -= 1