Humberto Gomez Lopez Hoijof

The Hoijof Process (v3)

The Hoijof Process is a structured, documentation-first software development methodology for AI-assisted projects driven from a terminal agent (e.g. Claude Code CLI). Its goal is to deliver complex, multi-phase work systematically — with high test coverage, transparent decisions, and a state that survives any single context window.

One sentence: treat the filesystem as the agent's long-term memory and the context window as RAM — and manage the boundary between them deliberately.

What this process does not promise: it does not "eliminate hallucinations." Grounding the agent in good, current documentation measurably reduces context drift and confident-wrong work. It does not replace human judgment, and stale docs are worse than no docs — which is why reconciliation (§5) is a first-class step, not an afterthought.

	# The Hoijof Process

	The "Hoijof Process" is a structured, documentation-first, and AI-friendly software development methodology designed to successfully deliver complex projects systematically with high test coverage and transparent decision-making. It is tailored to handle large context applications and maximize the efficiency of AI coding assistants.

	---

	## Quick Start (TL;DR)
	1. Check the Roadmap: Read the current Phase Roadmap to understand the next priority and overarching goal.
	2. Read/Write the Design Doc: Outline the "What" and the "Why" for the upcoming feature before any code is written. Get it approved.
	3. Follow the Implementation Plan: Execute the strict Test-Driven Development (TDD) loop task-by-task.

	[
	"King",
	"Lewis",
	"Black",
	"White",
	"Ames",
	"Warner",
	"Simpson",
	"Parker",
	"Suave",

	[
	"Amanda",
	"Laura",
	"Anne",
	"Jessica",
	"Lisa",
	"Bonita",
	"Angel",
	"Pat",
	"Yan-ping",

	[
	"Ryan",
	"Sergio",
	"Bill",
	"James",
	"Marty",
	"Angel",
	"Pat",
	"Toshiro",
	"Yan-ping",

	/* City population < 100,000 = listed once if the city is somehow important
	(i.e., biggest city in a U.S. state or territory, or most important city in a
	metropolitan area with over 200,000 people)
	100,000 < City population < 200,000 = listed once
	200,000 < City population < 400,000 = listed twice
	400,000 < City population < 600,000 = listed 3 times
	600,000 < City population < 1,000,000 = listed 4 times
	1,000,000 < City population < 5,000,000 = listed 5 times
	5,000,000 < City population = city listed 6 times and each of its 5 its boroughs listed 1-2 times
	Anyway, for states/territories without big cities their biggest city is listed once

	var femaleNames = ["Aekkein", "Erna", "Gica", "Iris", "Laen", "Oanei", "Urusla", "Unt", "Zy", "Giny", "Teni", "Tania",
	"Tenisa", "Falish", "Tirs", "Bera", "Boria", "Terkia", "Tronash", "Si", "Gi", "Ti", "Fi", "Di", "Mi", "Peli", "Irnia", "Beth",
	"Riven", "Vi", "Lio", "Nayeli"];

	var maleNames = ["Anttirnet", "Carnil", "Estiv", "Halt", "Hoijof", "Laen", "Lisiern", "Berin", "Ton", "Shome", "Regit",
	"Lurin", "Maers", "Musten", "Oanei", "Raesh", "Terio", "Unt", "Ust", "Redik", "James", "Loki", "Tem", "Regot",
	"Josh", "Tom" ,"Jei", "Lioth"];

	var surnames = ["Golpeo", "Anorda", "Severnin", "Part", "Kek-vek-loah", "Vaen", "Nerivin", "Haeshi", "Vin-ti-selh",
	"Ver-to", "Vintoret", "Da Teri", "Von Bien", "Maer", "Serisn", "Vintaren", "Bertis", "Tetirit", "Tornet", "Bellabi",

	body {
	background: red !important;
	font-size: 434px;
	}