I Have Spent 1000+ Hours With Claude Code. This Is What I Learned
TCThe Coding Sloth@TheCodingSloth · 643K subscribers
- Views
- 909K
- 908,613
- Outlier
- ×7.2
- Median 125K
- Length
- 22:31
- Published
- Aug 18
- Tuesday
- Comments
- 459
- 17.1K likes
Script
How it's written
- Words
- 5,203
- Words a minute
- 232
- Reading time
- 22 min
- Segments
- 16
The hook
0:00–0:17I have spent an unhealthy amount of time using Claude Code, and I got to get this out of my chest already. Their usage limits suck. Oh my goodness. I say hi and boom, there goes my limit and I got to wait 3 hours. And with this new Claude fable model, I recorded a lot of this footage like a month ago. So yes, I know, it's not new.
Structure
I have spent an unhealthy amount of time using Claude Code, and I got to get this out of my chest already. Their usage limits suck. Oh my goodness. I say hi and boom, there goes my limit and I got to wait 3 hours. And with this new Claude fable model, I recorded a lot of this footage like a month ago. So yes, I know, it's not new. Leave me alone. Just laugh at my jokes, okay? I've been programming with the $20 plan and I have had situations where I prompt once or twice and I hit the limit. Like bro, no wonder people are getting better results. They don't get enough time to use it properly. I'm glad they're making it better, but it's painful. So I want to share everything that I've learned so you can use it effectively. So things like my workflow, my favorite MCPs, my favorite skills, and I'll also share some ways you can save on some tokens so you can actually use it more. Trust me, I've learned some strategies to use as little tokens as possible so I can get my money's worth because I am not spending $100 a month for this. That's expensive and I'd rather spend that on a McDonald's. Okay, so what's Claude Code? It's Claude, but for coding. You're welcome. No, but really, it's Claude, but it's specialized for coding and it lives in your terminal. Now, do I like the terminal? Meh. I prefer the IDE approach. Uh specifically the IDE and agent combo approach. You get the agent interface and an actual IDE. Plus there's buttons I can actually click. I'll take that over a terminal any day. What can I say? I like visuals. I'm a toddler. The good news is you can use Claude Code in your IDE and on the web. Pretty cool. Now, why have I been using it? Well, everyone and their moms are using it, even big tech companies. Some a little too much, Uber. It also made like a billion dollars in 6 months, which is pretty crazy. And that made every other AI company copy and paste Claude Code and now we have this mess.
Watch from 0:00And every company wants you to learn these types of tools so you can become a tonex engineer so they can give you more work. And that also didn't work cuz it was too expensive. They also gave me some free stickers, which is pretty cool. Do I recommend you learn it? Yeah, pretty helpful until you hit those usage Yeah, pretty convenient. Jobs want you to learn it. And if it gets you a better chance at a job, hey, you got to do what you got to do. The good news is a lot of these Claude Code concepts apply to other coding agents, which means I can give you some alternatives to Claude Code since this video's not sponsored. Okay, so let's go over the features of Claude Code. I've done my fair share of research. I've looked at some Twitter articles. I've watched YouTube videos. I've seen Claude's tutorials. I've watched videos and articles from the guy who freaking built the thing. As I was doing research for this video, I realized that Claude Code has like 80 plus different command and features that I have never seen in my life. Did you know there's an ultra plan mode? I didn't. Nobody else uses this. I don't think I've seen the creator use this. Hey, editor Sloth here. I recorded that a month ago, too. And uh ultra plan doesn't even exist anymore. That's how useless it was. Yeah, so originally I was going to go through every single one, but no, there's way too many. Most of them are just configuration or just useless. So now we're only going to cover the essential ones. And even then, I'm going to tier rank them from how useful they are. Because in my experience, some of these features that people call essential, you're never going to touch. Now, if you are serious and you do want to learn more about programming and AI, you should check out my free newsletter, Sloth Bites. Oh, you don't know what Sloth Bites is? Sloth Bites is just a newsletter I'm working on. It's currently one of the biggest programming newsletters in the world. I made that up. I don't know if that's true.
Watch from 1:28And it's completely free. Where every week I send you programming advice and news so you can stay up to date and not get behind. Did I mention it's free? All I need from you is your sweet, delectable email. Let's start with the slash init and Claude file. This is the command you're supposed to run when you first open up Claude Code in a project. So far in my experience, it's all right. Essentially, Claude looks at your entire code base and it puts it all inside this Claude.md file. This file becomes Claude's permanent memory for the project. Now, I have beef with Claude for this feature because other AI agents do the same thing except they put it into an agents.md file. Claude is the only one that doesn't do this, which is very, very annoying. The one nice thing about Claude files is you can actually import additional files. So if you are using an agents.md file, you can just import it inside the Claude.md file, which saves you from having a symlink. But it would be nice if, you know, Claude just supported it. But it is what it is. There's also a new experimental version of this command. You just have to turn on this environment flag. And this one actually has some potential. Instead of analyzing the code base and writing the file, it now interviews you, which is really good. And it will now also recommend some skills and hooks, which is really nice. We'll get into those in a bit. Based on my experience, I'm honestly going to give this feature like a C or even a D. I don't use it very much. Whoa, me from a month ago was really stupid. Yeah, after a month my opinion has changed and it still stays the same. I think it's pretty mid. But the cloud file, I'm moving that up.
Watch from 2:53After months of dealing with the sloppy code, you definitely start to get an idea of these AI models quirks and their habits, really disgusting habits. And so, for the most part, my claw.md file has information like a quick description of the project, current status of it, um my coding styles. And I've also been testing some interesting things like this working philosophy. A funny rule I have in my file is uh user-facing capitalization. For some reason when uh AI models create designs, they really love to use all caps. No idea why, but it's ugly. Another thing I've been testing and liking a lot is setting the pull request language. But this is what I like to use so far. This file can change quite a bit. Be flexible with it. But this file is honestly not a make or break thing. You could easily survive not even having one. So, don't freak out too much about it because you can honestly just use skills and you can get similar or even better results. All right, I haven't explained skill A tier, but if you're smart with it, easy S tier. A skill is also just a markdown file, specifically a skill.md file. It's essentially a guide for something you do over and over that the AI can use when it makes sense or you can explicitly tell it to use it. It would be for things like your best practices, your workflow for something, or how you would research something. Essentially, any type of workflow that's repeatable. Claude Code has some default skills pre-installed like code review, security review, and some other stuff. I will give those skills like a B tier A tier. I do recommend using them if Claude implements a feature. It's just a nice bonus. Personally, I freaking love skills and I love that there's a whole community of them now because it's literally companies and genius engineers taking their knowledge and best
Watch from 4:14practices and putting it all into one file. So, not only is it useful for the agent, it's useful for me. I've learned so much just reading other people's skills. So, some of my favorite places to find skills has been the website skills.sh. This is my go-to place for finding and installing skills, but there's also some other GitHub repos where you can find skills. My favorite type of skills that I like to use are Matt Pocock skills. He must read a dictionary every day because his vocabulary is immaculate. Such a smart and brilliant guy. I really like using his grow with doc skill. Helps me refine my requirements and I also like using the improved code base architecture skill. It's just a nice workflow. I also like that it comes with a nice visual. I mean, hey, you won me over. Like I said, I'm a toddler. I also like using cursors. I like this name. Thermonuclear code quality review skill. Really helpful. It really simplifies the code that AI generates, which eliminates a lot of the slop. Strongly recommend you use this and it actually combines really good with the improved code base architecture skill. I've been using both of them at the same time and I think they're pretty good. One of the recent skills I like to use is a Shatien's improved skill. I've been trying it out and I'm loving it. I really love the idea here. It audits your code base and it writes the plans for other agents. Oh yeah, play easiest here. If you hit shift and tab on Cloud Code, Cloud goes into plan mode. Instead of reading and making changes, it reads your code more thoroughly, writes up a full plan, and it shows it to you before doing a single thing. And then you can either approve it or deny it. This feature is a must for Cloud models, I think. You get a higher quality result since now the model takes the time to explore and think about its actions before doing something. It's also way easier to catch
Watch from 5:45a mistake in a plan than in like 3,000 lines of code and 12 different files it modifies. I recommend using plan mode for big task. Don't use it for small task like typos, renaming variables, or small design changes. That's just a waste and you don't get much better results. Anyways, back to the improved skill. It's such a good idea. It'll probably become the default strategy if it's not already. Essentially, you would use the smart model to write the plan and then you would use a cheaper, faster model to implement it. Now, keep in mind when I say faster and cheaper, that doesn't mean dumb. Some of these faster models are actually pretty intelligent now, which is why this workflow works. You save way more money, and everybody loves money, right? For example, if you are on Cloud Code, you would use the Fable model. Oh, wait, that's gone. Again, that was recorded over a month ago. It's not gone, but you do need usage credits, so it basically is gone. I guess you would use the Opus model for the plan and then Sonnet for the implementation. But, if you're not using Cloud Code, Cursor, Open Code, Codex, then you can truly mix models. But, overall, my best practices for skills, do not spam skills and do not install a hundred of them. Some of these skills are pretty subjective since everyone has an opinion on good code, so I would also recommend sticking with one specific group of skills or skills that match your coding style. Since we're talking about coding styles and doing things the right way, let's talk about verification. This isn't exactly a feature or a command, it's more so a workflow and best practice. And I'm giving this an S tier, and if anything, a double S or even a triple S, because this isn't just an AI thing. This is just good software engineering fundamentals. AI just makes
Watch from 7:16this more important. So, what exactly is verification? Essentially, you're giving Claude a way to check its own work before it considers something done. It actually has no idea if it's correct, but with verification, it can write the code and see if it's actually correct, not just telling you it's done. Now, there's multiple ways to verify, and the most obvious one is test. But, make sure you do test correctly. Tell Claude to write the test first and then implement. This is important. If you tell it to implement first and then write the test, it's just going to write tests that pass its own code, and that's not exactly testing, that's cheating. Make sure you don't test every single line, just test the most important things. I've noticed that smarter models like to test every single thing when it's really not necessary and it kind of just bloats your code base. Some other ways to verify are type checkers and linters. If your language supports it, tell Claude to run it before considering the task done. Two other ways you can do verification and this is if you're doing front end and design work is screenshot testing and testing with the browser. Because Claude is literally blind, it can't actually see what it's making. With these two verification methods, Claude can actually open your app, click around, get some screenshots and actually see what's happening. It's nice to see that AI models are getting good at using computers. You used to have to use MCPs, but now they're just built in. All right, MCP B tier. Actually, I'm lying. A tier.
Watch from 8:47MCPs give Claude access to other tools. So, things like GitHub, your database, Slack, checking out your analytics, your deployments, and if you do front end work, a browser. Some of the ways I like to use MCPs are for fetching design inspirations, database seeding, so adding fake data to test certain features, researching documentation, and of course browser testing. Now, in my experience, I think you only need an MCP when Claude has to directly interact with something outside your code base. There's really no reason to use an MCP for things like best practices, patterns, or how to implement something because the skill can handle that. The best practices for MCPs are basically the same as skills. Don't spam them. Don't install a bunch of them. Only use what's necessary. Honestly, the big pattern with AI is only do what's necessary. Let's quickly go over some features and commands I feel like not enough people talk about. I'll make it quick because they're simple, but really convenient. {slash} voice. B tier. Claude code has a voice mode. All you have to do is type {slash} voice and just talk. And with this, whatever you say turns into the prompt. I feel like in voice mode, it's easier to be more descriptive than typing. It lets you think out loud and understand what you want more and I feel like it's better for maintaining your technical knowledge. It's also way faster than typing if you're slow at that. {slash} BTW. C tier. Probably won't use this much, but it's nice to have. It lets you ask a question mid-task and it doesn't interrupt Claude or touch the conversation history, so you can ask about stuff Claude has already read or implemented. When you run this command, Claude can't read files or use any commands. It just uses the conversation history, but it's really nice to have if you have a question about something and want to know why it's making these decisions.
Watch from 10:02I mentioned you can use Claude in different ways. {slash} teleport and remote control lets you move sessions between these apps, so you can move between your phone, the web, or the terminal, which I appreciate a lot. Because sometimes I just get that random genius idea or inspiration in the middle of the drive-thru line in McDonald's, and I really got to tell Claude about it. So, I can start that in the mobile app, and when I get home, I can transfer it to my terminal. It's great. If you touch grass a lot, I'll give it an A tier, but I don't go out very much. So, personally, it's kind of like a C tier or D tier, but it is convenient. Shell mode, also a C tier, but I do think it's one of the more underrated features here. If you type exclam- Oh my god, that was terrible. If you start your message with {exclamation point}, you enter shell mode. And this basically goes back to a normal terminal, but the difference in this mode is Claude also sees the output. It's just a really convenient shortcut. {slash} radio, F tier for productivity, but triple S tier for vibes. This command opens up Claude FM, which is just lo-fi music you can listen to while you code. And yeah, that's it. That's the whole feature. I can't play the music because I don't know if it's copyrighted, but it's pretty chill. Let's be honest, not everyone here is rich with unlimited tokens. I can't just spend a million dollars worth of tokens, and neither can big companies. A lot of you are probably on the $20 plan like me, or maybe you're Mr. Big Bucks over here with the $100 or $200 plan. Either way, context management matters for all of you. You see, Claude tracks usage based on tokens. It's not based on how many prompts you send. Every message you send, every file Claude reads, every response it writes, it generates tokens.
Watch from 11:32The goal here is to make these tokens effective and last long for both your usage limits and Claude's performance. Because Claude has a context window that also relies on these tokens. It's basically Claude's short-term memory. Now, the important thing here is Claude has a dumb zone. The more context you use, the dumber Claude gets. It starts forgetting things, contradicting itself, and making dumb mistakes. Claude has two different context limits. One is at like 300,000 tokens, and another one's at a million. I think Claude code to a million tokens. Now, you would think the difference in 300,000 and a million for context would reduce the dumb zone, but all it really does is extend the dumb zone. In my experience, once you're above like 100,000 or 200,000 tokens, that's when the performance starts to dip a bit and those usage limits get cut. You can see Claude's context right now with the {slash} context command. And I'll give this command a B tier. I think it's pretty important to use, especially if you want to get more advanced with AI. And I suggest running this command before you run a big task, but just being able to see the context window doesn't really do much. How should you use your context? In my experience, to get the most out of this context window is number one, for every new task, start a new session. Every task after the first one is just going to be a worse quality because every time I run like a medium or big task with Claude Code, it uses up a lot of context. It's like always minimum 50,000 tokens it uses. And if you tell it to research or use a skill or an MCP, it could easily go above 100,000 tokens.
Watch from 13:00So, if you do multiple tasks and you're just going to get worse output and you're going to run out of your usage limit real fast. Number two, do not let Claude go on research tangents. If you notice that Claude starts to explore files or search topics it doesn't need, tell Claude right away not to do that because every file and website Claude reads is tokens you're spending. If you have specific files and sources it should use, tell it to use it, which leads to the next tip. Be specific in your prompts, stupidly specific. If you give Claude vague prompts, it's just going to read everything to figure out what you want. And this tip is very important for technical decisions. Now, even with these tips, you'll probably end up in a task that actually uses the context limit. And when you do reach that limit, Claude is going to run the {slash} compact command. I'll give this command a C tier when Claude uses it, but if you know how to use it, it's probably like a B tier. This command summarizes the whole conversation history down into a shorter version so that it fits in the context window. If Claude runs this command on its own, that's your sign to just start a new session because when Claude compacts itself mid-task, it basically gets dementia. You'll notice right away there's a bit of a quality drop. Now, if you're on a task where you're positive it doesn't need a separate conversation, it's better to run the command yourself and tell it exactly what to keep. Now, if you want to optimize your context even more, there are some additional community tools built specifically for this. I'll probably just leave them in the description so you can check it out.
Watch from 14:22Ah, yes. You see, AI enthusiasts and software engineers have collectively discovered a revolutionary, innovative solution with AI, the for loop. Yeah, I'm not kidding. It's It's a whole trend right now. I can't wait till we move on to object-oriented prompting and then functional prompting and maybe a little bit of system prompting. I can't wait for this. No, but honestly, it's incredible. And I blame the people saying programmers are going to get replaced or the ones saying, "Why would I ever need to learn to code again?" This is why right here. People are just reinventing the same thing over and over, just in a different font. And if you couldn't read code, you would never even notice. So, please, learn to code. We need more people with actual brains. Knowing how to code is the exact reason why all these tips work and why I get decent results from AI. I don't want you to be the type of programmer where you hit your usage limit and suddenly you can't even work on your own project because you never learned how any of it works. And if that's you, you've already been replaced. I'm sorry. So, if you are going to lean on AI, you should use it to do the work and make you smarter. I mean, it's a win-win. Brain bigger and AI does better work because brain big. You could have Claude teach you as you go. I would recommend that. Make it explain every change instead of blindly smashing accept. But, if you do want something more interactive and specialized where a tutor will walk your small brain through it step-by-step, you can check out today's sponsor, Brilliant. And this isn't the Brilliant you remember. This is the new Brilliant, personal tutor for math and coding.
Watch from 15:39Brilliant already had a world-class curriculum. It covers everything in math and coding from grade five to college and beyond. It's designed by experts from MIT, Harvard, and Stanford. It was interactive so that learning could feel fun. But, no matter how good a curriculum is, private tutoring will always be the single most effective way to learn. Obviously, not everyone can do this. It's expensive and annoying to schedule. So, that's what the new Brilliant is really about. Taking that personal tutor experience and making it something everyone can actually use. And that's where their new tutor, Koji, comes in. It sits right there on your screen while you work. It sees what you're stuck on. It sketches, points, and hits you with the right guiding questions instead of just handing over the answer. Basically, everything a great tutor does. It makes each lesson feel more like a puzzle than a lecture. And now you have someone to train you to think like a software engineer by helping you focus on logical reasoning and debugging. You can try Brilliant's new tutor for free and get 20% off an annual subscription by scanning the QR code or clicking the link in the description. Go learn and make your brain bigger. All right. So, what's the deal with this live-changing command? I mean, {slash} loop, it's pretty straightforward. You give it a time interval, how often it should run this task, and it'll keep doing it. It's essentially like an AI cron job. I mean, I'm not going to lie, it is really convenient. I've been enjoying loops a lot because you can create automations because I'm not working on my personal projects every single day. But, with loops, I've been setting up these routines or automations, and it allows me to keep making progress even when I'm not actually there. Some of my favorite automations that I've been running recently have been on implementing a GitHub issue where every day it'll pick from the open issues in my project and it'll work on it. And so, I come back
Watch from 17:03and there's a PR waiting for me. Another automation I like using is security and bug sweep. It'll scan the code base for any known vulnerabilities or if it finds any bugs, and it'll flag what it finds and puts that into a GitHub issue. And my third automation that I've been testing recently, feature brainstorming, where it's going to look at the code base, the PRs, the issues, and it's going to brainstorm features that would actually help the project. You can also run automations when certain things happen, but it lets you make some really sick automations. I think a lot of companies and open source projects are testing this and they are getting some decent results. It's honestly worth trying. It's here. It's straight. This command is pretty straightforward. You basically give Claude a goal, and it'll keep working on it until it completes it or it needs your help. So, you can do something like make sure every test passed and there's no type errors, and have that as a goal, and Claude will just keep doing it until it meets it. I'll give this command like a B tier if you're on one of the lower plans, but if you are on one of the higher plans or you have unlimited tokens, it's definitely more so on the A tier. We have an agent, which is the main Claude chat. This is the one you always talk to. You can think of this as the daddy agent, the Chad, the group leader, whatever works for you. And a sub agent is just a mini Claude your daddy agent starts for one specific job. So, the sub agent could be a researcher, a reviewer, a debugger. You can make as many sub agents as you want, and each sub agent gets its own context window. It does its thing, and when it finishes, it gives the daddy agent a summary of what it did. There's multiple ways to make one, but honestly, the easiest is just telling Claude to create the sub agent and a description of what it'll do. But, realistically speaking though, most
Watch from 18:34people can't run sub agents all the time because sub agents drain your usage limits so fast. Each sub agent is basically its own full conversation running in parallel. And on the $20 plan, even a small multi-agent setup can eat your entire limit before the task even finishes. But, I will say honestly, sub agents are still like an A tier, and if you do have unlimited tokens or you're on a higher plan, it's easily an S tier. It makes the quality of the implementation so much better. A tier. Work trees is a feature that allows you to check out into multiple branches of the same repository. Every time you create a work tree, it essentially copies the project into its own separate folder, and it's the perfect thing for parallel development with AI. The workflow I essentially use is that every chat is a work tree. So, instead of working on one branch at a time and waiting around, you can work on multiple branches at once, and they're completely isolated. So, you wouldn't have to worry about agents interfering with each other. And Claude Code does have native work tree support. So, what if you don't want to use Claude Code? Well, that's great because it's not the only option. One good alternative is of course CodeX. It's OpenAI's version, and I personally love it. I think that's the one I've been using the most. Their usage limits are actually generous. Our lord and savior Tibo keeps resetting them, so I get to use a lot, and I've been making tons of progress on my projects thanks to him. There's open code, which is essentially the open source version of Cloud Code.
Watch from 20:06And if you want to use any model, I do recommend you check it out. Another alternative that I've seen is a one called pie. It's basically like a minimalist setup. So, if you're the type of person that wants to create their own workflow from scratch, this is the tool for you. And if you're interested in like an IDE and agent combo, there's Cursor. It's what I like to use if I need to use an IDE. This one also lets you pick any type of model. I like their own models. I like Grok and Composer. They're so fast, and they're really cheap. And of course, there's VS Code and GitHub Copilot, the OG. Most of you know what VS Code is. And a recent one that's been getting really good is actually T3 Code. I'll just read it from their website. It summarizes it pretty good. It's an open source control plane for a coding agents. So, if you have a Cloud subscription, you'll probably enjoy the UI of T3 Code way more. But if you have multiple subscriptions, so if you have Cloud Code, Codex, Open Code, Cursor subscription, if you have all of those, then maybe you should check out T3 Code, since you can basically use all your subscriptions in just one application instead of going all over the place. So, go pick whatever AI tool you want to use. If you want to use Cloud Code, so be it. Enjoy those usage limits. And when you do hit those usage limits, go watch more of my videos. I'll see you all in the next video.
Watch from 21:23Full transcript
- 0:00
I have spent an unhealthy amount of time using Claude Code, and I got to get this out of my chest already. Their usage limits suck. Oh my goodness. I say hi and boom, there goes my limit and I got to wait 3 hours. And with this new Claude fable model, I recorded a lot of this footage like a month ago. So yes, I know, it's not new. Leave me alone. Just laugh at my jokes, okay? I've been programming with the $20
- 0:21
plan and I have had situations where I prompt once or twice and I hit the limit. Like bro, no wonder people are getting better results. They don't get enough time to use it properly. I'm glad they're making it better, but it's painful. So I want to share everything that I've learned so you can use it effectively. So things like my workflow, my favorite MCPs, my favorite skills, and I'll also share some ways you can save on some tokens so you can actually
- 0:41
use it more. Trust me, I've learned some strategies to use as little tokens as possible so I can get my money's worth because I am not spending $100 a month for this. That's expensive and I'd rather spend that on a McDonald's. Okay, so what's Claude Code? It's Claude, but for coding. You're welcome. No, but really, it's Claude, but it's specialized for coding and it lives in your terminal. Now, do I like the terminal? Meh. I prefer the IDE approach. Uh specifically the IDE and
- 1:02
agent combo approach. You get the agent interface and an actual IDE. Plus there's buttons I can actually click. I'll take that over a terminal any day. What can I say? I like visuals. I'm a toddler. The good news is you can use Claude Code in your IDE and on the web. Pretty cool. Now, why have I been using it? Well, everyone and their moms are using it, even big tech companies. Some a little too much, Uber. It also made like a billion dollars in 6 months,
- 1:22
which is pretty crazy. And that made every other AI company copy and paste Claude Code and now we have this mess. And every company wants you to learn these types of tools so you can become a tonex engineer so they can give you more work. And that also didn't work cuz it was too expensive. They also gave me some free stickers, which is pretty cool. Do I recommend you learn it? Yeah, pretty helpful until you hit those usage Yeah, pretty convenient. Jobs want you
- 1:42
to learn it. And if it gets you a better chance at a job, hey, you got to do what you got to do. The good news is a lot of these Claude Code concepts apply to other coding agents, which means I can give you some alternatives to Claude Code since this video's not sponsored. Okay, so let's go over the features of Claude Code. I've done my fair share of research. I've looked at some Twitter articles. I've watched YouTube videos. I've seen Claude's tutorials. I've watched videos and articles from the guy who freaking built the thing. As I was
- 2:03
doing research for this video, I realized that Claude Code has like 80 plus different command and features that I have never seen in my life. Did you know there's an ultra plan mode? I didn't. Nobody else uses this. I don't think I've seen the creator use this. Hey, editor Sloth here. I recorded that a month ago, too. And uh ultra plan doesn't even exist anymore. That's how useless it was. Yeah, so originally I was going to go
- 2:23
through every single one, but no, there's way too many. Most of them are just configuration or just useless. So now we're only going to cover the essential ones. And even then, I'm going to tier rank them from how useful they are. Because in my experience, some of these features that people call essential, you're never going to touch. Now, if you are serious and you do want to learn more about programming and AI, you should check out my free newsletter, Sloth Bites. Oh, you don't know what
- 2:45
Sloth Bites is? Sloth Bites is just a newsletter I'm working on. It's currently one of the biggest programming newsletters in the world. I made that up. I don't know if that's true. And it's completely free. Where every week I send you programming advice and news so you can stay up to date and not get behind. Did I mention it's free? All I need from you is your sweet, delectable email.
- 3:06
Let's start with the slash init and Claude file. This is the command you're supposed to run when you first open up Claude Code in a project. So far in my experience, it's all right. Essentially, Claude looks at your entire code base and it puts it all inside this Claude.md file. This file becomes Claude's permanent memory for the project. Now, I have beef with Claude for this feature because other AI agents do the same thing except they put it into an agents.md file. Claude is the only one
- 3:29
that doesn't do this, which is very, very annoying. The one nice thing about Claude files is you can actually import additional files. So if you are using an agents.md file, you can just import it inside the Claude.md file, which saves you from having a symlink. But it would be nice if, you know, Claude just supported it. But it is what it is. There's also a new experimental version of this command. You just have to turn on this environment flag. And this one
- 3:50
actually has some potential. Instead of analyzing the code base and writing the file, it now interviews you, which is really good. And it will now also recommend some skills and hooks, which is really nice. We'll get into those in a bit. Based on my experience, I'm honestly going to give this feature like a C or even a D. I don't use it very much. Whoa, me from a month ago was really stupid. Yeah, after a month my opinion has changed and it still stays
- 4:11
the same. I think it's pretty mid. But the cloud file, I'm moving that up. After months of dealing with the sloppy code, you definitely start to get an idea of these AI models quirks and their habits, really disgusting habits. And so, for the most part, my claw.md file has information like a quick description of the project, current status of it, um my coding styles. And I've also been
- 4:33
testing some interesting things like this working philosophy. A funny rule I have in my file is uh user-facing capitalization. For some reason when uh AI models create designs, they really love to use all caps. No idea why, but it's ugly. Another thing I've been testing and liking a lot is setting the pull request language. But this is what I like to use so far. This file can
- 4:53
change quite a bit. Be flexible with it. But this file is honestly not a make or break thing. You could easily survive not even having one. So, don't freak out too much about it because you can honestly just use skills and you can get similar or even better results. All right, I haven't explained skill A tier, but if you're smart with it, easy S tier. A skill is also just a markdown file, specifically a skill.md
- 5:13
file. It's essentially a guide for something you do over and over that the AI can use when it makes sense or you can explicitly tell it to use it. It would be for things like your best practices, your workflow for something, or how you would research something. Essentially, any type of workflow that's repeatable. Claude Code has some default skills pre-installed like code review, security review, and some other stuff. I will give those skills like a B tier A
- 5:34
tier. I do recommend using them if Claude implements a feature. It's just a nice bonus. Personally, I freaking love skills and I love that there's a whole community of them now because it's literally companies and genius engineers taking their knowledge and best practices and putting it all into one file. So, not only is it useful for the agent, it's useful for me. I've learned so much just reading other people's
- 5:54
skills. So, some of my favorite places to find skills has been the website skills.sh. This is my go-to place for finding and installing skills, but there's also some other GitHub repos where you can find skills. My favorite type of skills that I like to use are Matt Pocock skills. He must read a dictionary every day because his vocabulary is immaculate. Such a smart and brilliant guy. I really like using his grow with doc skill. Helps me refine
- 6:15
my requirements and I also like using the improved code base architecture skill. It's just a nice workflow. I also like that it comes with a nice visual. I mean, hey, you won me over. Like I said, I'm a toddler. I also like using cursors. I like this name. Thermonuclear code quality review skill. Really helpful. It really simplifies the code that AI generates, which eliminates a lot of the slop. Strongly recommend you use this and it actually combines
- 6:36
really good with the improved code base architecture skill. I've been using both of them at the same time and I think they're pretty good. One of the recent skills I like to use is a Shatien's improved skill. I've been trying it out and I'm loving it. I really love the idea here. It audits your code base and it writes the plans for other agents. Oh yeah, play easiest here. If you hit shift and tab on Cloud Code, Cloud goes into plan
- 6:56
mode. Instead of reading and making changes, it reads your code more thoroughly, writes up a full plan, and it shows it to you before doing a single thing. And then you can either approve it or deny it. This feature is a must for Cloud models, I think. You get a higher quality result since now the model takes the time to explore and think about its actions before doing something. It's also way easier to catch a mistake in a plan than in like 3,000
- 7:18
lines of code and 12 different files it modifies. I recommend using plan mode for big task. Don't use it for small task like typos, renaming variables, or small design changes. That's just a waste and you don't get much better results. Anyways, back to the improved skill. It's such a good idea. It'll probably become the default strategy if it's not already. Essentially, you would use the smart model to write the plan
- 7:39
and then you would use a cheaper, faster model to implement it. Now, keep in mind when I say faster and cheaper, that doesn't mean dumb. Some of these faster models are actually pretty intelligent now, which is why this workflow works. You save way more money, and everybody loves money, right? For example, if you are on Cloud Code, you would use the Fable model. Oh, wait, that's gone. Again, that was recorded over a month ago. It's not gone, but you do need
- 8:00
usage credits, so it basically is gone. I guess you would use the Opus model for the plan and then Sonnet for the implementation. But, if you're not using Cloud Code, Cursor, Open Code, Codex, then you can truly mix models. But, overall, my best practices for skills, do not spam skills and do not install a hundred of them. Some of these skills are pretty subjective since everyone has
- 8:20
an opinion on good code, so I would also recommend sticking with one specific group of skills or skills that match your coding style. Since we're talking about coding styles and doing things the right way, let's talk about verification. This isn't exactly a feature or a command, it's more so a workflow and best practice. And I'm giving this an S tier, and if anything, a double S or even a
- 8:41
triple S, because this isn't just an AI thing. This is just good software engineering fundamentals. AI just makes this more important. So, what exactly is verification? Essentially, you're giving Claude a way to check its own work before it considers something done. It actually has no idea if it's correct, but with verification, it can write the code and see if it's actually correct, not just telling you it's done. Now,
- 9:02
there's multiple ways to verify, and the most obvious one is test. But, make sure you do test correctly. Tell Claude to write the test first and then implement. This is important. If you tell it to implement first and then write the test, it's just going to write tests that pass its own code, and that's not exactly testing, that's cheating. Make sure you don't test every single line, just test the most important things. I've noticed
- 9:23
that smarter models like to test every single thing when it's really not necessary and it kind of just bloats your code base. Some other ways to verify are type checkers and linters. If your language supports it, tell Claude to run it before considering the task done. Two other ways you can do verification and this is if you're doing front end and design work is screenshot testing and testing with the browser. Because Claude is literally blind, it
- 9:44
can't actually see what it's making. With these two verification methods, Claude can actually open your app, click around, get some screenshots and actually see what's happening. It's nice to see that AI models are getting good at using computers. You used to have to use MCPs, but now they're just built in. All right, MCP B tier. Actually, I'm lying. A tier. MCPs give Claude access to other tools.
- 10:04
So, things like GitHub, your database, Slack, checking out your analytics, your deployments, and if you do front end work, a browser. Some of the ways I like to use MCPs are for fetching design inspirations, database seeding, so adding fake data to test certain features, researching documentation, and of course browser testing. Now, in my experience, I think you only need an MCP when Claude has to directly interact
- 10:25
with something outside your code base. There's really no reason to use an MCP for things like best practices, patterns, or how to implement something because the skill can handle that. The best practices for MCPs are basically the same as skills. Don't spam them. Don't install a bunch of them. Only use what's necessary. Honestly, the big pattern with AI is only do what's necessary. Let's quickly go over some features and
- 10:46
commands I feel like not enough people talk about. I'll make it quick because they're simple, but really convenient. {slash} voice. B tier. Claude code has a voice mode. All you have to do is type {slash} voice and just talk. And with this, whatever you say turns into the prompt. I feel like in voice mode, it's easier to be more descriptive than typing. It lets you think out loud and understand what you want more and I feel like it's better for maintaining your technical knowledge. It's also way
- 11:06
faster than typing if you're slow at that. {slash} BTW. C tier. Probably won't use this much, but it's nice to have. It lets you ask a question mid-task and it doesn't interrupt Claude or touch the conversation history, so you can ask about stuff Claude has already read or implemented. When you run this command, Claude can't read files or use any commands. It just uses the conversation history, but it's really nice to have if
- 11:27
you have a question about something and want to know why it's making these decisions. I mentioned you can use Claude in different ways. {slash} teleport and remote control lets you move sessions between these apps, so you can move between your phone, the web, or the terminal, which I appreciate a lot. Because sometimes I just get that random genius idea or inspiration in the middle of the drive-thru line in McDonald's, and I really got to tell Claude about
- 11:48
it. So, I can start that in the mobile app, and when I get home, I can transfer it to my terminal. It's great. If you touch grass a lot, I'll give it an A tier, but I don't go out very much. So, personally, it's kind of like a C tier or D tier, but it is convenient. Shell mode, also a C tier, but I do think it's one of the more underrated features here. If you type exclam- Oh my god, that was terrible. If you start your message with
- 12:09
{exclamation point}, you enter shell mode. And this basically goes back to a normal terminal, but the difference in this mode is Claude also sees the output. It's just a really convenient shortcut. {slash} radio, F tier for productivity, but triple S tier for vibes. This command opens up Claude FM, which is just lo-fi music you can listen to while you code. And yeah, that's it. That's the whole feature. I can't play the
- 12:30
music because I don't know if it's copyrighted, but it's pretty chill. Let's be honest, not everyone here is rich with unlimited tokens. I can't just spend a million dollars worth of tokens, and neither can big companies. A lot of you are probably on the $20 plan like me, or maybe you're Mr. Big Bucks over here with the $100 or $200 plan. Either way, context management matters for all
- 12:51
of you. You see, Claude tracks usage based on tokens. It's not based on how many prompts you send. Every message you send, every file Claude reads, every response it writes, it generates tokens. The goal here is to make these tokens effective and last long for both your usage limits and Claude's performance. Because Claude has a context window that also relies on these tokens. It's basically Claude's short-term memory.
- 13:12
Now, the important thing here is Claude has a dumb zone. The more context you use, the dumber Claude gets. It starts forgetting things, contradicting itself, and making dumb mistakes. Claude has two different context limits. One is at like 300,000 tokens, and another one's at a million. I think Claude code to a million tokens. Now, you would think the difference in 300,000 and a million for context would reduce the dumb zone, but
- 13:33
all it really does is extend the dumb zone. In my experience, once you're above like 100,000 or 200,000 tokens, that's when the performance starts to dip a bit and those usage limits get cut. You can see Claude's context right now with the {slash} context command. And I'll give this command a B tier. I think it's pretty important to use, especially if you want to get more advanced with AI. And I suggest running this command before you run a big task,
- 13:55
but just being able to see the context window doesn't really do much. How should you use your context? In my experience, to get the most out of this context window is number one, for every new task, start a new session. Every task after the first one is just going to be a worse quality because every time I run like a medium or big task with Claude Code, it uses up a lot of context. It's like always minimum 50,000
- 14:16
tokens it uses. And if you tell it to research or use a skill or an MCP, it could easily go above 100,000 tokens. So, if you do multiple tasks and you're just going to get worse output and you're going to run out of your usage limit real fast. Number two, do not let Claude go on research tangents. If you notice that Claude starts to explore files or search topics it doesn't need, tell Claude right away not to do that because every file and website Claude
- 14:37
reads is tokens you're spending. If you have specific files and sources it should use, tell it to use it, which leads to the next tip. Be specific in your prompts, stupidly specific. If you give Claude vague prompts, it's just going to read everything to figure out what you want. And this tip is very important for technical decisions. Now, even with these tips, you'll probably end up in a task that actually uses the
- 14:58
context limit. And when you do reach that limit, Claude is going to run the {slash} compact command. I'll give this command a C tier when Claude uses it, but if you know how to use it, it's probably like a B tier. This command summarizes the whole conversation history down into a shorter version so that it fits in the context window. If Claude runs this command on its own, that's your sign to just start a new session because when Claude compacts itself mid-task, it basically gets
- 15:19
dementia. You'll notice right away there's a bit of a quality drop. Now, if you're on a task where you're positive it doesn't need a separate conversation, it's better to run the command yourself and tell it exactly what to keep. Now, if you want to optimize your context even more, there are some additional community tools built specifically for this. I'll probably just leave them in the description so you can check it out. Ah, yes. You see, AI enthusiasts and
- 15:42
software engineers have collectively discovered a revolutionary, innovative solution with AI, the for loop. Yeah, I'm not kidding. It's It's a whole trend right now. I can't wait till we move on to object-oriented prompting and then functional prompting and maybe a little bit of system prompting. I can't wait for this. No, but honestly, it's incredible. And I blame the people saying
- 16:03
programmers are going to get replaced or the ones saying, "Why would I ever need to learn to code again?" This is why right here. People are just reinventing the same thing over and over, just in a different font. And if you couldn't read code, you would never even notice. So, please, learn to code. We need more people with actual brains. Knowing how to code is the exact reason why all these tips work and why I get decent
- 16:24
results from AI. I don't want you to be the type of programmer where you hit your usage limit and suddenly you can't even work on your own project because you never learned how any of it works. And if that's you, you've already been replaced. I'm sorry. So, if you are going to lean on AI, you should use it to do the work and make you smarter. I mean, it's a win-win. Brain bigger and AI does better work because brain big. You could have Claude teach you as you
- 16:45
go. I would recommend that. Make it explain every change instead of blindly smashing accept. But, if you do want something more interactive and specialized where a tutor will walk your small brain through it step-by-step, you can check out today's sponsor, Brilliant. And this isn't the Brilliant you remember. This is the new Brilliant, personal tutor for math and coding. Brilliant already had a world-class curriculum. It covers everything in math
- 17:07
and coding from grade five to college and beyond. It's designed by experts from MIT, Harvard, and Stanford. It was interactive so that learning could feel fun. But, no matter how good a curriculum is, private tutoring will always be the single most effective way to learn. Obviously, not everyone can do this. It's expensive and annoying to schedule. So, that's what the new Brilliant is really about. Taking that personal tutor experience and making it
- 17:28
something everyone can actually use. And that's where their new tutor, Koji, comes in. It sits right there on your screen while you work. It sees what you're stuck on. It sketches, points, and hits you with the right guiding questions instead of just handing over the answer. Basically, everything a great tutor does. It makes each lesson feel more like a puzzle than a lecture. And now you have someone to train you to think like a software engineer by helping you focus on logical reasoning
- 17:49
and debugging. You can try Brilliant's new tutor for free and get 20% off an annual subscription by scanning the QR code or clicking the link in the description. Go learn and make your brain bigger. All right. So, what's the deal with this live-changing command? I mean, {slash} loop, it's pretty straightforward. You give it a time interval, how often it should run this task, and it'll keep doing it. It's essentially like an AI cron job. I mean, I'm not going to lie,
- 18:10
it is really convenient. I've been enjoying loops a lot because you can create automations because I'm not working on my personal projects every single day. But, with loops, I've been setting up these routines or automations, and it allows me to keep making progress even when I'm not actually there. Some of my favorite automations that I've been running recently have been on implementing a GitHub issue where every day it'll pick
- 18:31
from the open issues in my project and it'll work on it. And so, I come back and there's a PR waiting for me. Another automation I like using is security and bug sweep. It'll scan the code base for any known vulnerabilities or if it finds any bugs, and it'll flag what it finds and puts that into a GitHub issue. And my third automation that I've been testing recently, feature brainstorming, where it's going to look at the code base, the PRs, the issues, and it's
- 18:52
going to brainstorm features that would actually help the project. You can also run automations when certain things happen, but it lets you make some really sick automations. I think a lot of companies and open source projects are testing this and they are getting some decent results. It's honestly worth trying. It's here. It's straight. This command is pretty straightforward. You basically give Claude a goal, and it'll keep working on it until it
- 19:12
completes it or it needs your help. So, you can do something like make sure every test passed and there's no type errors, and have that as a goal, and Claude will just keep doing it until it meets it. I'll give this command like a B tier if you're on one of the lower plans, but if you are on one of the higher plans or you have unlimited tokens, it's definitely more so on the A tier. We have an agent, which is the main Claude chat. This is the one you always
- 19:34
talk to. You can think of this as the daddy agent, the Chad, the group leader, whatever works for you. And a sub agent is just a mini Claude your daddy agent starts for one specific job. So, the sub agent could be a researcher, a reviewer, a debugger. You can make as many sub agents as you want, and each sub agent gets its own context window. It does its thing, and when it finishes, it gives
- 19:54
the daddy agent a summary of what it did. There's multiple ways to make one, but honestly, the easiest is just telling Claude to create the sub agent and a description of what it'll do. But, realistically speaking though, most people can't run sub agents all the time because sub agents drain your usage limits so fast. Each sub agent is basically its own full conversation running in parallel. And on the $20
- 20:16
plan, even a small multi-agent setup can eat your entire limit before the task even finishes. But, I will say honestly, sub agents are still like an A tier, and if you do have unlimited tokens or you're on a higher plan, it's easily an S tier. It makes the quality of the implementation so much better. A tier. Work trees is a feature that allows you to check out into multiple branches of the same repository. Every
- 20:37
time you create a work tree, it essentially copies the project into its own separate folder, and it's the perfect thing for parallel development with AI. The workflow I essentially use is that every chat is a work tree. So, instead of working on one branch at a time and waiting around, you can work on multiple branches at once, and they're completely isolated. So, you wouldn't have to worry about agents interfering with each other. And Claude Code does
- 20:57
have native work tree support. So, what if you don't want to use Claude Code? Well, that's great because it's not the only option. One good alternative is of course CodeX. It's OpenAI's version, and I personally love it. I think that's the one I've been using the most. Their usage limits are actually generous. Our lord and savior Tibo keeps resetting them, so I get to use a lot, and I've been making tons of
- 21:18
progress on my projects thanks to him. There's open code, which is essentially the open source version of Cloud Code. And if you want to use any model, I do recommend you check it out. Another alternative that I've seen is a one called pie. It's basically like a minimalist setup. So, if you're the type of person that wants to create their own workflow from scratch, this is the tool for you. And if you're interested in like an IDE and agent combo, there's Cursor. It's what I like to use if I
- 21:40
need to use an IDE. This one also lets you pick any type of model. I like their own models. I like Grok and Composer. They're so fast, and they're really cheap. And of course, there's VS Code and GitHub Copilot, the OG. Most of you know what VS Code is. And a recent one that's been getting really good is actually T3 Code. I'll just read it from their website. It summarizes it pretty good. It's an open source control plane for a coding agents. So, if you have a
- 22:00
Cloud subscription, you'll probably enjoy the UI of T3 Code way more. But if you have multiple subscriptions, so if you have Cloud Code, Codex, Open Code, Cursor subscription, if you have all of those, then maybe you should check out T3 Code, since you can basically use all your subscriptions in just one application instead of going all over the place. So, go pick whatever AI tool you want to use. If you want to use Cloud Code, so be it. Enjoy those usage
- 22:20
limits. And when you do hit those usage limits, go watch more of my videos. I'll see you all in the next video.
Description
SponsorTry Brilliant's tutor for free: https://brilliant.org/TheCodingSloth/ You’ll also get 20% off an annual Premium subscription.
Finally remembered my YouTube password. Anyways enjoy everything I learned from suffering a bunch of hours with Claude Code. If you have any cool workflows or tips, definitely let me know.
// USEFUL CLAUDE CODE TOOLS//
ponytail: https://github.com/DietrichGebert/pon...
rtk-ai: https://github.com/rtk-ai/rtk
caveman: https://caveman.so/
skills.sh: https://www.skills.sh/
// NEWSLETTER //
Sloth Bytes: https://slothbytes.beehiiv.com/subscribe
// BUSINESS INQUIRIES //
For business: thecodingsloth@smoothmedia.co
For brand partnerships: https://tally.so/r/mZVvKa
// SOCIALS //
Twitter: / thecodingsloth1
TikTok: / thecodingsloth
Discord: / discord
// TOOLS/THINGS I REALLY LIKE //
SponsorIf you wanna build 10x developer level projects check out CodeCrafters (40% off):
https://app.codecrafters.io/join?via=...
SponsorIf you want to build an awesome newsletter like Sloth Bytes I use beehiiv (20% off):
https://www.beehiiv.com?via=the-codin...
Sponsor(some of these links are affiliates, so I'll earn some money which supports the channel!)
SponsorThis video was sponsored by Brilliant.
More from The Coding Sloth
×279:41Learn To Code Like a GENIUS and Not Waste Time
The Coding Sloth3.4M views
×2414:2720 Programming Projects That Will Make You A God At Coding
The Coding Sloth3M views
×1810:54Using AI to NEVER LOSE in KAHOOT
The Coding Sloth2.3M views
×1616:36DESTROYING Cookie Clicker With My Cookie God Program
The Coding Sloth2.1M views
