Jamon Holmgren jamonholmgren

Agent Setup -- how I approach setting up a project for AI coding

I've reached a pretty solid workflow for getting the most from agents in my code base. This setup and workflow has significantly reduced how often I have to fix obvious issues caused by agents doing the wrong thing.

This entire guide was hand-written by me, Jamon, with no AI-generated text nor any AI-suggested text or review. Fully human-generated.

Philosophy

My philosophy is based on these concepts:

Instructions for humans

Lessons learned on how to use AI agents effectively. In no particular order. Edited from time to time.

Pay down tech debt immediately

With agents, there should be no such thing as “tech debt”. An agent should simply pay down every bit of tech debt before presenting you with the “finished work”. Unlike humans, agent time is not very valuable; it can continue to work on something until it’s done, and shouldn’t make concessions assuming human constraints.

If an agent tells you that it’s “leaving something for later”, tell it to go finish it first before saying it’s done.

Set up homebrew on a Standard User account

Per: https://x.com/jamonholmgren/status/2043385696535331324

mkdir -p "$HOME/homebrew"
git clone https://github.com/Homebrew/brew "$HOME/homebrew/.linuxbrew/Homebrew"
mkdir -p "$HOME/homebrew/bin"
ln -s "$HOME/homebrew/.linuxbrew/Homebrew/bin/brew" "$HOME/homebrew/bin/brew"
# Homebrew (per-user)

AGENTS

Mode

Determine your mode from the user's request before doing anything else:

Plan — User describes a feature, bug, or idea. The Project Manager reads GAME_DESIGN + PROGRESS + TODOS, consults relevant experts to flesh out the plan, produces concrete steps, creates/updates TODO entries, and stops for user review. No code yet.
Build — User says "do this" or points at a specific TODO. The Project Manager identifies which experts and docs are relevant, gets their input on approach, then implements. After implementation, experts review and the PM runs the quality checklist. Lint and commit.
Review — User asks for review, or you're finishing a build. The Project Manager runs relevant experts against recent changes and produces a structured report with an overall assessment.
Loop — User explicitly requests the agent loop. Read Docs/AGENT_LOOP.md and follow it.

Infinite Red preferred podcast hardware

(as of March 20, 2024)

Yamaha AG03 3-Channel Mixer / 1 Microphone $150

Electro-Voice RE320 Large Diaphragm Dynamic Vocal Microphone $200 used, $300 new.

How to reinstall iOS on an iPhone X where the touchscreen is unresponsive

My daughter's iPhone X got into a state where the touchscreen didn't respond to any touches. We force-restarted it several times by doing the "Up Volume, Down Volume, Hold Power" sequence, but it did not work -- the touchscreen stayed unresponsive.

I plugged it into my Mac with a lightning cable and went to Finder (because iTunes isn't available anymore). Clicking on the iPhone asks me to Trust it, but clicking Trust just results in a spinner. I think it wanted me to log into the iphone and tap Trust there, but of course I can't -- the touchscreen wasn't responding.

So, I figured out this alternative sequence.

Running Objective-C (sorta) from JavaScript directly

To do this:

const result = invokeObjC(`[[NSString stringWithString:[[[@[@"One", @"Two", @"Three"] mutableCopy] addObject:@"Four"] componentsJoinedByString:@" | "]] uppercaseString]`)
console.log(result) // "ONE | TWO | THREE | FOUR"

I don't know how useful this will be. But ... it was enjoyable to play with!

	#!/usr/bin/env bash
	set -euo pipefail

	# Downloads the latest Terrain3D build artifacts from the main branch
	# and installs them into addons/terrain_3d/.
	# Can be run from the project root or any subfolder.

	REPO="TokisanGames/Terrain3D"
	ARTIFACT_NAME="Terrain3D"

	# This class should be added as an autoload called "Sync".
	# This is an efficient way to sync data to other players.
	#
	# Usage in a node:
	# func _ready():
	# Sync.enable(self)
	#
	# func on_sync(p: Sync.SyncPack) -> void:
	# # All data is always collected
	# global_transform = p.sync(global_transform)

	mkdir -p "$HOME/homebrew"
	git clone https://github.com/Homebrew/brew "$HOME/homebrew/.linuxbrew/Homebrew"
	mkdir -p "$HOME/homebrew/bin"
	ln -s "$HOME/homebrew/.linuxbrew/Homebrew/bin/brew" "$HOME/homebrew/bin/brew"
	# Homebrew (per-user)
	eval "$($HOME/homebrew/bin/brew shellenv)"
	# Put casks in your user ~/Applications so we never need sudo
	export HOMEBREW_CASK_OPTS="--appdir=$HOME/Applications"
	mkdir -p "$HOME/Applications"
	# Reload shell