klabo joelklabo

1) Prime Claude with `/init`

I started by running /init so Claude reads the repo and rewrites CLAUDE.md with real project affordances: how to run one test with xcodebuild, where Vice models live, what Swift 6.1 concurrency rules we enforce, and the bundle/CloudKit facts. I cut redundancy, kept only the sharp bits, and verified with CI. This establishes a trustworthy "ops manual" Claude sees first, not tribal memory.

Why: if the source of truth is precise, agents stop hallucinating paths/flags.

2) Level up Claude Code (settings, commands, hooks, nested docs)

Next pass: I mapped the whole Claude Code surface (settings, slash commands, MCP hooks, status line, nested CLAUDE.mds). Then I added:

.claude/settings.json — status line, model prefs, environment, and hook wiring.
Custom commands as the primary UX: small, composable, documented.

Complete iOS Project Claude Code Setup - Master Prompt

IMPORTANT: This comprehensive setup will transform any iOS project into a fully automated, context-aware, self-maintaining Claude Code environment. This prompt is designed specifically for Claude Code (claude.ai/code) users.

PHASE 0: Prerequisites & Environment Verification

0.1 Check Required Tools

Before starting, verify these tools are installed:

	sudo apt-get update
	sudo apt-get install -y \
	autoconf automake build-essential git libtool libgmp-dev libsqlite3-dev \
	python3 python3-pip python3-mako net-tools zlib1g-dev libsodium-dev gettext \
	nodejs npm
	pip3 install --upgrade pip
	pip3 install --user poetry

	sudo apt-get install snapd
	sudo snap install bitcoin-core

	joel@lightning:~/code/lnprototest$ make check PYTEST_ARGS='--runner=lnprototest.clightning.Runner'
	pytest --runner=lnprototest.clightning.Runner
	========================================================== test session starts ==========================================================
	platform linux -- Python 3.8.10, pytest-6.1.2, py-1.10.0, pluggy-0.13.1
	rootdir: /home/joel/code/lnprototest
	plugins: rerunfailures-9.1.1, flaky-3.7.0, timeout-1.4.2, xdist-2.2.1, forked-1.3.0
	collected 26 items

	tests/test_bolt1-01-init.py .. [ 7%]
	tests/test_bolt1-02-unknown-messages.py . [ 11%]

	//
	// Shape_04ViewController.m
	// Shape_04
	//
	// Created by test on 9/4/09.
	// Copyright __MyCompanyName__ 2009. All rights reserved.
	//

	#import "Shape_04ViewController.h"

	Latency Comparison Numbers Time Light Distance Approximate Light Distance
	-------------------------- ---- -------------- --------------------------
	L1 cache reference 0.5 ns 0.15 m Diagonal across your smartphone
	Branch mispredict 5 ns 1.5 m Height of Natalie Portman
	L2 cache reference 7 ns 2.1 m Height of Shaq
	Mutex lock/unlock 25 ns 7.5 m Height of a school flag pole
	Main memory reference 100 ns 30 m Half a Manhattan city block (North/South)
	Compress 1K bytes with Zippy 3,000 ns 900 m Width of Central Park
	Send 1K bytes over 1 Gbps network 10,000 ns 3,000 m Width of Manhattan
	Read 4K randomly from SSD* 150,000 ns 45,000 m NYC to Hempstead on Long Island

	FROM THIS:


	describe('.setCurrentUser', function (){
	it('creates message types for the user', function (){
	yam.setCurrentUser({
	id: 1
	, attachments: [
	{ app_id: 'praise', name: 'foo' }
	, { app_id: 'polls', name: 'bar' }

	// Logging 'load' event
	this._yammerClient.reportEvent({
	success: function(data){ console.log('successfully logged "load"') },
	error: function(data){ console.log('failed to log', data) },
	data: {
	events: yam.json.stringify([{ name: 'desktop_session', properties:
	{ type: 'load',
	version: this._settings._config.siteVersion.current
	}
	}])

	if (!params.type \|\| (params.type == 'following' && yam.currentUser.treatments.algo_feed)) {
	// users may have hardlinked /threads/index?type=following
	// so we want to check and show the preferred feed instead
	params.type = yam.currentUser.getPreferredFeedType();
	}