Jony SuperJony

Complete the next task from the plan in docs/start-here.md

Please look at docs/start-here.md and follow the instructions. Your job is to get the next task done. Ultimately, you are the one guiding the work and making sure it meets what it's supposed to do. Chunk the work into small pieces, when it's helpful.

First, review the necessary files, think carefully, review more, and then create a plan to create the next chunk of work. Output your plan for approval by me (the user) before proceeding. Pause after outputting the plan to wait for my input.

Then, after we discuss and the plan is approved, execute the plan to finish the task. Use subagents when helpful. Mark the tasks as "in progress" to let other developers know you are working on them.

When you are done with the next task, say you are done and that we are ready to commit the work.

Chat GPT "DAN" (and other "Jailbreaks")

	## Stack:
	## Tanstack Start
	## Infra: Alchemy / Cloudflare
	## UI: Shadcn
	## Store: Zustand
	## DB Drizzle

	## Commands

	- Dev Server: pnpm dev (runs Alchemy dev with hot-reload; uses .env.dev)

	#!/bin/bash
	set -euo pipefail
	trap 'echo "at line $LINENO, exit code $? from $BASH_COMMAND" >&2; exit 1' ERR

	# This is a Claude Code hook to stop it saying "you are right".
	#
	# Installation:
	# 1. Save this script and chmod +x it to make it executable.
	# 2. Within Claude Code, /hooks / UserPromptSubmit > Add a new hook (this file)
	#

	<artifacts_info>
	The assistant can create and reference artifacts during conversations. Artifacts are for substantial, self-contained content that users might modify or reuse, displayed in a separate UI window for clarity.

	# Good artifacts are...
	- Substantial content (>15 lines)
	- Content that the user is likely to modify, iterate on, or take ownership of
	- Self-contained, complex content that can be understood on its own, without context from the conversation
	- Content intended for eventual use outside the conversation (e.g., reports, emails, presentations)
	- Content likely to be referenced or reused multiple times

	//
	// ContentView.swift
	// MeshGradientPlayground
	//
	// Created by Bill Richards on 6/14/24.
	//

	import SwiftUI

	struct ContentView: View {

	import SwiftUI

	// Remember to download FontSettings.swift

	struct WWDC24AnimatedTextView: View {
	var text = "Hello, World!"
	var animation: Animation = .easeInOut
	var targetFontSize: CGFloat = 40
	var minimumFontSize: CGFloat = 30
	var targetFontWeight: Font.Weight = .semibold

	{
	"messages": [
	{
	"content": "You are an advanced, reliable, candid AI system that takes user search queries, converts them into questions, and answers them, using specific facts and details sourced from webpages to prove your answer. You admit when you're unsure or don't know, and you never make a statement without providing a fact or instance to back it up. You answer questions directly and clearly, then provide more detail later. You follow the JSON schema exactly.",
	"role": "system"
	},
	{
	"content": "# CONTEXT\nCurrent date: #{DATE_TIME}.\n\nHere are result from a web search for '#{QUERY}':\nBEGIN WEB PAGE #{HOST_1} #{MARKDOWN_1}END WEB PAGE\nBEGIN WEB PAGE #{HOST_2} #{MARKDOWN_2}END WEB PAGE\nBEGIN WEB PAGE #{HOST_3} #{MARKDOWN_3}END WEB PAGE\nBEGIN WEB PAGE #{HOST_4} #{MARKDOWN_4}END WEB PAGE\nBEGIN WEB PAGE #{HOST_5} #{MARKDOWN_5}END WEB PAGE\nBEGIN WEB PAGE #{HOST_6} #{MARKDOWN_6}END WEB PAGE",
	"role": "system"
	},

	const sleep = ms => { return new Promise(resolve => setTimeout(resolve, ms)) }


	const injectButton = async () => {
	// Similiarly, we also need to wait for the page to load in...
	await sleep(1000);
	console.log("hey");
	const {url} = await fetch("https://bhchiang--get-url-get.modal.run/").then(r => r.json());
	const URL = `${url}/get_prompt`;

	import * as React from "react";
	import { useMousePosition } from "~/hooks/useMousePosition";

	/** Component to cover the area between the mouse cursor and the sub-menu, to allow moving cursor to lower parts of sub-menu without the sub-menu disappearing. */
	export function MouseSafeArea(props: { parentRef: React.RefObject<HTMLDivElement> }) {
	const { x = 0, y = 0, height: h = 0, width: w = 0 } = props.parentRef.current?.getBoundingClientRect() \|\| {};
	const [mouseX, mouseY] = useMousePosition();
	const positions = { x, y, h, w, mouseX, mouseY };
	return (
	<div