Forbes 30 Under 30 · Y Combinator
About David Iya
David Iya is the co-founder of Claude Code Club, the #1 community for learning Claude Code. He has shipped products that reached more than a million users across 30 different countries, generated over $70M in GMV, and raised more than $14M in venture funding - with over 18 years of experience in software.
A Forbes 30 Under 30 honoree and Y Combinator alumnus, David has spent his career turning raw ideas into real products. He now teaches builders to do the same with Claude Code - going from idea to shipped without writing code by hand.
Inside Claude Code Club he leads the build systems, go-to-market, and monetization playbooks members use to turn AI skills into real income.
Areas of expertise
Articles
Trello now ships its own hosted MCP server, so Claude Code can read and update your boards without a community plugin standing in the middle. Here's the setup, the exact permissions to grant, and the one thing the server still won't let it do no matter what you ask.
Atlassian runs its own official MCP server, so Claude Code can read a ticket, search a project, and leave a comment without you copying anything by hand. Here's the exact setup, the OAuth-versus-token choice, and the one reliability quirk to know about first.
GitHub runs its own remote MCP server, so Claude Code can read a repo, browse open issues and pull requests, and check CI status without you copying anything between tabs. Here's the setup, the one place it differs from Slack, Notion, and Linear, and the scope habit that keeps a token from seeing more than it should.
Linear ships and hosts its own MCP server, so Claude Code can read an issue's full description and comment thread, then update its status or leave a comment, without you copying anything between tabs. Here's the setup, what it's actually good for, and the scope habit that keeps it from touching more than it should.
As of August 14, 2026, Claude Code runs in auto mode by default on Pro, Max, and Team plans instead of asking permission before every action. Here is what the safety data actually shows, what the classifier still refuses to do no matter what, and the two switches that put you back in manual control.
Notion ships and hosts its own MCP server, so connecting Claude Code to your Notion workspace doesn't need a community plugin or a workaround. Here's the setup for both the hosted and self-hosted routes, what Claude Code can actually do once it's connected, and the sharing habit that keeps it from seeing more than it should.
The /design skill turns a written brief into a canvas of editable UI options, then builds the one you pick. It shipped as a research preview in August 2026, and it changes the first hour of a screen redesign from staring at a blank file to choosing between real options.
Connecting Claude Code to Figma means turning on Figma's Dev Mode MCP Server and pointing Claude Code at it, so it reads a design's real components, variables, and layout instead of guessing from a screenshot. Here's the setup, what actually transfers cleanly, and the manual check I still run before any of it ships to a client.
Claude Code now runs at claude.ai/code as a cloud session that keeps working after you close the tab and that you can check from your phone. Here's what it actually does, how it differs from the desktop app, and the three questions I ask before sending a task to the cloud instead of running it locally.
Refactoring is the one job where an agent can produce a beautiful diff that quietly changes what your app does. The fix is not a better prompt. It is a fence built before the first line moves, and a refactor cut into pieces small enough to check.
Claude Code reads images. Paste a screenshot of the broken layout instead of writing three paragraphs describing it. Here is how to get one in, what it can and cannot see, and the three-shot pattern that fixes things in one pass.
Claude Code runs natively on Windows, and for most people the desktop app is the whole setup. Here are the real requirements, when WSL is worth the trouble, and why the install command you pasted threw an error.
A WordPress plugin is one of the best first real builds, because the platform gives you the whole application and you only write the missing piece. Here is the process I use with Claude Code, the four questions to answer before you prompt, and the PHP-specific traps the agent will walk you into.
Claude Code is usually slow for one of three reasons: the context you are sending is too big, the tools it is running are the actual bottleneck, or you picked a heavier model than the task needs. Here is the Slow Loop Audit I run to find which one it is in about five minutes.
You can add authentication with Claude Code in an afternoon. The risk is that it looks finished and is not, because the login screen works while the server never checks anything. Here is the Auth Gate Checklist we run before any build with a login goes live.
Claude Code can write your README, your API reference, and your onboarding guide in minutes. The problem is that it will happily describe features you deleted last month. Here is the Read-Write-Prove loop I use so generated docs describe the code that actually exists.
A monorepo is the environment where Claude Code goes wrong most predictably, and the reason is not intelligence. It is scope. Here is the package-scoped session rule I use to keep an agent working on one part of a big repo without dragging the other twenty into context.
An MCP server that shows as failed is almost always one of five things, and none of them require you to understand the protocol. Here is the order to check them in, and how to read the error you actually got.
Getting a first deploy out is easy. Keeping every deploy after that from quietly overwriting someone else's work is the part nobody warns you about. Here is the deploy contract I hand Claude Code before it ships anything, and the two failure modes that cost me the most time.
How to install the Claude Code GitHub Action, the difference between interactive and automation mode, the permissions the workflow actually needs, and the cost controls that keep a runaway agent from eating your budget.
Claude Code reads CLAUDE.md, not AGENTS.md. If your repo standardized on AGENTS.md for another coding agent, Claude Code skips it silently - no error, no warning, just a session running with none of your project rules. Here is the one-line import that keeps both tools on the same source file.
A 400-line CLAUDE.md burns context in every session and gets followed less the longer it grows. The .claude/rules directory fixes both problems by letting you scope instructions to the files they apply to, so your API rules only load when Claude is actually reading API code.
The Claude desktop app runs full Claude Code sessions - parallel builds, a diff viewer, a browser pane, connectors - inside a normal window, with no terminal required to start. Here is what the Code tab actually gives you and how we teach members to use it.
The standalone /output-style command is gone - deprecated in Claude Code v2.1.73 and removed in v2.1.91. If a guide still tells you to type it, that guide is out of date. Here is how output styles actually work now, and how we use them for client work.
An MCP server for Claude Code is a small program that hands the agent new tools and live data it did not ship with - your CRM, your internal API, your file format. Here is the minimal build, wired end to end, that I use when the ready-made servers do not cover what a client actually needs.
The permission prompt is not friction to switch off - it is the dial that decides how much Claude Code can do before it checks with you. Set it wrong and you either approve every keystroke or hand an agent the keys to your machine. Here is how the permission modes actually work and the setup I use for client work.
Claude Code vs Windsurf comes down to where the agent lives and how far it can reach. Windsurf is an AI-native editor built around its Cascade agent; Claude Code is a terminal-native agent that works alongside any editor and can run without you watching. Here is how to tell which one fits how you actually build.
Claude Code extended thinking gives the agent extra reasoning time before it answers, and you control how much through four escalating keywords: think, think hard, think harder, and ultrathink. Here is what each level actually buys you, and the CCC Effort Ladder I use to decide when it is worth the wait.
Claude Code runs on a usage allowance that resets on a rolling window, and the worst time to learn that is mid-build. Here is what actually happens when you hit the limit and the habits I run so it stops catching me off guard.
Both Claude Code and OpenAI Codex are agentic coding tools now, not autocomplete. I ran the same real client task through both to see which one actually gets to a working result with less babysitting, and which one I'd trust on a build I'm charging for.
Claude Code checkpoints every prompt automatically and /rewind can undo a bad session in seconds. Here is exactly what it does, the specific things it can't undo, and why I still commit to Git on every real build.
Claude Code's built-in sandbox restricts what Bash commands can read, write, and reach on the network, enforced by the operating system. It's the single best safety upgrade for running Claude Code with less hand-holding, but it protects less than most builders assume. Here's exactly what it covers.
Claude Code context management explained: how the context window works, what breaks it, and the exact habits I use to keep large projects running cleanly without the agent losing the plot.
Claude Code and GitHub Copilot are both AI coding tools but they do fundamentally different jobs. Copilot lives inside your editor and suggests the next line. Claude Code takes the whole task, plans it, writes the files, and runs the commands. I have used both and here is the honest breakdown of where each one wins.
Git worktrees let you run two Claude Code sessions on the same repository at the same time, each in its own directory and on its own branch. No file conflicts, no blocked agents waiting, no merge headaches mid-build. Here is how to set them up in two minutes.
Building a dashboard with Claude Code starts with the data, not the design. Tell Claude Code what numbers you need to track, paste in a sample of your data, and it generates the component structure, wires in the charts, and handles the responsive layout. You direct; it builds.
Most Claude Code beginners jump straight to building. The ones who get better results start with a planning pass first. Here is the plan-first workflow I use on every project above a few hours, and how to prompt Claude to think through the whole build before it writes a single line of code.
Claude Code writes code fast, and without a commit rhythm you can lose hours of working progress in one wrong command. Here is the branch strategy, commit pattern, and four rules I follow on every build to keep AI-written code clean and recoverable.
Claude Code does not remember your project between sessions by default. Every new conversation starts from scratch. The memory bank changes that - here is how to use CLAUDE.md and a few supporting files to give Claude permanent context on any project.
The right way to manage .env files with Claude Code is to keep secrets out of the conversation entirely. Set up your environment variables before the session starts, reference them by name in prompts, and never paste a live key into the chat. Here is the Safe Env Pattern I use on every project.
Running parallel Claude Code agents means deliberately opening two or more sessions to work on separate tasks simultaneously - not waiting for one to finish before starting the next. The Fork Method is the system I use to decide when to split work across sessions and how to keep them from colliding.
Claude Code forgets everything when a session ends. The Memory Bank is a two-file system that gives it persistent context, so every new session starts informed instead of blank. Here is how to set one up in ten minutes.
You can build a real Next.js app with Claude Code from the desktop app, no terminal expertise required. Here is the Next.js Build Loop I use to go from a blank project folder to a live URL in a single working session.
Adding Stripe payments to a Claude Code project is a four-step integration you can describe in plain English and have working in an afternoon. Here is the Stripe Integration Stack I use to wire up real payments without touching the code by hand.
Leaving Claude Code to work on its own overnight sounds like the dream. I tried it on an actual client build and learned exactly where it saves you hours and where it quietly wanders off. This is the Leash Loop I use to get unattended work without waking up to a mess.
Skills and MCP servers both extend Claude Code, and people mix them up constantly. They solve different problems. Here's the plain-English difference, the Skill-or-Server Test I run before building either, and the mistakes that make people reach for the wrong one.
Most people open Claude Code, poke around, and never get it configured to actually help them. This is the Day-One Stack I walk every new member through - the plan to buy, the desktop app choice, and the two files that make Claude useful from your first real session instead of your tenth.
Everyone has an opinion on how to prompt Claude Code. I stopped arguing and ran the test: I built the exact same feature three times with three different prompt styles - terse, detailed spec, and plan-first. One clearly won. Here's the whole experiment and what it means for how you prompt.
The fastest way to stop Claude Code from confidently shipping broken code is to make it write the test first. When the test exists before the code, the agent has a target it cannot fake its way past. Here is the Red-Green-Verify loop I use to get working code on the first pass.
Subagents let Claude Code spin up separate agents that each own a task and run at the same time. Used well they cut a multi-part build from an afternoon to an hour. Used badly they make a mess in parallel. Here is the Delegate-Verify loop I use to get the speed without the chaos.
CLAUDE.md is the project memory file Claude Code reads at the start of every session. Set it up once with your conventions, guardrails, and always/never rules and Claude walks in already briefed - no re-explaining, no drift, no wasted back-and-forth on every new chat.
The safe way to connect Claude Code to a database is through a read-only MCP server, not by pasting rows into a prompt. Here is the exact setup I use - a least-privilege database user, an MCP bridge, and a few hard rules - so Claude can read your schema and answer questions about your data without ever being able to break it.
Claude Code is easy on a fresh repo and overwhelming on a 200-file legacy one. Here is the exact workflow I use to point it at a large existing codebase - CLAUDE.md, scoped exploration, and small verified edits - so it ships correct changes instead of confidently breaking things.
Most people never touch settings.json and let Claude Code run on defaults. Here is the exact config file I drop into every repo - permissions, hooks, model, and env - so every project starts safe, fast, and consistent instead of me babysitting the same prompts.
Slash commands are saved prompts you trigger by typing a slash and a name - a way to run your best multi-step workflow in one keystroke instead of retyping it every time. Here are the custom commands I built for client work, exactly how I wrote them, and the ones that actually earn their place in my day.
Most people write one vague line and wonder why Claude Code guessed wrong. Here is the exact three-part prompt I use - goal, context, constraints - to get the right result on the first try instead of the fifth.
Plan Mode is Claude Code's read-only research mode - it reads your codebase and writes a step-by-step plan for your approval before it touches a single file. Here's the exact loop I run on every client build to catch the wrong approach in a plan I can edit in seconds, instead of in code I'd have to rip out an hour later.
Claude Code can write a whole feature in one turn, but shipping it blind is how you burn a client. Here is the exact review pass I run on every build - what I read first, what I never trust, and how I keep it fast.
Most Claude Code hooks look clever and then get deleted a week later. After running them on real client builds, here are the three hooks I actually kept, the ones I dropped, and how to add your first one without breaking anything.
MCP servers are how Claude Code reaches past your code and into your real tools. Here are the best Claude Code MCP servers to install first, grouped by what they let the agent actually do - from your repos and the live web to browsers, databases, and your workspace.
Claude Code subagents let you launch several specialized agents from one session, each with its own clean context. Here is what they are, when to reach for them, and how to brief them so a whole team of agents works on your project at once.
Learn how to build a chatbot with Claude Code from scratch - pick the type, describe the behaviour in plain English, connect it to a real interface, and deploy it so it runs without your laptop.
Learn how to build a mobile app with Claude Code even if you have never shipped one - choose the right approach, describe the app in plain English, preview it on your own phone, and get it ready for the app stores.
You can build a budget tracker with Claude Code even if you have never written code. Follow the Budget Blueprint to turn your income and spending into a clear picture of where your money goes.
The best Claude Code tips for beginners are habits, not tricks. Follow the Ten Starter Habits to go from opening the app for the first time to shipping something small and real.
A save-worthy list of ten real, finishable projects you can build with Claude Code - five personal tools to build this week, and five you can build to get paid - each described in plain English with who it is for and why it is worth building.
A plain-English walkthrough: plan the one action your page should drive, let Claude Code choose the stack and write every section, wire up a working form, and deploy it to a real URL - all through conversation, no design or coding background needed.
A command-line tool lets you run one command instead of repeating a chore by hand. This guide walks you through building a real bulk file renamer with Claude Code - from describing what you want to adding flags, a help message, and installing it so you can run it from anywhere.
A complete beginner's walkthrough: what a REST API actually is, how to plan your endpoints, let Claude Code choose and wire up the stack, add API key authentication, and deploy it to a live URL - all through plain conversation.
Learn how to build a Slack bot with Claude Code from scratch - covering Slack app setup, bot tokens, and wiring it all together through the Claude Code desktop app.
You can build a working Discord bot with Claude Code even if you have never written a line of code. Follow this walkthrough to go from an empty folder to a bot that is live in your server and doing a real job.
You can build an invoice generator with Claude Code even if you have never written code. Follow the Invoice Blueprint to turn your details into a clean, reusable invoice you can send in seconds.
You can build a web scraper with Claude Code even if you have never written a line of code. Follow the Polite Scrape method to pull the data you need from a page, safely and within the rules.
You can build a Telegram bot with Claude Code in a single afternoon. Follow the Bot in an Afternoon method to go from idea to a running bot, safely and step by step.
Claude Fable 5 is the most capable public Claude model, and you can start using it in the desktop app today. Here is how to turn it on, pick a job worth its power, and get a real result on your first run without wasting the included allowance.
Claude Fable 5 costs roughly double the Opus class per token, and in long agent runs those tokens compound fast. The fix is not avoiding Fable, it is using it deliberately. Here are five levers that cut the bill hard while keeping the results that made you reach for it.
Claude Fable 5 vs Opus 4.8 is not a close fight on paper, but it is the wrong question for most builds. Here is the honest split: what Fable's Mythos-class tier actually buys you, where Opus 4.8 is still the smarter call, and a simple two-question test for picking the right one every time.
Anthropic shipped Claude Fable 5, pulled it three days later under a US government export-control order, and redeployed it globally on July 1. Here is what actually changed, why it vanished and came back, and how to put the most capable public Claude model to work on a real build right now.
Learn how to automate spreadsheets with Claude Code using the Spreadsheet Handoff, a simple method to turn repetitive sheet work into a script that runs itself.
A Claude Code hook is a shell command the app runs automatically at set moments in a session, like right after an edit or before a tool runs. Here is what hooks are, the four moments they can fire, and two you can copy today to auto-format your code and protect files you never want touched.
A subagent is a second Claude Code instance that runs a job in its own context window and reports back. Here is what Claude Code subagents are, the three jobs they do well, how to spawn and build your own, and what the June 2026 update changed.
A simple Claude Code Git workflow that protects your work with save points. Learn the Safe Commit Loop, explained in plain English for non-technical builders.
Anthropic launched Claude Tag, a new way to put Claude inside Slack as a standing teammate you tag like any coworker. Here is what it does, who can use it today, and the standing-agent shift it points every builder toward.
You can build a Chrome extension with Claude Code even with no prior experience. Follow the Extension Starter Path to go from an idea to a working extension in your browser.
Most Claude Code mistakes are not about the tool, they are about how you brief it. Here are the 10 mistakes beginners make most, the exact fix for each, and the CCC brief, scope, verify framework that prevents almost all of them.
Learn how to debug with Claude Code using a repeatable five-step loop, so you stop guessing and start fixing bugs with calm, one change at a time.
These are the Claude Code slash commands I reach for every single day, what each one does in plain language, and when to use it. Save this as your quick reference, then build your own custom command on top.
A CLAUDE.md template is the single highest-leverage file in any Claude Code project, because it is the memory the agent reads every time it works. Here is the CCC project-brief skeleton plus 8 ready-to-paste CLAUDE.md templates, one per project type.
A Claude Code cheat sheet you can screenshot: the essential slash commands, the four core concepts (skills, subagents, MCP servers, hooks), and the CCC build flow I run every day. Plain-language purpose for each one, no fluff.
These are the 10 Claude Code prompts I run when I want a week of work done in a day - audit a codebase, write tests, fix a failing build, ship a feature, and more. Copy them, swap in your details, and run them in the desktop app today.
Claude Code agent loops are the engine behind the magic: the agent gathers context, acts, checks its own work, and repeats until the job is done. Here is what an agent loop is, the CCC loop framework, and how to run your first one today.
Claude Code vs Cursor is the wrong question until you know which one fits how you actually work. Here is a clear, honest comparison of the two, what each is best at, and a five-minute test to pick the right one.
Stuck on what to build? Here are 12 Claude Code project ideas sorted into three tiers, from a one-sitting starter to a self-running system, each with the exact first move so you actually finish.
Forgot to order something again? Good. A thing you build beats a thing you bought. Here are four Father's Day gifts you can ship this afternoon with Claude Code, even if you have never written a line of code.
A single survey of around 15,000 developers found Claude Code on top by a wide margin. The number is the hook. The real lesson is the why, and you can copy it whether or not the survey holds.
An agent is not magic and it is not months of work. It is a clear job, a subagent or two, and a few tools it can call. Here is how to build your first one this afternoon, start to finish.
As of June 15, 2026, headless Claude Code and Agent SDK runs stop counting against your Pro or Max limit. Here is what changed, which automations are affected, and the one thing you have to claim before it costs you.
Auto mode lets Claude Code take a whole sequence of actions while you watch from checkpoints. Here is what it actually changes, and how to use it without burning money or breaking something you cannot undo.
Most people stall at Level 1 and never realize there are four more above them. Here is the full progression, how to self-diagnose where you are, and the one concrete move that gets you to the next level.
Wire the n8n MCP server into Claude Code and it can read all 1,851 n8n nodes, build the workflow for you, and deploy it straight to your instance. Here is the full setup, start to finish.
Your Claude Code sessions keep forgetting what you're building because you only set up one layer of memory. There are three. Here's the stack the shippers are running this month - and how to install it in a weekend.
The headlines led with the valuation. The part that actually matters: the model sitting under your Claude Code session is about to get longer, cheaper, and faster shipped. Here's what the milestone unlocks for builders, and the habit stack to install this week so you ride it.
Most builders learn Claude Code. The ones who ship have a different set of habits. Here are seven of them - the ones that take you from tinkering forever to actually shipping the thing this week.
Seven days, four shipped things, a Chrome extension that almost killed my browser, and the exact moment Claude Code stopped feeling like magic and started feeling like a tool.
A step-by-step walkthrough of going from a blank folder to a working app in an afternoon - the exact setup, prompts, and mindset that get beginners shipping on day one.
Shipping something real in your first week sounds like hype until you see the path. Here's a day-by-day roadmap that takes you from zero to a deployed project - calmly, without burning out.
Both can write code, so why do serious builders reach for Claude Code? An honest look at where each tool fits, and why the difference comes down to acting in your project, not just chatting about it.
Built by
Claude Code Club is built and taught by David Iya and Duncan Rogoff - operators with two decades of shipping work across multi-billion-dollar brands.
David IyaForbes 30 Under 30 · Y Combinator
Duncan RogoffApple · PlayStation · Charles SchwabOur team has worked with and been recognized by
Join Claude Code Club, the #1 community for learning claude code, for $9/month.
We use cookies to keep the site running, remember your preferences, and understand how people find us. See our Cookie Policy for details.
