Tokenmaxxing: My Claude Code Workflow

In this video, I wanted to spend a In this video, I wanted to spend a little time to talk about my approach to little time to talk about my approach to little time to talk about my approach to software development using Cloud Code. software development using Cloud Code. software development using Cloud Code. And in the past two or three weeks, I And in the past two or three weeks, I And in the past two or three weeks, I think I've spent around 70 million think I've spent around 70 million think I've spent around 70 million tokens using Cloud Code. So, I've tokens using Cloud Code. So, I've tokens using Cloud Code. So, I've learned quite a few things that work for learned quite a few things that work for learned quite a few things that work for me, and I want to share my workflow with me, and I want to share my workflow with me, and I want to share my workflow with you in this video. Here's my Cloud Code you in this video. Here's my Cloud Code you in this video. Here's my Cloud Code desktop, where you can see my token desktop, where you can see my token desktop, where you can see my token spend starting from June 4th, which is spend starting from June 4th, which is spend starting from June 4th, which is when I started using this. Today is June when I started using this. Today is June when I started using this. Today is June 22nd, so I've been using it for almost 22nd, so I've been using it for almost 22nd, so I've been using it for almost three weeks. And that time, I've spent three weeks. And that time, I've spent three weeks. And that time, I've spent around 70 million tokens, give or take. around 70 million tokens, give or take. around 70 million tokens, give or take. Now, I've been using the $100 plan, Now, I've been using the $100 plan, Now, I've been using the $100 plan, which I believe is called 5x Max. I was which I believe is called 5x Max. I was which I believe is called 5x Max. I was on the 20x plan for a little while while on the 20x plan for a little while while on the 20x plan for a little while while Fable was available, but they took it Fable was available, but they took it Fable was available, but they took it away, and there was no point in away, and there was no point in away, and there was no point in continuing on that plan, so I continuing on that plan, so I continuing on that plan, so I downgraded. Now, you can see some days downgraded. Now, you can see some days downgraded. Now, you can see some days were more useful than others, but in the were more useful than others, but in the were more useful than others, but in the past couple of days, I think I've dialed past couple of days, I think I've dialed past couple of days, I think I've dialed down the approach that works really well down the approach that works really well down the approach that works really well and produces good results for me. Here's and produces good results for me. Here's and produces good results for me. Here's the workflow that I apply when using the workflow that I apply when using the workflow that I apply when using Cloud Code. So, number one, you need an Cloud Code. So, number one, you need an Cloud Code. So, number one, you need an idea. What are you going to work on, or idea. What are you going to work on, or idea. What are you going to work on, or what are you going to build? So, as I what are you going to build? So, as I what are you going to build? So, as I said, I start with an idea, and the said, I start with an idea, and the said, I start with an idea, and the first thing I want to do is produce a first thing I want to do is produce a first thing I want to do is produce a design document. So, this just contains design document. So, this just contains design document. So, this just contains the high-level description of what I the high-level description of what I the high-level description of what I want to build in a little more technical want to build in a little more technical want to build in a little more technical detail. So, here I would define things detail. So, here I would define things detail. So, here I would define things like architecture, code style, and like architecture, code style, and like architecture, code style, and quality constraints, maybe infra quality constraints, maybe infra quality constraints, maybe infra components if I'm adding something new components if I'm adding something new components if I'm adding something new to the system. We could also talk about to the system. We could also talk about to the system. We could also talk about the deployment approach, and whatever the deployment approach, and whatever the deployment approach, and whatever else I think is necessary to fulfill the

else I think is necessary to fulfill the else I think is necessary to fulfill the design that I want to achieve. So, once design that I want to achieve. So, once design that I want to achieve. So, once we've got our high-level definition in we've got our high-level definition in we've got our high-level definition in place, we can then take that and use it place, we can then take that and use it place, we can then take that and use it to break down our high-level feature to break down our high-level feature to break down our high-level feature into smaller subtasks. So, let's say into smaller subtasks. So, let's say into smaller subtasks. So, let's say we've got a couple of subtasks here, and we've got a couple of subtasks here, and we've got a couple of subtasks here, and these are my actual work units that I'm these are my actual work units that I'm these are my actual work units that I'm going to hand off to the agent. Now, going to hand off to the agent. Now, going to hand off to the agent. Now, what I figured out that works really what I figured out that works really what I figured out that works really well for me is to hand off each of these well for me is to hand off each of these well for me is to hand off each of these subtasks to a coding agent in a separate subtasks to a coding agent in a separate subtasks to a coding agent in a separate session. So now this becomes one session session. So now this becomes one session session. So now this becomes one session and I just expand across how many tasks and I just expand across how many tasks and I just expand across how many tasks I have. When you think about it, this I have. When you think about it, this I have. When you think about it, this isn't all too different from how you isn't all too different from how you isn't all too different from how you would lead a software development team would lead a software development team would lead a software development team in the real world. So I'm effectively in the real world. So I'm effectively in the real world. So I'm effectively just replicating what already works in just replicating what already works in just replicating what already works in the real world using agents except with the real world using agents except with the real world using agents except with this our feedback loop is a lot faster this our feedback loop is a lot faster this our feedback loop is a lot faster as we can produce a large amount of code as we can produce a large amount of code as we can produce a large amount of code in very short amount of time. Now this in very short amount of time. Now this in very short amount of time. Now this is also where I want is also where I want is also where I want on how you can actually rein in the AI on how you can actually rein in the AI on how you can actually rein in the AI and stop it from producing slop because and stop it from producing slop because and stop it from producing slop because it's very easy to fall into this trap of it's very easy to fall into this trap of it's very easy to fall into this trap of thinking that you are being productive thinking that you are being productive thinking that you are being productive because you're generating a large amount because you're generating a large amount because you're generating a large amount of code. That's very far from the truth.

of code. That's very far from the truth. of code. That's very far from the truth. Now I do want to comment on how I Now I do want to comment on how I Now I do want to comment on how I actually get the agents to work on actually get the agents to work on actually get the agents to work on something until it's done and this is by something until it's done and this is by something until it's done and this is by using the goal command in Cloud Code. using the goal command in Cloud Code. using the goal command in Cloud Code. Now I think this is an implementation of Now I think this is an implementation of Now I think this is an implementation of what's called a loop although there's what's called a loop although there's what's called a loop although there's also a loop command. It's all a bit also a loop command. It's all a bit also a loop command. It's all a bit confusing. Nonetheless, when I give it a confusing. Nonetheless, when I give it a confusing. Nonetheless, when I give it a goal, it's going to continue working on goal, it's going to continue working on goal, it's going to continue working on this until it satisfies the goal. This this until it satisfies the goal. This this until it satisfies the goal. This is where you can actually make it is where you can actually make it is where you can actually make it produce the desired result. So what you produce the desired result. So what you produce the desired result. So what you do is you take your task description and do is you take your task description and do is you take your task description and feed it to the goal command and then feed it to the goal command and then feed it to the goal command and then it's really important that you come up it's really important that you come up it's really important that you come up with a bunch of constraints. Now with a bunch of constraints. Now with a bunch of constraints. Now depending on your use case, these depending on your use case, these depending on your use case, these constraints can vary. What I do is tell constraints can vary. What I do is tell constraints can vary. What I do is tell the agent to work in a separate kit work the agent to work in a separate kit work the agent to work in a separate kit work tree. This is basically a copy of your tree. This is basically a copy of your tree. This is basically a copy of your repo on the file system. And then the repo on the file system. And then the repo on the file system. And then the agents can work in parallel on separate agents can work in parallel on separate agents can work in parallel on separate work trees. Now this is obviously very work trees. Now this is obviously very work trees. Now this is obviously very resource intensive but it allows you to resource intensive but it allows you to resource intensive but it allows you to parallelize the work as much as parallelize the work as much as parallelize the work as much as possible. Now what I also tell it to do possible. Now what I also tell it to do possible. Now what I also tell it to do is write tests and make sure they pass is write tests and make sure they pass is write tests and make sure they pass and when everything's done, I want it to and when everything's done, I want it to and when everything's done, I want it to create a pull request that I can then create a pull request that I can then create a pull request that I can then review. So the end result of this is I review. So the end result of this is I review. So the end result of this is I now have a lot of pull requests to now have a lot of pull requests to now have a lot of pull requests to review and make sure that everything is review and make sure that everything is review and make sure that everything is in order. Of course, if I'm working on in order. Of course, if I'm working on in order. Of course, if I'm working on something mission critical, I definitely something mission critical, I definitely something mission critical, I definitely want to go in and actually debug code, want to go in and actually debug code, want to go in and actually debug code, but if it's something trivial that I've but if it's something trivial that I've but if it's something trivial that I've done myself dozens of time before, I'm done myself dozens of time before, I'm done myself dozens of time before, I'm going to just review the code and make going to just review the code and make going to just review the code and make sure I have proper integration tests in sure I have proper integration tests in sure I have proper integration tests in place to be sure that this is working place to be sure that this is working place to be sure that this is working correctly. Now, a couple of trade-offs correctly. Now, a couple of trade-offs correctly. Now, a couple of trade-offs that you're going to make with this that you're going to make with this that you're going to make with this approach is code quality is going to

approach is code quality is going to approach is code quality is going to suffer. Now, you have to ask yourself if suffer. Now, you have to ask yourself if suffer. Now, you have to ask yourself if this is something that you are okay this is something that you are okay this is something that you are okay with. The benefit being that you're now with. The benefit being that you're now with. The benefit being that you're now able to iterate much faster and produce able to iterate much faster and produce able to iterate much faster and produce working solutions in less time. This working solutions in less time. This working solutions in less time. This also doesn't mean we're going to produce also doesn't mean we're going to produce also doesn't mean we're going to produce bad code, what people would call slop. bad code, what people would call slop. bad code, what people would call slop. It's just that AI-generated code tends It's just that AI-generated code tends It's just that AI-generated code tends to be more on the verbose side, and if to be more on the verbose side, and if to be more on the verbose side, and if you don't spend quite a bit of time you don't spend quite a bit of time you don't spend quite a bit of time reeling it in and telling it to remove reeling it in and telling it to remove reeling it in and telling it to remove unnecessary parts, you're going to end unnecessary parts, you're going to end unnecessary parts, you're going to end up with a code base that's quite up with a code base that's quite up with a code base that's quite verbose, full of comments, with possibly verbose, full of comments, with possibly verbose, full of comments, with possibly many unnecessary abstractions, for many unnecessary abstractions, for many unnecessary abstractions, for example, interfaces with just a single example, interfaces with just a single example, interfaces with just a single implementation that don't really do much implementation that don't really do much implementation that don't really do much except help unit testing using mocks, except help unit testing using mocks, except help unit testing using mocks, which in my opinion is not that valuable which in my opinion is not that valuable which in my opinion is not that valuable because you want to be integration test because you want to be integration test because you want to be integration test where it's most critical use cases. Now, where it's most critical use cases. Now, where it's most critical use cases. Now, this entire approach can be described this entire approach can be described this entire approach can be described with a single word that I'm going to with a single word that I'm going to with a single word that I'm going to just call token maxing. I totally did just call token maxing. I totally did just call token maxing. I totally did not invent this. I've probably seen it not invent this. I've probably seen it not invent this. I've probably seen it used dozens of times, but it's used dozens of times, but it's used dozens of times, but it's effectively what I'm trying to achieve effectively what I'm trying to achieve effectively what I'm trying to achieve here. I want to use the maximum number here. I want to use the maximum number here. I want to use the maximum number of tokens that's available to me while of tokens that's available to me while of tokens that's available to me while all of this usage is subset. And this is all of this usage is subset. And this is all of this usage is subset. And this is also one of the reasons why I've been also one of the reasons why I've been also one of the reasons why I've been less active on YouTube than usual. I've less active on YouTube than usual. I've less active on YouTube than usual. I've been working on a big project, as you been working on a big project, as you been working on a big project, as you can see by the token spend, that I hope can see by the token spend, that I hope can see by the token spend, that I hope to talk about more in the coming weeks.

to talk about more in the coming weeks. to talk about more in the coming weeks. I also became a dad past month, so sleep I also became a dad past month, so sleep I also became a dad past month, so sleep is now scarce, and finding time to work is now scarce, and finding time to work is now scarce, and finding time to work is even more difficult. And as you can is even more difficult. And as you can is even more difficult. And as you can see by my background, I've moved see by my background, I've moved see by my background, I've moved apartments, and I'm still setting up the apartments, and I'm still setting up the apartments, and I'm still setting up the new studio. A lot of things going on at new studio. A lot of things going on at new studio. A lot of things going on at the same time, and not enough time to the same time, and not enough time to the same time, and not enough time to work on videos. And hopefully, all of work on videos. And hopefully, all of work on videos. And hopefully, all of this gets better sooner rather than this gets better sooner rather than this gets better sooner rather than later. Now, I mentioned that this usage later. Now, I mentioned that this usage later. Now, I mentioned that this usage is subsidized. And I actually took my is subsidized. And I actually took my is subsidized. And I actually took my token spend and gave it to ChatGPT. I token spend and gave it to ChatGPT. I token spend and gave it to ChatGPT. I didn't want to give it to Claude on didn't want to give it to Claude on didn't want to give it to Claude on purpose just to see what ChatGPT is purpose just to see what ChatGPT is purpose just to see what ChatGPT is going to tell me. And it took the input going to tell me. And it took the input going to tell me. And it took the input and output token costs from Anthropic's and output token costs from Anthropic's and output token costs from Anthropic's documentation. Now, these are API costs, documentation. Now, these are API costs, documentation. Now, these are API costs, mind you, and I'm using a subscription, mind you, and I'm using a subscription, mind you, and I'm using a subscription, which is subsidized. And it came up with which is subsidized. And it came up with which is subsidized. And it came up with the figure of about $1,850 the figure of about $1,850 the figure of about $1,850 of token spent in the past 3 weeks. Now, of token spent in the past 3 weeks. Now, of token spent in the past 3 weeks. Now, mind you, I'm paying $100 a month, give mind you, I'm paying $100 a month, give mind you, I'm paying $100 a month, give or take, to get this much in token or take, to get this much in token or take, to get this much in token spent. And I'm not even maximizing my spent. And I'm not even maximizing my spent. And I'm not even maximizing my token usage as much as I should be. I've token usage as much as I should be. I've token usage as much as I should be. I've only figured out how to properly do this only figured out how to properly do this only figured out how to properly do this in the past couple of days. Just to give in the past couple of days. Just to give in the past couple of days. Just to give you a reference, I've managed to use up you a reference, I've managed to use up you a reference, I've managed to use up about 75% of my weekly limit, which is about 75% of my weekly limit, which is about 75% of my weekly limit, which is something that I haven't been able to do something that I haven't been able to do something that I haven't been able to do in the past two cycles. So, this time in the past two cycles. So, this time in the past two cycles. So, this time around, I'm really leaning into it and around, I'm really leaning into it and around, I'm really leaning into it and just trying to maximize my token usage just trying to maximize my token usage just trying to maximize my token usage on the 5x plan on Claude code. I've on the 5x plan on Claude code. I've on the 5x plan on Claude code. I've explained my high-level workflow. What explained my high-level workflow. What explained my high-level workflow. What about some low-level details? For about some low-level details? For about some low-level details? For example, some people are going to ask, example, some people are going to ask, example, some people are going to ask, "What about Claude skills?" I started "What about Claude skills?" I started "What about Claude skills?" I started out not using them. After a week or so out not using them. After a week or so out not using them. After a week or so on working on this project, I just asked on working on this project, I just asked on working on this project, I just asked the agent, "What are some repetitive the agent, "What are some repetitive the agent, "What are some repetitive tasks that I keep asking you to do, and tasks that I keep asking you to do, and tasks that I keep asking you to do, and can you turn those into skills?" And I can you turn those into skills?" And I can you turn those into skills?" And I think that's how you produce actually

think that's how you produce actually think that's how you produce actually useful skills. You figure out the pain useful skills. You figure out the pain useful skills. You figure out the pain points while you work and turn those points while you work and turn those points while you work and turn those into repeatable skills that the agents into repeatable skills that the agents into repeatable skills that the agents can use. I also did not have a Claude MD can use. I also did not have a Claude MD can use. I also did not have a Claude MD or an Agents MD present when I started or an Agents MD present when I started or an Agents MD present when I started working on this. This is also something working on this. This is also something working on this. This is also something I asked Claude to generate for me. And I asked Claude to generate for me. And I asked Claude to generate for me. And one thing that Claude also has is hooks. one thing that Claude also has is hooks. one thing that Claude also has is hooks. I wasn't aware of this, and it's I wasn't aware of this, and it's I wasn't aware of this, and it's something that it suggested I should something that it suggested I should something that it suggested I should add. And I'm using it just to run some add. And I'm using it just to run some add. And I'm using it just to run some extra heavy tests before every command, extra heavy tests before every command, extra heavy tests before every command, and this is coming in handy because it's and this is coming in handy because it's and this is coming in handy because it's saving me a lot of usage in GitHub saving me a lot of usage in GitHub saving me a lot of usage in GitHub Actions because I was running into Actions because I was running into Actions because I was running into timeouts and resource issues with timeouts and resource issues with timeouts and resource issues with running so many agents in parallel. Now, running so many agents in parallel. Now, running so many agents in parallel. Now, another problem you're going to run into another problem you're going to run into another problem you're going to run into when using this workflow, and to give when using this workflow, and to give when using this workflow, and to give you an idea, I usually have like five to you an idea, I usually have like five to you an idea, I usually have like five to 10 agents running in parallel working on 10 agents running in parallel working on 10 agents running in parallel working on different aspects of my code base. And different aspects of my code base. And different aspects of my code base. And one roadblock that I hit was the one roadblock that I hit was the one roadblock that I hit was the available RAM on my system. It turns out available RAM on my system. It turns out available RAM on my system. It turns out that coding agents are incredibly that coding agents are incredibly that coding agents are incredibly resource hungry. And right now I've got resource hungry. And right now I've got resource hungry. And right now I've got 32 GB of RAM, and this forced me to do 32 GB of RAM, and this forced me to do 32 GB of RAM, and this forced me to do perform an upgrade. I opted for two 32 perform an upgrade. I opted for two 32 perform an upgrade. I opted for two 32 GB sticks, which is going to double my GB sticks, which is going to double my GB sticks, which is going to double my effective RAM, and you really don't want effective RAM, and you really don't want effective RAM, and you really don't want to know how much I spent on these. Like, to know how much I spent on these. Like, to know how much I spent on these. Like, the prices of RAM are basically insane.

the prices of RAM are basically insane. the prices of RAM are basically insane. What I can tell you is that the 32 GB What I can tell you is that the 32 GB What I can tell you is that the 32 GB that I bought, I think, 4 years ago, are that I bought, I think, 4 years ago, are that I bought, I think, 4 years ago, are now worth double the amount that I paid now worth double the amount that I paid now worth double the amount that I paid at the time, which is unheard of in the at the time, which is unheard of in the at the time, which is unheard of in the world of computer components. But, I world of computer components. But, I world of computer components. But, I guess this is the sign of the times that guess this is the sign of the times that guess this is the sign of the times that we are living in. Also, here's what it we are living in. Also, here's what it we are living in. Also, here's what it looks like when I get a bunch of results looks like when I get a bunch of results looks like when I get a bunch of results from my coding agents as pull requests from my coding agents as pull requests from my coding agents as pull requests that I now have to sit down and review. that I now have to sit down and review. that I now have to sit down and review. I think this is about nine or 10 pull I think this is about nine or 10 pull I think this is about nine or 10 pull requests. I go through all of them one requests. I go through all of them one requests. I go through all of them one by one, and almost all of these are by one, and almost all of these are by one, and almost all of these are based on some documentation I had wrote based on some documentation I had wrote based on some documentation I had wrote previously in the repo and use that as previously in the repo and use that as previously in the repo and use that as the baseline to produce the actual pull the baseline to produce the actual pull the baseline to produce the actual pull request. Now, as I already mentioned, I request. Now, as I already mentioned, I request. Now, as I already mentioned, I got nearly $2,000 of usage out of a got nearly $2,000 of usage out of a got nearly $2,000 of usage out of a $100-a-month plan. And I don't think $100-a-month plan. And I don't think $100-a-month plan. And I don't think this is going to last for a while. We this is going to last for a while. We this is going to last for a while. We already lost GitHub Copilot subsidies, already lost GitHub Copilot subsidies, already lost GitHub Copilot subsidies, and sooner or later the other providers and sooner or later the other providers and sooner or later the other providers going to have to follow. So, some people going to have to follow. So, some people going to have to follow. So, some people are exploring things like self-hosting are exploring things like self-hosting are exploring things like self-hosting large language models, and currently large language models, and currently large language models, and currently there's a popular DGX Spark machine, there's a popular DGX Spark machine, there's a popular DGX Spark machine, which is selling for almost $5,000, and which is selling for almost $5,000, and which is selling for almost $5,000, and you can run some local models on here.

you can run some local models on here. you can run some local models on here. But, in my opinion, this is currently But, in my opinion, this is currently But, in my opinion, this is currently not worth it, even with all the not worth it, even with all the not worth it, even with all the subsidies in place, because $5,000 is subsidies in place, because $5,000 is subsidies in place, because $5,000 is almost 2 years of cloud code usage on almost 2 years of cloud code usage on almost 2 years of cloud code usage on the 20X Max, which is $200 And don't the 20X Max, which is $200 And don't the 20X Max, which is $200 And don't expect you're going to be running expect you're going to be running expect you're going to be running anything close to Opus or Fable level anything close to Opus or Fable level anything close to Opus or Fable level models, and even then, your local models models, and even then, your local models models, and even then, your local models are going to be just incredibly slow and are going to be just incredibly slow and are going to be just incredibly slow and a pain to work with. Now, who should a pain to work with. Now, who should a pain to work with. Now, who should actually be exploring this path? Well, actually be exploring this path? Well, actually be exploring this path? Well, as I said, privacy is a big concern when as I said, privacy is a big concern when as I said, privacy is a big concern when using AI from popular providers, and using AI from popular providers, and using AI from popular providers, and running local models gives you a lot of running local models gives you a lot of running local models gives you a lot of autonomy, and obviously full control autonomy, and obviously full control autonomy, and obviously full control over where your data ends up. Now, to over where your data ends up. Now, to over where your data ends up. Now, to actually to able to run something useful actually to able to run something useful actually to able to run something useful in terms of a coding agent and then in terms of a coding agent and then in terms of a coding agent and then scale that across a team, you're looking scale that across a team, you're looking scale that across a team, you're looking at a big spending bill to make that at a big spending bill to make that at a big spending bill to make that happen. Maybe you don't need like half a happen. Maybe you don't need like half a happen. Maybe you don't need like half a million or a million dollars to build a million or a million dollars to build a million or a million dollars to build a small data center, but you definitely small data center, but you definitely small data center, but you definitely need to spend multiple tens of thousands need to spend multiple tens of thousands need to spend multiple tens of thousands of dollars on hardware to be able to run of dollars on hardware to be able to run of dollars on hardware to be able to run these models locally. Now, take all that these models locally. Now, take all that these models locally. Now, take all that with a grain of salt as I haven't really with a grain of salt as I haven't really with a grain of salt as I haven't really been into the self-hosting space, which been into the self-hosting space, which been into the self-hosting space, which is something I'm going to explore and is something I'm going to explore and is something I'm going to explore and make videos on. I'll all of that in due make videos on. I'll all of that in due make videos on. I'll all of that in due time. My conclusion is that with the time. My conclusion is that with the time. My conclusion is that with the economics that we have in place today, economics that we have in place today, economics that we have in place today, taking into account the subsidies, the taking into account the subsidies, the taking into account the subsidies, the cost of hardware, and the local models cost of hardware, and the local models cost of hardware, and the local models that we have available, it's still not that we have available, it's still not that we have available, it's still not worth it, at least to me. I'll be worth it, at least to me. I'll be worth it, at least to me. I'll be exploring this avenue, but I definitely exploring this avenue, but I definitely exploring this avenue, but I definitely think you should not be closing the door think you should not be closing the door think you should not be closing the door on this, especially if you care about on this, especially if you care about on this, especially if you care about privacy and owning your data. Hope that privacy and owning your data. Hope that privacy and owning your data. Hope that at least something I shared today with at least something I shared today with at least something I shared today with you is valuable and you can maybe use it you is valuable and you can maybe use it you is valuable and you can maybe use it in your own work. I'm definitely late to in your own work. I'm definitely late to in your own work. I'm definitely late to this game of properly using coding

this game of properly using coding this game of properly using coding agents, so I'm still learning things agents, so I'm still learning things agents, so I'm still learning things myself as I go and I'm going to be myself as I go and I'm going to be myself as I go and I'm going to be sharing them here with you as I gain sharing them here with you as I gain sharing them here with you as I gain more insights. If you found this video more insights. If you found this video more insights. If you found this video valuable, go ahead and smash the like valuable, go ahead and smash the like valuable, go ahead and smash the like button right below. Thanks a lot for button right below. Thanks a lot for button right below. Thanks a lot for watching. I really appreciate it and watching. I really appreciate it and watching. I really appreciate it and until next time, stay awesome.