harryf

diff --git a/Keyboard/DirectionEnum.swift b/Keyboard/DirectionEnum.swift
index 5371350..3fcd9d4 100644
--- a/Keyboard/DirectionEnum.swift
+++ b/Keyboard/DirectionEnum.swift
@@ -6,13 +6,13 @@
 //  Copyright (c) 2014 Alexei Baboulevitch ("Archagon"). All rights reserved.
 //
 
-enum Direction: Int, CustomStringConvertible {
+public enum Direction: Int, CustomStringConvertible {

harryf

Verifying my Blockstack ID is secured with the address 1LTjWdry6oRq8bFCjEJ1egeikJD87Pedyo https://explorer.blockstack.org/address/1LTjWdry6oRq8bFCjEJ1egeikJD87Pedyo

harryf

#!/bin/sh

# Cron job
# 15 10 * * * /Users/<username>/bin/backup-passwords
# may need some hacks to get crontab running on OSX

DIR="$HOME/GoogleDrive/passwords"
PASSWDF="$DIR/passwords2.kdbx"
BACKUPF="$DIR/passwords2-"$(date "+%Y%m%d")".kdbx"

harryf

# Stir the cauldron at 135 beats per minute
use_bpm 135

# Shared sigils - when the light dies, all hearts go silent
set :stop_flag, false
set :master_amp, 1.0     # hidden hand that rules all volumes

# The ward that lets any loop vanish on command
define :check_stop do
  stop if get(:stop_flag)

harryf

#!/usr/bin/env python3

import sys
import re
import subprocess

# Usage:
#   echo "sha1..." | ./extract_function_history.py fin_toolkit/cli.py search
#   or
#   ./extract_function_history.py fin_toolkit/cli.py search sha1_file.txt

harryf

Claude Code Task System: ANTI-HYPE Agentic Coding (Advanced)

Overview

This video introduces Claude Code's new task system for multi-agent orchestration, demonstrating how to reliably create teams of agents that communicate, validate each other's work, and handle complex engineering tasks in parallel. The tutorial emphasizes foundational engineering principles over hype, showing how to build reusable, self-validating agent systems through template meta-prompts. This is a summary of the video with links to jump to relevant parts.

---

Getting Started: How to Run Agent Teams with Claude Code

harryf

TL;DR

This video introduces a powerful pattern for automating codebase setup and maintenance using Claude Code's new setup hook, JustFile command runner, and agentic prompts. The core idea: combine deterministic scripts with intelligent AI agents to create self-documenting, interactive installation and maintenance workflows that make onboarding new engineers instant instead of taking days.

Simple Example Anyone Can Try

Open Claude Code and type:

Create a simple "install" command that:

harryf

AI Techniques Distilled From Thousands of Hours of Real Work

This is a summary of a YouTube video by an experienced AI practitioner sharing battle-tested techniques for working effectively with large language models. Watch the original video

Overview

After thousands of hours building with AI for coding, writing, and planning, the creator has distilled six essential practices that solve the most common failure modes when working with LLMs. The key insight: AI will quietly drop requirements even when you're doing everything right—and these techniques help prevent that.

The Six-Step Process at a Glance

harryf

Making Codebases Agent Ready – Eno Reyes, Factory AI

Source

This is a summary of a conference talk by Eno Reyes from Factory AI about preparing codebases for AI agent integration. Watch the original video

Overview

The talk focuses on how organizations can prepare their codebases to maximize the effectiveness of AI coding agents. The key insight is that the limiting factor for AI agent success isn't the agents themselves, but rather the quality and comprehensiveness of automated validation in your codebase. By investing in rigorous validation criteria—tests, linters, documentation, and other automated checks—organizations can unlock 5-7x productivity gains rather than just 1.5-2x improvements.

Key Topics

harryf

Claude Opus 4.6 vs GPT-5.3 Codex

Source

This is a summary of a YouTube video featuring Greg and Morgan Linton comparing the newly released Claude Opus 4.6 and GPT-5.3 Codex models. Watch the original video

Overview

On a major AI release day, both Anthropic and OpenAI dropped competing coding models. This video provides a deep technical comparison between Claude Opus 4.6 and GPT-5.3 Codex through a practical head-to-head test: building a PolyMarket competitor from scratch. Rather than declaring a single winner, the hosts reveal that these models represent fundamentally different coding philosophies and use cases.