Dave Hardy davehardy20

The Software Factory Playbook — Dex Horthy's 4-gate workflow as a skill

A Claude Code Agent Skill built from Dex Horthy's (HumanLayer) playbook on David Ondrej's podcast.

"Once the model has written thousands of lines of code, it is harder to change. The sessions that generate design docs are context-light — you get the most model intelligence when you do the hard thinking early."

By default, agents build horizontally: all the backend, then all the frontend, then a 2,000-line diff lands in your lap and reviewing it is your problem. This skill flips that. Every decision that matters gets made before the code exists — where changing your mind costs a sentence, not a rewrite.

What it does

name

edr-reverse-engineering

description

Standardized workflow for reverse engineering endpoint security products, including extraction, decompilation, rule and model recovery, vulnerability analysis, detection gap analysis, proof-of-concept planning, live probes, and stakeholder reports. Use when Claude is asked to analyze an endpoint detection and response product, endpoint protection agent, security sensor, antivirus engine, or similar endpoint security package from installer artifacts, extracted binaries, live systems, or prior workspace outputs.

EDR Reverse Engineering

Use this skill to run a complete, repeatable reverse-engineering workflow for endpoint security products. Apply the same structure to every product so outputs can be compared across analyses and future work can resume without rediscovery.

OpenClaw after 50 days: all prompts

Companion prompts for the video: OpenClaw after 50 days: 20 real workflows (honest review)

These are the actual prompts I use for each use case shown in the video. Copy-paste them into your agent and adjust for your setup. Most will work as-is or the agent will ask you clarifying questions.

Each prompt describes the intent clearly enough that the agent can figure out the implementation details. You don't need to hand-hold it through every step.

My setup: OpenClaw running on a VPS, Discord as primary interface (separate channels per workflow), Obsidian for notes (markdown-first), Coolify for self-hosted services.

name	orchestrating-swarms
description	Master multi-agent orchestration using Claude Code's TeammateTool and Task system. Use when coordinating multiple agents, running parallel code reviews, creating pipeline workflows with dependencies, building self-organizing task queues, or any task benefiting from divide-and-conquer patterns.

Claude Code Swarm Orchestration

Master multi-agent orchestration using Claude Code's TeammateTool and Task system.

OpenCode Plugins Guide

A comprehensive guide to writing plugins for OpenCode that extend agent behavior with hooks, custom tools, and event handling.

Quick Start

Create a TypeScript file in .opencode/plugin/ (project) or ~/.config/opencode/plugin/ (global)
Export a named plugin function
Restart OpenCode

Opencode plugin development guide

Generated with LLM assistance on 2 Nov 2025 with minimal human verification.

Overview

Opencode plugins extend the functionality of the Opencode AI assistant by allowing you to add custom tools, authentication providers, event handlers, and hooks into the core system. This guide covers how to create, configure, and distribute plugins.

Source files:

Ghostty Configuration

This document describes the configuration options for Ghostty, a terminal emulator. The following sections detail the various settings, grouped by category, with explanations and configuration options formatted for clarity and suitable for PDF export via Pandoc.

	---
	name: codebase-review-question-audit
	description: Perform a deep structured review of the codebase, identify ambiguities, risks, and missing decisions, and generate a QUESTIONS.md file to clarify architecture, behavior, security, performance, and refactoring concerns before implementation.
	version: 1.0.0
	phase: discovery
	produces: QUESTIONS.md
	next: questions-md-resolution-implementation
	---

	# Codebase Review Question Audit

	GET /beta/deviceLocalCredentials/[DEVICE-ID]?$select=credentials HTTP/1.1
	ocp-client-version: 1.0
	client-request-id: 96cbfa59-dbfc-4a92-b261-7f77bd8f4b9b
	ocp-client-name: Get-LapsAADPassword Windows LAPS Cmdlet
	User-Agent: Mozilla/5.0 (Windows NT 10.0; Microsoft Windows 10.0.22621; en-US) PowerShell/5.1.22621.963 Invoke-MgGraphRequest
	SdkVersion: graph-powershell/1.26.0, Graph-dotnet-1.25.1
	FeatureFlag: 00000047
	Cache-Control: no-store, no-cache
	Authorization: Bearer [AAD-JWT-HERE]
	Accept-Encoding: gzip

	#!/usr/bin/env python3
	#
	# detect whether the remote MSMQ service on 1801/tcp is enabled or not
	# by sending a valid message to the target
	#
	# resources:
	# https://learn.microsoft.com/en-us/openspecs/windows_protocols/ms-mqmq/b7cc2590-a617-45df-b6a3-1f31102b36fb
	# https://learn.microsoft.com/en-us/openspecs/windows_protocols/ms-mqqb/85498b96-f2c8-43b3-a108-c9d6269dc4af
	#