The creator of Claude Code just revealed his INSANE workflow
Alex Finn distills Boris Czerny's X thread into 7 executable Claude Code workflow steps — from parallel terminals to end-of-session verification.
January 6th 2026Alex Finn built a $300K/year app and 50K subscribers talking about one tool — here are the eight lessons nine months of 12-hour days actually taught him.
Nine months. Twelve hours a day. A $300K/year app and fifty thousand subscribers built almost entirely inside one tool. Alex Finn has probably logged more hours in Claude Code than anyone outside Anthropic — and the lesson he keeps hammering is the one nobody wants to hear: stop adding complexity.
stated at 00:32“Whether you're a day one beginner or you're an absolute Claude code professional, I promise you, you're going to learn a ton in this video and be a master by the end of it.”delivered at 19:00

Alex establishes authority: 9 months daily use, $300K/year app, 50K subscribers, 8 lessons nobody else talks about.

VS Code extension beats CLI-in-Cursor for stability and UX. Cursor is a fork; VS Code gets upstream updates first and has zero layout bugs. Free, no subscription.

Sub-agents, MCPs, 40 slash commands = content-farming noise. Sonnet 4.5 is smart enough to find docs on its own. 99.9% of users need nothing beyond a clear prompt.

With /model Haiku selected, Claude still uses Sonnet for plan-mode planning but drops to Haiku for implementation. Thorough Sonnet plan + Haiku execution = same quality, fraction of the cost.

80% of vibe-coding time is idle wait. YC's Plinko IDE = worst product ever made. Use idle time with a desktop AI chat as co-pilot CEO: feature roadmap, marketing, life decisions. Doom-scrolling is the alternative.

Nine rules that eliminate lazy loops and whack-a-mole bugs: structured todo plan, check-in before execution, step-by-step explanations, simplicity above all, DO NOT BE LAZY x2, no temporary fixes.

Complex context/UI/database/schema prompt templates are useless. Plan mode handles context discovery. Just tell it what you want. Simple natural language beats structured prompting every time.

Default Claude UI = blue and purple gradients, always. Fix: drag in a v0 design system screenshot or Pinterest app-design board image alongside any UI prompt. Screenshot = art direction Claude can actually follow.

Before plan mode, run brainstorm mode: ask Claude for options, what to add, what to change. Demo: asks about folder system, Claude suggests hashtag tagging — that idea wasn't Alex's, it came from Claude and made it into the app.

Three-point recap: keep it simple, don't waste downtime, the AI is smarter than you think. Subscribe, newsletter CTA, alexfinn.ai/subscribe.
Nine rules delivered as prompts in CLAUDE.md that prevent lazy loops, whack-a-mole bugs, and over-engineered solutions. Rules 8 and 9 are all-caps by design — it changes the model's behavior.
Before entering plan mode (shift-tab x2), first run a free-form brainstorm: ask Claude for options, what features to add, what it would change. Only then switch to plan mode with your chosen direction. Separates idea generation from execution planning.
Use /model to select Haiku. Claude Code still uses Sonnet for plan-mode planning (shift-tab x2), then drops to Haiku for the implementation pass. A thorough Sonnet plan is detailed enough for Haiku to execute without quality loss.
“Stop listening to all the gurus. You don't need to use every single feature inside Claude code.”
“I saw this tweet from Y Combinator yesterday, and it literally made me sick to my stomach.”
“If you spend 80% of your day scrolling TikTok, your brain's melting out of your ears.”
“Prompt engineering is the most overrated concept in history.”
“It's not just some junior dev going out writing code for you. It's your partner.”
“Sign up for the number one AI newsletter on planet Earth. It's completely free. Link down below. Alexfinn.ai/subscribe.”
Soft — recap comes first, then subscribe ask, then newsletter. No hard sell. Mirrors the video's 'keep it simple' ethos.
Alex's CLAUDE.md is the most copy-paste-ready artifact in the video — and the Brainstorm Mode → Plan Mode sequence is the single most underused pattern in Claude Code.
The single biggest productivity unlock isn't a new feature — it's changing how you use the 80% of time you spend waiting for the AI to finish.
00:00
00:22
00:37
00:52
01:07
01:22
01:37
01:52
02:07
02:22
02:36
02:51
03:06
03:21
03:36
03:51
04:06
04:21
04:36
04:51
05:06
05:21
05:36
05:51
06:06
06:21
06:36
06:51
07:06
07:21
07:35
07:50
08:05
08:25
08:35
08:50
09:05
09:20
09:35
09:50
10:05
10:18
10:35
10:50
11:05
11:20
11:35
11:50
12:05
12:20
12:34
12:49
13:04
13:19
13:34
13:53
14:04
14:19
14:34
14:49
15:02
15:24
15:37
15:49
16:04
16:19
16:34
16:49
17:04
17:19
17:33
17:48
18:03
18:18
18:33
18:48
19:03
19:18
19:33
19:48Alex Finn distills Boris Czerny's X thread into 7 executable Claude Code workflow steps — from parallel terminals to end-of-session verification.
January 6th 2026A 10-minute walkthrough of the Ralph Wiggum plugin — a while-loop wrapper that turns Claude Code into an autonomous agent that won't stop until your success criteria are met.
January 10th 2026A 13-minute verdict: CLI inside VS Code beats Cursor, the desktop app, and the extension — and a live app build is the receipt.
December 30th 2025A 31-minute build-along that teaches parallelization over prompting — spin up cloud agents, fill dead time with AI consultants, and ship an app with design, roadmap, and marketing done before you close your laptop.
November 4th 2025Ten quietly shipped Claude Code features Alex Finn says most people missed — from session naming and context visualization to YOLO mode and the plugin store.
December 22nd 2025A 23-minute walkthrough that takes a non-coder from zero to a working drag-and-drop calendar app using three undocumented Claude Code workflow secrets.
June 16th 2025