00:00There's a new king of AI coding tools and its name is Claude code

00:02But 6 months ago, I was using Claude code all wrong

00:07I was basically treating it like chatbt with a save button, typing in vague prompts, and just hoping for the best

00:14It was like buying a Ferrari, but never taking it out of first gear

00:16Fast forward to today, and I'm a Cloud Code Power user

00:21I can run multiple instances of Claude Code at the same time and work on a week's worth of features in just a few hours

00:28See how each Claude Code instance is working on different app feature completely independent from the other

00:34And yes, Claude Code will merge all the changes together at the end

00:37In this video, I'm going to save you 6 months of pain by sharing 36 specific lessons about how to get the most out of Claude Code

00:46These lessons are going to be organized into three clear levels: beginner, intermediate, and master

00:51In level one, the beginner section, we're going to cover Claude code foundations

00:58We'll cover installation and setup, essential concepts and commands, and how to use things like the claw.md file to put you ahead of 99% of beginners

01:05In level two, the intermediate section, we're going to look at workflow enhancements

01:12We'll cover claiming mode, using Claude for research and documentation, and using Claude code to automatically answer issues and create PRs in GitHub

01:20And finally, level three, the master section

01:23We're going to look at advanced techniques

01:25We'll cover things like using multiple claude codes at the same time to work on multiple different features, custom commands, and custom sub aents, and using Claude code with MCP servers

01:36So whether you're a Claude Code beginner or power user like me, I can guarantee that you're going to learn something from this video that's going to help you cook at a higher level with Claude Code

01:46But before we dive in, I'm Afar and I teach people how to use AI coding tools, even if you're new to coding

01:54So if you're trying to level up with AI coding tools, maybe it's for your job, maybe it's for a new business you're trying to start, maybe it's for a side project, please subscribe to the channel and turn on notifications for more videos about the best AI coding tools and how to get the most out of them

02:09With that out the way, let's get into level one, the foundations of Claude Code

02:13All right, so if you're new to Cloud Code or feel like you might be missing some basics, this section is for you

02:19We're going to cover everything you need to get up and running with Cloud Code, including things like installation and setup, basic commands, project configurations, and debugging

02:27First up, installation

02:30The way that you install Claude Code and the way that the majority of people use it is just on their local laptops or their local machines

02:38You go to the Enthropic website, copy the command for claude code, and install it on your local machine using your terminal

02:44It's quick, it's easy, and you can begin coding right away

02:48Option two, and this is great for using Claude Code for back-end projects, is to install Cloud Code on a remote server

02:55Just log in to wherever the server is hosted, for example, AWS, Digital Ocean, or Herzner, and install Cloud Code just like you would things like Python or Node

03:03A bonus of the remote server approach is that this allows you to code from anywhere

03:07For example, you can use the termius app on iOS to control claude code right from your phone

03:13Tip number three is that you can use claude code inside other AI coding tools like cursor, windf

03:22This is great if you're already familiar with those tools or still getting comfortable with the terminal

03:25To get started, navigate to the directory of your choice and type claude in your terminal

03:31You can also use the resume flag

03:33That's d-res any previous session

03:36Tip number four is to use my favorite feature of Claude Code and that's to-do list

03:40This is the thing that made Claude Code stand out for me among all the other AI coding tools at the time

03:46It didn't just jump into writing code straight away

03:48First, it created a to-do list

03:51Now, this happens most of the time automatically, but you can also explicitly prompt plot code to use to-do list in the prompt that you give it

04:00The great thing about to-do list is that as Claude works, it checks off items so that you can see what's happening and what's coming next

04:09And it also enables Claude to work on big complex tasks without getting stuck in loops or erasing past work

04:13Next, let's look at some essential commands

04:18First up is bash mode

04:18Bash mode enables you to run bash commands inside Claude code so you don't have to exit out of it

04:25Claude can also run bash commands itself, meaning it can do things like read and write files, search, and even handle git commands for you

04:32For example, you can tell Claude to read all the files in a certain folder and use it for context for tasks it will do

04:39Tip number six is to use Claude for instant documentation

04:44Documentation doesn't have to be painful

04:46Just ask Claude to explore and explain the architecture of an app and how it works and save its output in a file called something like architecture.md

04:57This is great when you're getting up to speed with a new project or touching a project that you haven't worked on in a couple weeks or just documenting key things for you, your teammates, or even Claude to reference later

05:07Tip number eight is auto accept mode

05:09Claude will usually prompt you for permissions to make changes

05:14If you want to let Claude take the wheel, you can turn on auto accept mode by pressing shift and tab together

05:20This enables Claude to make changes without asking each time

05:22Tip number nine is about model switching

05:27Now, Claude code allows you to choose from a variety of anthropic models to power its AI coding sessions

05:31The /model command allows you to choose which model to use

05:38You can use Opus, which is the most powerful model when you need deeper analysis or want the most powerful coding capabilities for your toughest challenges

05:46And you can use Sonnet for routine tasks

05:48So if you just want to save tokens or get faster responses

05:50I usually keep it at the default mode, which is using Opus until you've hit 50% of your usage limits for that month

05:57But my new favorite is actually the Opus plan mode, which is where it uses Opus, the more powerful model to plan, and Sonnet, the more costefficient model, to actually write the code and do the execution

06:10It's something I recommend you play around with and see which model works best for your use case

06:14Next up, don't be afraid to interrupt Claude

06:16The escape key is your friend

06:18You can press the escape key once to interrupt Claude and twice to go back to a previous prompt in your session

06:25Don't hesitate to interrupt Claude if you see it heading in the wrong direction

06:29It's much better to redirect early than to waste precious tokens

06:33Next up in the beginner section, let's talk about fixing your mistakes or debugging with Claude code

06:40It's actually much simpler than you think

06:42First up is a screenshot method

06:44Now, claude code can take images as input

06:46So, if you run into any UI issues or any bugs in your application, you can actually take screenshots and give them to Claude Code as inputs for your prompts

06:55This allows Claude to see all the context and it usually can tell exactly what went wrong or it allows it to pinpoint exactly where in the UI you want to make a particular fix

07:04Now you can also use the image input for other things like giving it UI designs and diagrams as well, but I think the most common usage is for debugging

07:12The next level of debugging is letting Claude write your tests for you

07:18This is as simple as just asking Claude to write tests for a particular feature or write tests for the new onboarding flow

07:24Just make sure to focus on general end toend tests rather than implementation specific ones

07:30And we can take this further with tip number 13 which is using cloud code for testdriven development or TDD

07:37Now test-driven development is a really popular software engineering philosophy

07:42But when it comes to Claude code, essentially what this means is asking Claude to first write tests for a given feature and then to implement it

07:50This helps Claude catch issues early and it gives it a bit of structure to work with, which can lead to better outputs

07:56Next up is project configuration

07:58And that brings us to what I think is the most important thing in this video, which is the claude.md file

08:05You can think of the claude.md file as your project's memory

08:07It's a file that gets added to context every single time Claude Code does any task and it's all the information that you want to give Claude Code to work on your project your way

08:20Here are some snippets of my claude.md file for an iOS app that I'm working on

08:25It consists of things like Git workflows and best practices, project and architecture overviews, build commands and best practices for things like testing and debugging, and analytics and documentation how-tos

08:40Now, the great thing about putting these in the claude.md file is that Claude will follow these rules automatically

08:46It'll create proper branches, commit regularly, and never accidentally push to main

08:51It'll follow my preferences for documenting its work and always add tests and analytics when building out new features

08:58This ability to follow complex rules and tailor both workflows and output has made Claude my favorite AI coding tool, outshining the likes of cursor and replet

09:08Now, before you worry that you have to manually write your claw.md file, you can actually just ask Claude to write it for you

09:15That's going to be a recurring theme in this video

09:19Using Claude code to help you use Claude code better

09:21What this means in this case is asking Claude to update the claw.md file as you add specific features to your project or as you discover preferences that you want to make Claude respect

09:32Tip number 15 is the message Q

09:34Now the message Q is a real gamecher because it means that you don't have to wait for Claude to finish its current task before you give it input

09:43You can just type a message while Claude is working and it gets added to the message queue and Claude will act on it once it's finished with the current task

09:52Just add tasks as you think of them and Claude will work through them all in order

09:56And that brings us to tip number 16, which is the final tip in our beginner section and that is for long prompts, you can actually put your prompt in a markdown file and feed it to Claude by referencing that file in the prompt using the at symbol

10:11This is much cleaner than trying to type everything in the terminal and it's great if you have long prompts if you want to think things through before you give it to Claude

10:20Now, that brings us to the end of the foundation section that gives you everything you need in order to get started with Claude code

10:25Let's take it up a notch to the intermediate section where we're going to look at Claude Code workflow enhancements

10:32Now that you're comfortable with the basics, it's time for level two or the intermediate section and that's about working smarter, not harder

10:39I'm going to share with you the enhanced workflows that I use in Claude Code to plan better, research faster, and integrate with my existing GitHub workflows

10:49First up is planning and thinking features that are going to help you level up and enable Claude code to tackle your toughest problems

10:58Tip number 17 is to use planning mode

11:00Now, most of the time, you don't just want to jump straight into writing code

11:04Often times, you want to plan and strategize before you start implementing

11:09To do this, use the planning mode on Claude Code and ask it to plan before it starts working on a new feature

11:15Just hit tab and shift until you see the plan only mode and that will ensure that Claude gives you a plan to review before any code is written

11:24I use the planning mode all the time for architecture decisions or to force Claude to think through how to fix nollie bugs before it takes action

11:30When it comes to planning, a hidden setting to make use of is the opus plan mode

11:38This means that you can use opus for planning and sonnet for implementation just by selecting the /model command

11:46This is a good default to ensure that you get the most powerful model for planning but the cheaper model for implementation

11:51Another underrated feature when it comes to planning is to use sub agents to create multiple plans for how to do let's say implementing a given feature or to fix a certain bug and let you or Claude pick the best one

12:05Look out for more on planning and parallel sub aents in the advanced section of the video

12:09Next up, did you know that you can control how much Claude thinks when it's working? Meet the think keywords

12:16These allow you to tell Claude how much time to spend thinking when you're working on tough problems

12:22There's actually three think keywords

12:24There's the basic think, there's think hard for deeper analysis, and for maximum thinking power, use the keyword ultra think

12:32Just include the appropriate thinking keyword in your prompt and it will tell Claude to use more of its thinking budget

12:39Now imagine you're prompting Claude to add a new feature and you're using the think hard keyword in your prompt

12:45But you're also using planning mode and you're saving that output into a markdown file for future reference

12:51That's just one example of combining tips that we've seen in this video into a powerful workflow for vibe coding

12:57The next unlock for me was that I could use Claude code for more than just code

13:01My favorite example of this is research

13:06Claude has a web search and web fetch tool that enables it to search the web and read website content and take action on it

13:13This means that you can use Claude code to research small things like how to use a Stripe API or ask it to do larger research tasks like put together a report on the best O tool to use in your application that also has pre-built login components

13:27It's that powerful

13:30This saves you a ton of time and allows you to take into account more of your app's context as you add tools and features

13:36Another hidden feature when it comes to research is that Claude Code can read PDFs

13:40This means that it can combine information that you have in PDF files with information that it finds in its web searches

13:48My favorite example of how to use this feature is feeding Claude PDFs of Chad GBT deep research reports so that it can reference those in its research phase

13:58Beyond research, Claude code is great for document generation

14:03This is important because I've noticed that you need to think like a product manager and give Claude code all the context that it needs in order to do its job well

14:11The good news is that you don't have to write all of these product specs by yourself

14:15You can actually leverage Claude to generate artifacts that both you and Claude reference later

14:21I use Claude to generate things like product requirement docs or PRDS for features, user experience guides, API documentation, and technical design docs

14:31I find these docs to be more useful than the ones made in chatbt because they take into account more of the actual structure of my application and leverage all the context of my project for better results

14:44Tip number 26 is something that I use to stay organized in the projects that I build and that's using claude code for automatic change tracking

14:51This is about leveraging clawed code for things like creating change logs for it to reference later, documenting the most up-to-date features of your app for use on your website, or making things like decision docs, which outlines why you made a particular decision

15:06I highly recommend leveraging Claude Code for keeping track of how your project evolves over time

15:11Your future self and your future Claude Code agents will thank you

15:15Next up is a Claude Code GitHub integration

15:17Claude Code is fantastic for teams thanks to its deep integration with GitHub actions

15:22Now, you may remember how you can use Claude Code to handle Git commands for you as you develop features

15:29But this Claude Code and GitHub actions integration takes it to the next level

15:33First, run the /install GH actions from the Cloud Code menu

15:39And once you've set that up, you can tag Claude Code in issues and pull requests and ask it to fix it

15:44and Claude code will run using GitHub actions and submit a PR or a fix without needing to run on your local or your remote machine

15:54Claude can even review PRs automatically as they come in

15:59Finally, in this intermediate section, I want to talk about the mindset that helps me get the most out of working with Claude code

16:05For best results with working with Claude code, you need to think like a product manager

16:09And this means two specific things

16:11Firstly, it means giving Claude lots of clear, relevant context and constraints when it comes to achieving your goals

16:19Secondly, and probably most importantly, it means letting go of reviewing the code yourself or needing to understand everything that Claude has implemented and working to verify Claude's outputs at higher levels of abstraction

16:32What this means is that you don't need to understand every line of code outputed by Claude

16:39Can you verify that the app experience is what you want? Can you verify that the tests pass? Can you verify that the app works as intended? That's what matters

16:49This approach literally changed how I built with AI coding tools

16:52And it's a mindset shift that I had to make, similar to what I've experienced in real life when I had to work and manage smart technical people on my team at previous jobs that I've held

17:03Now, this brings us to the end of level two, the end of the intermediate section of Claude Code

17:08I'm sure you're seeing just how powerful Claude code can be and are probably super excited to use it in your own projects

17:14But hold up because we have more to learn in level three and that's the master section where we're going to go through advanced techniques

17:22Level three is where you become a Claude code master by leveraging advanced techniques that allow you to feel the full power of Claude code

17:30We'll cover things like using multiple instances of claude code to develop multiple features at the same time, custom commands, custom sub aents, and using claude code with MCP servers

17:42First up, let's talk about working in parallel or using multiple Claude codes at the same time

17:47For those of you keeping count, this is tip 29 and it's using parallel sub aents for planning and exploration

17:53This allows Claude to explore multiple solutions simultaneously and then you pick the best one

17:59It's like having a team brainstorming session

18:01All you need to do is ask Claude to plan and use parallel sub aents to explore solutions

18:08Parallel sub aents are great if you want to explore how to add complex features to your app or if you want to fix gnarly bugs or problems

18:15Now remember at the start of this video where I used three claude code instances to work on three features at the same time

18:22I'm going to show you how to do that using the power of cloud code and get work trees

18:26Get to work trees give you isolation that enables multiple claude agents to work on your project without conflicts

18:34Just create a hidden folder in your project

18:39I called mine trees and use the git add commands to create a work tree for each different feature or thread that you want to work on

18:46Once the work trees are created, you can spin up a terminal session for each work tree and then run claude code in each

18:52Here's me doing that in cursor, but you can also do it in your terminal

18:56This gives you a beautiful clean git history that's easy to understand and review

19:00Using cloud code and git work trees allows you to work on multiple features at the same time on the same codebase without running into issues down the line

19:10When you're done, just ask Claude Code to merge each of these work trees in your folder together and fix any conflicts

19:18And boom, thanks to Cloud Code and using multiple Cloud Code instances and Git work trees, you can have a week's worth of development done in just a few minutes

19:27Now, that's how to use Cloud Code in parallel

19:29Next up is the advanced customization section

19:31And the next tip is using custom commands

19:36They're basically like having prompting shortcuts for Claude Code to act on repetitive tasks versus typing out the same long prompts over and over again

19:44Now, the easiest way to make custom/comands is just to ask Claude to do it for you

19:49But if you want to do it manually, here's how to set up custom commands yourself

19:52Create a commands folder in the Claude folder in your working directory

19:57Then add a markdown file with the name of your command

19:59For example, changelog.md

20:04Your command file should have a description of what the command does, the list of allowed tools, usually things like bash, read, and write, and the actual command prompts, which is what you want the command to do

20:13Command prompts can go beyond just plain text and include things like arguments for dynamic input, bash commands, and things like file references

20:23A pro tip here is that custom commands can be project specific or they can apply to all your Claude Co projects and this is called a personal command

20:32One more thing to note here is that custom commands don't automatically get added to context

20:37So if you want something to always be added to context, for example, information about your application, put these in the claw.md file, that always gets added to context

20:48Custom commands don't

20:48This brings us to tip 34, which is using specialized sub aents

20:53Just like custom commands, you can create custom sub aents

20:58These are specialized AI systems with custom prompts and tool permissions that can handle specific tasks autonomously

21:06And just like custom commands, they can be project specific or they can be personal and apply to all projects

21:13For example, you may want to create custom or specialized sub aents for things like user experience design, API design, security review, running tests or database administration and other domain specific tasks

21:27Each sub agent has specific tools that it can access and a domain specific purpose reflected in its system prompt

21:34The easiest way to create custom sub aents is to use the / aagents command in claude code

21:42This is another example of using Claude Code to help you use Claude Code better

21:47There's a wizard that walks you through setting up a new agent

21:49And this is much easier than setting it up yourself because Claude does the heavy lifting for you

21:55In this example, I'm setting up an agent to do mix panel analytics

22:00And here's what's going on under the hood

22:02Each agent has a markdown file which specifies its agent type, usage, accessible tools, and system prompts which gives you an overview of what the agent does

22:11You can view all the agents that you've created with the / agents command

22:15Once you've created your sub agents, Claude will automatically know that they exist

22:22It'll understand what it's used for based on what's in the usage field description in your agent markdown file and it'll automatically delegate tasks to your sub agent when relevant

22:31Claude will also use these sub agents if you explicitly ask for them in your prompt

22:38So for example, you could say, hey, use the testr runner sub aent in order to run these tests or use the database administration agent to make sure that the queries are correct for this new feature

22:49Now the final thing in this advanced section is using cloud code with MCP servers

22:54Now what happens when you want to extend Claude codes capabilities to take actions in third party tools like databases or tools like Figma or Canva? This is where model context protocol or MCP comes in

23:06Here are some ways that I like to use MCP servers with cloud code

23:12First up is database MCPS

23:14These are great for doing direct database work

23:17I've used the MongoDB MCP, the Postgress MCP server, as well as a Superbase MCP server for various database related things in the apps that I've built

23:27Next up is a Playrite MCP for browser automation

23:31This is great because it allows Claude code to actually visually see your application and your web UI, and it's great for things like testing and finding and fixing bugs

23:40Finally, there's a Figma MCP, which is great for going from design to code

23:45Now, there's many other MCP servers out there

23:48I'm actually curious if there's a particular MCP server that you found most useful

23:54Let me know in the comments

23:54But those are just three that I like

23:56These capabilities are incredibly powerful and I think they'll become even more powerful as the MCP server ecosystem matures

24:05So, that brings us to the end of level three

24:07That's the master section of Claude Code

24:09We've gone from beginner where we've looked at the foundations to intermediate where we looked at enhanced workflows to the master section where we've covered advanced techniques for getting the most out of claude code

24:21Congrats on making it this far in the video

24:23But before we end off, let's talk about a very important thing with AI coding tools and especially with Claude Code, and that's money

24:31How much does Claude Code cost and is it worth the money? Now, unfortunately, there's no free version of Claude Code, but there is two ways to access it

24:40The first way is via one of the Claude paid plans, and there's two of them that you can choose from

24:44The first one is a $20 a month pro plan

24:46You can use this to get started or to play around with

24:51And when you're serious about building, I'd recommend the Max plan, which goes for either $100 or $200 a month

24:59The Max 5X plan gets you 5x higher rate limits than the Pro plan for $100 a month

25:05And the Max 20X plan gets you 20x higher rate limits at $200 a month

25:12This is the plan that I personally use and I'd recommend it if you're serious about AI coding tools, but you know, pick whatever plan fits your budget

25:19The second way to use cloud code is through the anthropic API, but this is just ridiculously expensive and unless you're part of a large company that will pay for the anthropic API usage for you, I'd recommend picking a claude pro or max plan that fits your budget and not looking back

25:34Quick note, Anthropic announced that at the end of August, they're going to be imposing additional rate limits, and that's weekly rate limits on Claude Max users

25:46I'm not quite sure how this is going to impact Claude users

25:47I don't think the impact is going to be that big

25:49I still think Claude is good value for the money, but we'll have to see what these rate limits do come the end of August

25:56That brings us to the end of this video

25:58I hope it helped demystify Claude Code and made you super excited to build and unleash your creativity with Claude Code by your side

26:06If you learned something from this video, don't forget to like and subscribe

26:10And if you thought there was a feature that was really cool or maybe something that I didn't cover in this video, it could be about claude code, it could be about AI coding in general, let me know in the comments and I'll see you in the next One.