5 secret Claude Code features you need to know about

Flawed Code is the most powerful AI coding tool ever made. But what if I told you you're using it all wrong? In this video, I'm going to show you five hidden features that if you start using right now, you'll 10x your coding speed overnight. Let's get into it. The first hidden feature I'm going to

show you is a slash command that made my workflow so much easier. For those that don't know, a slash command include code is a quick command you can give with a slash that automatically runs some sort of process. The one we're about to build will automatically update all our documentation in the app. Having up-to-date documentation in Claude Code makes your AI agent so much more powerful because it has full context every time it works. So, it is critical that you constantly have your documentation up to date. The issue is it takes a lot of time to do. But with this slash command I'm about to show you, it makes it so much easier. So I want you to open up claude code inside cursor and put this prompt in. This will build the slash command for you. Build me a slash command and claude code that automatically updates all my readmes documentation and claude. md files every time a successful change happens. We're going to hit enter on that. And what's going to happen now is Claude will actually build out the slash command for us, save it to our directory, and now all we'll need to do is do slashupdate docs every time we make a change, and it'll update all our documentation for us. All right, so Claude built out the slash command for us. So now all I need to do is do slashupdate docs, hit enter on that, and it's going to use our new slash command that we just built to update all our documentation. So, as you can see, it's in my stock portfolio app I built. It's going through and it's creating documentation on every single component built. And the advantage here is next time I put in a prompt to change something in the app, the AI agent will have all the documentation to pour through. So, it knows exactly how to work on the app. This is going to make it so the coding the AI agent does is 10 times more accurate and we get way better results. All right, looks like the slash command finished. Let's check out what it did here. Here's the new readme file. automatically generated. It updated the readme with every single feature, every single technology, how it runs, so that next time we build anything out or maybe even go to a new AI agent, it will have full context on how our app works. The results you're going to start getting just by this one prompt I gave you is going to make your app so much better and building with cloud code so much nicer. So, that one feature is going to speed up your code and increase the quality of your app. But wait till you see this next one. It's even better.

The next hidden feature I'm going to talk about just released a couple days ago and that is Claude Code sub aents. What sub aents allow you to do is instead of coding with one agent in claude code which can take a tremendous amount of time. You now can create sub aents that can handle multiple tasks at once that will speed up your entire coding workflow. You can have sub agents for UI design, sub aents for creating content, sub aents for managing your database. There are so many options, but I figured out the best way ever to create sub agents inside of Claude Code. So down below is a link to the documentations for Claude Code sub agents. What you want to do is this. You want to copy the entire page of that documentation. Once you've copied the page, we're gonna go back into Claude Code. And then you're going to want to put in this prompt, which it'll be down below. Oh, I link all the prompts down below and all the links you need. There is a new feature in Claude Code called sub aents. The documentation is pasted in down below. Please go through it and determine what would be the best sub aents you can create for my app that would increase the quality of the app and speed up coding time. Then implement the new sub aents documentation and then paste in the documentation we just copied over and hit enter. Now, Claude Code's going to go in, determine what are the best sub agents for your app that will speed up your coding and then create them for you. Instead of you having to do all the decision making around which sub aents you should create and googling a 100 different things, you just give it to Claude Code and Claude Code will determine the best sub aents customized for your app. Then, when you give Claude Code any prompts after this, it will automatically spin up the best sub agents for you to speed up your coding time. All right, looks like it completed the agents. Let's see what it built. So, again, as a reminder, this is a stock tracking portfolio app I built. So, looks like it built me five different sub aents. It can spin up at any time. A UI designer that'll be totally in charge of designing the UI and making sure it looks beautiful. Build responsive mobile first components, implement interactive data visualizations. I love that. It has a portfolio optimizer that will actually optimize everything in my portfolio to make sure I'm investing in the right stocks. I like that. A dividend analyst that will analyze all my dividends as I'm building out different parts of my application. A data importer that will handle importing all the data into my app. An API integrator. This is a big one because my app uses a ton of APIs. It has an entire agent specifically for APIs. That's amazing. That's the power of using sub agents and having Claude code determine which sub aents to build. It will make sure it builds the best sub aents for your app that you might not have even thought of. Again, this is another feature that will make it so you code so much faster and get way better results from your agents. So, that feature is going to have a tremendous impact on how you code, but this next one's also going to have a massive one as well.

Not many people know about Claude code hooks, but they are a massively helpful feature inside Claude Code. The way Claude code hooks work is hooks are called anytime you take an action in your app. So you can set up hooks anytime you make any code changes, anytime you commit code, anything you could think of. You can set up hooks that automatically take actions inside Cloud Code. We are going to set up a hook now that will commit your code to GitHub anytime you make a successful change in your code without errors. And this hook is so helpful because this is the way you can have checkpoints inside of Claude code. One of the best parts about cursor is you can automatically rewind anytime the cursor agent messes up. That doesn't exist in clawed code, but setting up this hook basically recreates that functionality so that anytime you want to rewind, you can. By having the clawed code hook automatically commit to GitHub every time you make a code change, you can at any time rewind your git so that your code goes back to a working state. This is so helpful to do. So here's the prompt you want to use. I'll put this down below as well. Feel free to pause anytime and just copy paste this and get this done with me. I want to set up a cla code hook that automatically commits the code to GitHub anytime we make a successful code change without errors. Please set up this claude code hook. I'm going to hit enter on that. Claude Code's going to set up the hook for us. That's the most beautiful part about using Claude Code is you don't need to set anything up yourself. You just have the AI agent do it for you. So, it's going to set up the hook for us. Now, it's actually going into the anthropic documentation so we can understand hooks better. And now, it's going to go and set that hook up for us. It will automatically commit our code every time we make a change. So, it's so much easier to rewind if we ever make an error. All right, looks like it's done. It triggers after every successful writeed or multi-edit. So anytime the AI agent makes changes to the code, it will automatically commit our code to GitHub. So if we mess anything up or we make a mistake, we can easily rewind by rewinding to a past GitHub commit. This is going to make coding with Claude Code so much easier. And we did it again just with one single prompt.

The next hidden feature I want to talk about is the different think modes. For those who don't know, there are several different think modes in Claude Code that will make it work extra hard and give you better code if you use them correctly. For instance, you can tell Claude Code to think, think hard, and ultra think. If you tell Claude Code just to think, it will give you pretty good results. But if you tell Claude Code to ultraink, it will give you amazing results. So, if you use this strategically and you use ultrathink for your extra complex tasks, you give yourself a better chance of one-shotting your code and getting way better results on your first try. Let me give you an example. So, I'm going to have Claude Code build me an ultra stylized firsterson shooter using 3JS in a single file. This will just show us kind of baseline the way Claude Code works on just normal think mode. I'm going to hit enter on that. It's going to build me a 3D firstperson shooter. We'll see what this looks like on just normal think mode. And then right after I'll show you what Ultra Think looks like to see how much better it performs. All right, so it finished building on the regular Think mode. Let's check this out. Pretty good app, right? The enemies are these orange balls going around in this purple. I I like it. It's solid. I mean, it's kind of plain, right? It's got the purple pillars and pink balls. It's fine. There's not much to it. The bullets are kind of cool, but let's see what this looks like now on ultraink mode. So, I'm using the exact same prompt except this time I'm going to tell it to ultraink. So, I'm going to hit enter on this and we're going to see what kind of result it comes up with. This time using ultrathink mode which makes it work even harder on our complex problems. And again, all you need to do to use ultrathink mode is just tell Claude code ultrathink inside your prompt and it's going to give you way better results. Now, this could take a little bit longer. So, you don't want to use ultraink with every single prompt you give. But on those really strategic and complex tasks you want to give Claude code, you want to tell it ultra think. So, as you can already see here, it build out its to-do list for what it's going to do for this app. And there's like way more to-do items. So, it really is taking every step ultra carefully to make sure it gives us really amazing results. All right, looks like it's done here. Let's check this out to see what we got. As you can see, the world looks uh a good a good bit cooler. You can see there's a lot of different other items inside of the map. Oh, you can see there's like walls, too. You can see every time I fire, there's like sparks that come out of the gun and the enemies instead of just being a ball have these like rotating 3D shapes in them. And when I destroy them, they like explode, which is really cool. You can see there's an ammo counter in the bottom right. You can see there's a score in the top left. There's a lot more colors. stylized effects. This is the advantage of Ultra Think. It just spends a lot more time giving you a lot better results. Anytime you do something complex in Claude Code, you want to make sure you tell Claude Code to ultra think about it so you get better code and better results. So, those last four features are amazing and make your coding a lot better. But this last one I'm going to show you is mandatory.

Everyone should do this. This is so easy to implement and this is having the correct clawed rules. So clawed rules are rules that are sent to the agent every time you run any prompt. It's included in the context every single time. So if you create a claw. md file, you can put in whatever rules you want that are sent to the agent every time. These are the nine rules I use in my claw. md file with every single app I build. And this gives me so much better results inside of Claude code. I'm going to paste these down below. So, feel free to pause here, grab them, and put them into your own claw. md file. But just going over them real quick. Basically, what they cover is making sure Claude thinks in tasks and to-do lists. So, every time it does anything, it breaks it down in to-do lists, which makes it so that you get way better results. And it also makes sure that it isn't lazy. So, all fixes need to be validated in the code. in all fixes impact as little code as humanly possible so that you don't run into any of those dreaded error rabbit holes where you just make errors worse and worse. These nine rules I have here made my results from claude code so much better. And just by copying and pasting them into your own claude. md file, you'll instantly get better results from claude. So those five secret features have made my results in claude code so much better and have made my workflow so much faster. Go back, rewind, make sure you copy and paste all the prompts from down below. Implement them into your own clawed code today. I promise your results will be unbelievable. If you learned anything at all, leave a like. Make sure to subscribe and turn on notifications. All I do is make incredible videos on building things with AI. Also, I live stream every single Thursday at 400 p. m. Eastern. So, check out that as well. and I'll see you in the next