Reconstructed from Danny Postma's talk How I Built My Own AgentOS on Claude's Agent SDK (So You Can Too) (2026). This document is both a product spec for a human and an implementation prompt for an AI coding agent. Build exactly this system. Do not invent features that are not specified here.
Role contracts and prompts in this file are reconstructed from the talk, not his verbatim files. Mark every reconstructed prompt in code comments and docs as such.
| ╭─── Claude Code v2.1.12 ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮ | |
| │ │ Tips for getting started │ | |
| │ Welcome back Jonny! │ Run /init to create a CLAUDE.md file with instructions for Claude │ | |
| │ │ │ | |
| │ │ ───────────────────────────────────────────────────────────────── │ | |
| │ ▐▛███▜▌ │ Recent activity |
| <?php | |
| // Karen Bot by @levelsio | |
| // | |
| // ask Claude Code or Cursor to adapt it to your city | |
| // mine is for Lisbon in Portuguese but it should work with any city and any language! | |
| // save it as council.php and add a Nginx route /council on your server to use it | |
| // make sure to add /council?key= and set a key below to use it privately | |
| // | |
| // more info: https://x.com/levelsio/status/2009011216132526407?s=20 |
| osascript \ | |
| -e 'tell application "Google Chrome"' \ | |
| -e 'set b to bounds of front window' \ | |
| -e 'set h to (item 4 of b) - (item 2 of b)' \ | |
| -e 'set v to execute active tab of front window javascript "JSON.stringify([window.innerWidth, window.innerHeight])"' \ | |
| -e 'set AppleScript'"'"'s text item delimiters to ","' \ | |
| -e 'set vList to text items of (text 2 thru -2 of v)' \ | |
| -e 'set vW to item 1 of vList as number' \ | |
| -e 'set vH to item 2 of vList as number' \ | |
| -e 'set chromeH to h - vH' \ |
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.
| <!DOCTYPE html> | |
| <html lang="en"> | |
| <head> | |
| <meta charset="UTF-8"> | |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> | |
| <title>Chat with Dolphin</title> | |
| <style> | |
| * { margin: 0; padding: 0; box-sizing: border-box; } | |
| body { | |
| font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif; |
| You are Lyra, a master-level AI prompt optimization specialist. Your mission: transform any user input into | |
| precision-crafted prompts that unlock AI's full potential across all platforms. | |
| ## THE 4-D METHODOLOGY | |
| ### 1. DECONSTRUCT | |
| - Extract core intent, key entities, and context | |
| - Identify output requirements and constraints | |
| - Map what's provided vs. what's missing |
| import { Stagehand } from "@browserbasehq/stagehand"; | |
| import fs from "fs"; | |
| import path from "path"; | |
| import Tesseract from "tesseract.js"; | |
| import { OpenAI } from "openai"; | |
| import dotenv from "dotenv"; | |
| dotenv.config(); | |
| const openai = new OpenAI({ |
| Security Measure | Description | |
|---|---|---|
| ☐ | Use HTTPS everywhere | Prevents basic eavesdropping and man-in-the-middle attacks |
| ☐ | Input validation and sanitization | Prevents XSS attacks by validating all user inputs |
| ☐ | Don't store sensitive data in the browser | No secrets in localStorage or client-side code |
| ☐ | CSRF protection | Implement anti-CSRF tokens for forms and state-changing requests |
| ☐ | Never expose API keys in frontend | API credentials should always remain server-side |
| #!/bin/zsh | |
| # WARNING! The script is meant to show how and what can be disabled. Don’t use it as it is, adapt it to your needs. | |
| # Credit: Original idea and script disable.sh by pwnsdx https://gist.github.com/pwnsdx/d87b034c4c0210b988040ad2f85a68d3 | |
| # Disabling unwanted services on macOS Big Sur (11), macOS Monterey (12), macOS Ventura (13), macOS Sonoma (14) and macOS Sequoia (15) | |
| # Disabling SIP is required ("csrutil disable" from Terminal in Recovery) | |
| # Modifications are written in /private/var/db/com.apple.xpc.launchd/ disabled.plist, disabled.501.plist | |
| # To revert, delete /private/var/db/com.apple.xpc.launchd/ disabled.plist and disabled.501.plist and reboot; sudo rm -r /private/var/db/com.apple.xpc.launchd/* | |
| # user |
