Andrew Gerst Gerst20051

The Autonomous Agent Prompting Framework

This repository contains a disciplined, evidence-first prompting framework designed to elevate an Agentic AI from a simple command executor to an Autonomous Principal Engineer.

The philosophy is simple: Autonomy through discipline. Trust through verification.

This framework is not just a collection of prompts; it is a complete operational system for managing AI agents. It enforces a rigorous workflow of reconnaissance, planning, safe execution, and self-improvement, ensuring every action the agent takes is deliberate, verifiable, and aligned with senior engineering best practices.

I also have Claude Code prompting for your reference: https://gist.github.com/aashari/1c38e8c7766b5ba81c3a0d4d124a2f58

Reverse Engineering on macOS

Some notes, tools, and techniques for reverse engineering macOS binaries.

Basic Block Dude HTML and JavaScript Game

This is a basic implementation of Block Dude, an old TI-83/4 Calculator game. It's missing a few things intentionally and they're left as further exploration for the reader.

Further Exploration

More levels
Add more levels and have the next level start once the last one is finished

	#!/usr/bin/env zsh
	# Multi-project worktree manager with Claude support
	#
	# ASSUMPTIONS & SETUP:
	# - Your git projects live in: ~/projects/
	# - Worktrees will be created in: ~/projects/worktrees/<project>/<branch>
	# - New branches will be named: <your-username>/<feature-name>
	#
	# DIRECTORY STRUCTURE EXAMPLE:
	# ~/projects/

	# gtr ─ Git worktree helper
	#
	# Examples
	# --------
	# gtr create feature0 # add ~/code/worktrees/feature0 (branch claude/feature0)
	# gtr create feat1 feat2 # add two worktrees at once
	# gtr rm feature0 # remove the worktree directory
	# gtr cd feature0 # jump into the worktree directory
	# gtr claude feature0 # run `claude` while inside that worktree
	#

	# -----------------------------------------------------------------------------
	# AI-powered Git Commit Function
	# Copy paste this gist into your ~/.bashrc or ~/.zshrc to gain the `gcm` command. It:
	# 1) gets the current staged changed diff
	# 2) sends them to an LLM to write the git commit message
	# 3) allows you to easily accept, edit, regenerate, cancel
	# But - just read and edit the code however you like
	# the `llm` CLI util is awesome, can get it here: https://llm.datasette.io/en/stable/

	gcm() {

	0810 b' from '
	0678 b' ssh2'
	00d8 b'%.48s:%.48s():%d (pid=%ld)\x00'
	0708 b'%s'
	0108 b'/usr/sbin/sshd\x00'
	0870 b'Accepted password for '
	01a0 b'Accepted publickey for '
	0c40 b'BN_bin2bn\x00'
	06d0 b'BN_bn2bin\x00'
	0958 b'BN_dup\x00'

	# Author: Shubhang, 2023
	# Description: This Python script demonstrates how to visualize audio using NumPy, Matplotlib, and MoviePy.
	# It reads an audio file in WAV format, converts the audio samples to a NumPy array,
	# and creates a video animation from a plot of the audio samples.
	# The resulting video file shows the amplitude of the audio samples over time.



	import numpy as np
	import matplotlib.pyplot as plt

	from io import StringIO
	import sys
	from typing import Dict, Optional

	from langchain.agents import load_tools
	from langchain.agents import initialize_agent
	from langchain.agents.tools import Tool
	from langchain.llms import OpenAI

Andrew Gerst Gerst20051

The Autonomous Agent Prompting Framework

Reverse Engineering on macOS

Table of Contents

Basic Block Dude HTML and JavaScript Game

Further Exploration