WEBVTT 00:00:00.000 --> 00:00:03.520 Most AI coding tools still work like this. One task, 00:00:03.840 --> 00:00:04.960 one terminal, 00:00:05.040 --> 00:00:11.360 one conversation at a time. What if I told you you can code much faster because of one bottleneck, 00:00:11.360 --> 00:00:12.640 and that bottleneck 00:00:12.555 --> 00:00:19.995 is your attention. Today, I'm gonna show you how I use OpenCode to run multiple AI tasks in parallel, track usage, 00:00:20.395 --> 00:00:21.995 and stop babysitting 00:00:21.995 --> 00:00:22.875 terminals. 00:00:22.955 --> 00:00:26.315 This is a step by step tutorial and how I actually use OpenCode, 00:00:26.670 --> 00:00:28.030 a real workflow 00:00:28.030 --> 00:00:29.470 under real constraints 00:00:29.550 --> 00:00:45.925 to ship faster without a team. I'm Keith. I built and exited companies, taken one public, and now I help solopreneurs and builders ship faster by turning AI into real systems. I've used pretty much all of the coding tools, Cursor, OpenAI Codecs, 00:00:46.085 --> 00:01:00.290 Cloud Code. You name it. I've tried it. They're all good at generating code. None of them solved the thing that was slowing me down, running multiple tasks and knowing what's happening. So let me show you my old workflow. I'm subscribed to Gemini, Claude, and OpenAI, 00:01:00.370 --> 00:01:14.705 and I used to open a terminal for each one. But the problem was when I try to run multiple tasks in three different windows, I don't know which one has failed, which one is done, and most importantly, I don't know how much credit I have left for each one. So multitasking 00:01:14.705 --> 00:01:42.505 was a complete nightmare. What really ended up happening was I just had one window and I kept using it until the credits ran out, and then I switched to a different one. So I can only do one task at a time. After I switched to OpenCode, it really changed my world because now I can run multiple tasks in parallel and will tell me how much usage I've used. It'll alert me when a task is done, and I can run multiple models on the same project at the same time. Absolute game changer. Quick context, what is OpenCode? 00:01:42.585 --> 00:01:44.425 Here you see OpenCode is open, 00:01:44.745 --> 00:01:48.150 and I think of it basically as a task orchestration 00:01:48.150 --> 00:01:49.430 for AI coding 00:01:49.590 --> 00:02:03.735 instead of just one terminal and one task at a time. Here you see that I have multiple sessions going on, and for each one, I can choose a different model. So I can choose to run GPT 5.2 codecs for one task. 00:02:03.895 --> 00:02:04.775 Let it run, 00:02:05.175 --> 00:02:18.760 and I can run another session using Gemini three Pro. Let that task run as well. And when it's done, it'll alert me so I can run four or five different tasks at the same time, and that's what OpenCode does. I'm gonna go through the step by step instructions 00:02:18.920 --> 00:02:20.040 from installation 00:02:20.040 --> 00:02:23.320 all the way to very advanced features with OpenCode, 00:02:23.560 --> 00:02:31.185 but it's important to understand some high level concepts. So why am I excited about OpenCode? It's because previously I was doing sequential 00:02:31.185 --> 00:02:35.905 one task at a time, and now I can do parallel task and run multiple 00:02:35.985 --> 00:02:38.785 agents coding at the same time. So my job now 00:02:39.105 --> 00:02:49.330 isn't to watch AI work. My job now is to intervene when it's only needed. So what are we covering in this video today? We're gonna be covering from installing OpenCode as a terminal 00:02:49.490 --> 00:02:56.610 or downloading the desktop app and even showing you how the web version works to connecting to all your different AI providers 00:02:56.865 --> 00:03:03.185 like Gemini, OpenAI, how to choose the free models and your paid models, choosing between build 00:03:03.505 --> 00:03:04.705 and planning, 00:03:04.705 --> 00:03:06.305 adding MCP servers, 00:03:06.305 --> 00:03:11.480 adding agent skills, and how to integrate it with tools like warp, and finally, 00:03:11.720 --> 00:03:22.040 giving you a live demo of how I use it in my workflows, working on a project that's generating revenue and running multiple tasks. So the first thing you need to do is go to opencode.ai. 00:03:22.885 --> 00:03:29.045 And the first option I'm gonna show you and the easiest one is to download the desktop app. So you can click on download now, 00:03:29.205 --> 00:03:32.245 and I'm using a Mac app, so I'm gonna download 00:03:32.725 --> 00:03:34.005 Mac OS 00:03:34.005 --> 00:03:38.670 silicon. Alright. It's downloaded. I double click on it and just follow the instructions, 00:03:38.910 --> 00:03:45.150 and you should be granted with a desktop app like this. Alright. The next option is that you can choose extensions. 00:03:45.470 --> 00:03:47.550 And if you're already using Cursor, 00:03:47.550 --> 00:03:50.510 Windsurf, or any of the coding IDEs, you just press install, 00:03:50.955 --> 00:03:54.795 and it'll get installed into those IDEs as well. Very simple. 00:03:54.955 --> 00:04:04.395 And then you have the option of installing it through the terminal. Now what's the difference between installing through an extension or downloading the desktop app? Extensions like Cursor 00:04:04.395 --> 00:04:07.210 give you basically an app with an interface, 00:04:07.290 --> 00:04:15.050 so it makes it easier to have visibility, run multiple tasks, gives you alert, gives you gives you a lot more information to work with. 00:04:15.530 --> 00:04:19.290 But some people prefer terminal because it's very focused, 00:04:19.835 --> 00:04:23.115 and if you're familiar with terminal commands, it can be faster. 00:04:23.755 --> 00:04:26.875 I actually like terminal because I found using terminal, 00:04:26.875 --> 00:04:31.355 for some reason, seems to be faster than using an IDE, 00:04:31.355 --> 00:04:48.910 and you have all these options. Right? Curl, n p m, bun, brew, power. The most straightforward one is actually using this command, the curl command, because it will identify your operating system, and then it will choose the best option to install on your machine. Because if you're using Linux, you might use paru. 00:04:48.990 --> 00:04:56.205 If you're using macOS, you might use brew install. But if you're unsure, just run the curl command. So open your terminal. 00:04:56.285 --> 00:04:58.045 So you can go to terminal 00:04:58.125 --> 00:05:02.765 and open your terminal, but I use this different tool called ghosty. Same thing. 00:05:03.165 --> 00:05:09.770 Just type this in, enter, and it will do its magic. So those are the three options you can use to install 00:05:09.930 --> 00:05:10.730 OpenCode, 00:05:10.730 --> 00:05:18.945 and there's a hidden option which is you can run it on the web. So after you've installed it in the terminal, you just run this command, 00:05:19.265 --> 00:05:20.465 open code web, 00:05:20.705 --> 00:05:35.050 copy, and now it runs in my browser. So you can see that I can run open code there. Okay. So why would you wanna run a web version of open code? I think the most useful use case is where you want to run 00:05:35.130 --> 00:05:46.250 OpenCode on one machine, on one particular machine, and you wanna access it using a different machine, maybe your mobile phone. And so you can connect to it, open a browser, and start coding away while 00:05:46.410 --> 00:05:51.795 the source code of your project is on the computer. A bit of pro tip on installing 00:05:52.035 --> 00:05:53.235 the CLI, 00:05:53.315 --> 00:05:59.155 command line interface, in the terminal is that sometimes you run into trouble. No worries. You can download a tool called 00:05:59.635 --> 00:06:05.400 warp dot dev, and what warp dot dev is is an AI agent for the terminal. So 00:06:05.720 --> 00:06:08.280 you can just copy and paste your command 00:06:08.520 --> 00:06:34.220 into warp dot dev. And if there's any issues, you can just ask AI agent to fix it for you, and it will fix all the issues for you and make sure you get it installed. And once you have installed, all you need to do is type in open code and voila, you're inside the terminal and open code is running. The first thing I wanna show you inside the open code app is the settings because everyone loves dark mode. So you can come here, go to appearance, 00:06:34.860 --> 00:06:40.700 and go ahead and set it to dark. You can choose the font. You can also choose a theme, Dracula, 00:06:40.860 --> 00:06:41.660 Tokyo night. 00:06:42.425 --> 00:06:44.025 So pick whatever you want, 00:06:44.425 --> 00:06:51.305 and you have the option to turn on agents, permissions, errors, and you can also have a sound effect when your task completes, 00:06:51.785 --> 00:06:53.705 and you can also add in shortcuts. 00:06:54.185 --> 00:07:14.345 So that's basic settings. Now I'm gonna go through some of the features that OpenCode has. Right here, there's three different options you can choose from. There's build and there's plan. And how I use it is that when I'm thinking of adding a new feature, I usually go into plan mode first before I build it. So then it thinks through the logic 00:07:14.505 --> 00:07:34.230 and then it builds. Then you can choose your model. Now it comes with a lot of free models. GLM 4.7 is actually pretty good, and you can do a lot with free models already. But in the end, I think paid models are better, and I'd trade money for time any day of the week. Here, I've already connected Google, OpenAI, 00:07:34.230 --> 00:07:37.350 and Anthropic. And usually when I'm planning, I would choose 00:07:38.275 --> 00:07:39.155 Claude, 00:07:39.315 --> 00:07:44.515 but recently Claude announced they don't support third parties, so I do not recommend 00:07:44.835 --> 00:07:48.035 using Claude with open code because you might get banned. 00:07:48.275 --> 00:07:58.670 So when I'm planning, Gemini is better at planning, and so I'm gonna use the most powerful one, which is Gemini three pro preview. And then thinking effort, I can click, 00:07:58.830 --> 00:08:13.315 and I wanna set it on high because I wanna think carefully. And then when I'm ready with the plan, I click on build where it will actually start coding, and I would use either 5.2 or 5.2 codex. If it's more advanced 00:08:13.315 --> 00:08:14.035 feature, 00:08:14.275 --> 00:08:15.875 then I would use codex. 00:08:15.875 --> 00:09:00.125 But if it's something simple like adding a button or just fixing a bug, I would choose 5.2. And if that fails, then I would use a higher context one. So being mindful of my token use. And thinking effort is basically how many tokens you wanna cap your request at. This is an interesting button and actually is a very important tool because it shows how much usage you have left. If you're like me and you're on a $20 plan, things run out pretty quickly, but if you're a $100 plan, it might take you a while to run out, but it's good to see how much context you have left. And another thing I do is sometimes I attach screenshots saying that some certain UI elements are out of place, and I would just screenshot it and attach that and say fix this or show the AI 00:09:00.205 --> 00:09:09.325 what's being made. So those are the options here. I'm gonna take a second here to explain my model strategy because I'm subscribed to Claude, OpenAI, and Gemini 00:09:09.645 --> 00:09:15.050 on a $20 plan. And I like OpenCode because it forces you to think about using 00:09:15.130 --> 00:09:21.530 which AI and which model is most appropriate for your task. Right? And I basically use 00:09:22.330 --> 00:09:23.690 Gemini for 00:09:23.930 --> 00:09:26.090 high level planning, and I use 00:09:26.410 --> 00:09:29.450 OpenAI once the planning is done to execute the code. 00:09:30.245 --> 00:09:32.885 And depending on the task, if it's complex, 00:09:32.885 --> 00:09:51.230 I'll use GPT 5.2 codec. If it's just, uh, like, a simple bug fix or moving a button, I'll use a lower model, and I'll set the token limit to a lower rate. So this is, like, representing the token usage. So this is a good thing to just get in the habit of choosing the right model and thinking about how many tokens you need for 00:09:51.390 --> 00:10:05.155 what task. So another technique I use to save on my precious tokens is that, let's say I have three features. Instead of making it one long continuous chat one after another, which consumes a lot of tokens, 00:10:05.235 --> 00:10:06.835 I split them up into 00:10:06.995 --> 00:10:15.330 new sessions each one so that it saves me money and contacts as well. So a little trick that I use to save tokens. 00:10:15.330 --> 00:10:16.850 OpenCode comes 00:10:16.850 --> 00:10:21.730 with all these free options, but if you wanna be like me and connect to Anthropic, 00:10:22.095 --> 00:10:28.335 OpenAI, and Google, you need to connect to your provider. I'm gonna show you how to connect to different AI models 00:10:28.495 --> 00:10:30.415 in the OpenCode desktop app. 00:10:30.655 --> 00:10:31.935 You click slash, 00:10:32.655 --> 00:10:34.495 and then you go to model. 00:10:35.350 --> 00:10:40.550 And then on the top right, you can click on connect provider, and then you just choose 00:10:40.550 --> 00:11:04.720 the provider that you want. Let's say Google, and then you need to enter your API key. I'm also gonna show you how you can add models if you're using the TUI terminal app, and then I'll go into how you can actually get the API key easily with the help of AI agent without spending, like, ten minutes clicking around. Here, I've opened my terminal, and here I can type in slash, go down, and choose select. 00:11:04.720 --> 00:11:07.840 And then you can see that I've connected to Anthropic, 00:11:07.840 --> 00:11:18.960 OpenAI, and Google, but there's so many options here. This is the only tool where I've seen you can basically connect to everything that is out there. And I wouldn't underestimate 00:11:19.065 --> 00:11:20.185 the Chinese 00:11:20.265 --> 00:11:21.625 AIs because 00:11:22.105 --> 00:11:27.545 right now, in sixth place and seventh place, you have GLM 4.7, 00:11:27.545 --> 00:11:33.225 which is open source, and MiniMax, which is also open source. That's beating ChateaPT 5.2 00:11:33.385 --> 00:11:46.080 and Gemini three Flash. So you can get pretty good results with these other options as well, and it's much cheaper to subscribe to them. So let's click on one of them. I have Perplexity, so let's click on Perplexity, 00:11:46.080 --> 00:11:56.895 and then you enter your API key. And how do you do that? Well, I use a browser called Perplexity Comment, and what I can do is I can come here on the top right assistant, 00:11:57.855 --> 00:12:08.470 and the AI agent will actually click around the interface and find the API key for me. So saving you time from clicking and trying to find all these API keys for Google or ChatGPT. 00:12:08.470 --> 00:12:13.510 Just quick note that you never wanna pass your API keys or passwords into AI. 00:12:13.830 --> 00:12:20.595 And so this hack to do this is I need to create an API key for OpenCode from Perplexity. 00:12:20.595 --> 00:12:27.795 Can you set up the API key so that it goes up to the stage where the key is ready for me to manually copy and paste? 00:12:28.660 --> 00:12:35.140 Please do not copy and paste it for me. So right now, I've given instructions to basically set up the API key, but don't copy it. 00:12:35.620 --> 00:12:44.615 Stop there, and then I'll manually copy it and paste it into OpenCode. And now it should save you a ton of time in clicking around on interface. Okay. Now it's done. 00:12:45.175 --> 00:12:49.015 I'm gonna copy and paste. Okay. And now it's connected, 00:12:49.495 --> 00:12:59.580 and I can choose which one. And then now I should be able to go in Perplexity. I can choose Sonar, Sonar Pro, reasoning. So it's connected. So that's how you connect your different 00:12:59.740 --> 00:13:01.100 AI providers 00:13:01.420 --> 00:13:03.820 to OpenCode. Now I'm gonna actually 00:13:04.380 --> 00:13:07.260 show you how I actually use OpenCode. 00:13:07.660 --> 00:13:25.215 When you first come in, you're gonna open a project. If you're starting a new project, then you gotta create a new folder. And so I'm gonna open a project, and here I've opened my project. To give you some context, I have an app here, which is a health data analyzer app where you sync your health data and it gives you analysis, 00:13:26.020 --> 00:13:36.180 and you can do AI analysis of your health data as well. So here you can see that I've got an issue here with this not displaying correctly. So let's take a screenshot, 00:13:36.260 --> 00:13:42.775 and we'll use that in a bit. And now that I've connected, I wanna first fix that bug. I'm going to 00:13:43.575 --> 00:13:44.375 attach 00:13:44.535 --> 00:13:47.495 the screenshot and say for the graphs, 00:13:48.295 --> 00:13:49.815 the time frame 00:13:49.895 --> 00:13:51.655 word is out of place. 00:13:52.215 --> 00:13:53.815 Can you fix it? And then 00:13:54.280 --> 00:13:58.280 I can click send. So it's using the attach image function, 00:13:59.080 --> 00:14:01.640 and I've chosen my model. 00:14:03.960 --> 00:14:07.320 While that is running, this will display and it's doing its magic. 00:14:07.785 --> 00:14:10.345 I'm gonna start a new session. I'm gonna plan, 00:14:10.985 --> 00:14:14.025 and I'm gonna choose Gemini, which is different model, 00:14:14.585 --> 00:14:19.065 and say, for my health analyzer app, I wanna add some gamification 00:14:19.065 --> 00:14:19.785 ideas 00:14:20.260 --> 00:14:30.500 to the products so it makes it more sticky, maybe adding streaks or something. But the end idea is to make sure people sync their data on a regular basis 00:14:30.900 --> 00:14:34.260 and kinda reward them for the when they actually do 00:14:34.575 --> 00:14:36.175 sync their data. So 00:14:36.495 --> 00:14:41.055 I'm gonna let it plan, hit enter, and you can see here that this is running. 00:14:41.455 --> 00:14:57.120 And, also, my other session is also running. So this is where multiple thing can run at the same time, I and can start another session and say, can you some ideas on how to improve the UI, UX of the product? I can run that too. And you'll see that if we check-in, 00:14:57.120 --> 00:14:59.040 it it's showing you the progress 00:14:59.600 --> 00:15:01.760 and the time it's elapsed 00:15:01.920 --> 00:15:08.215 and also how much code is being changed with the plus sign and or how much is being deleted. You can see 00:15:08.535 --> 00:15:13.815 all the changes it's making in the code base. And when you see this blue icon, 00:15:14.535 --> 00:15:15.495 it means that 00:15:16.200 --> 00:15:19.560 the task has been completed. You can also turn on notification 00:15:19.720 --> 00:15:29.960 where it will show up on the top right of your Mac that a task has been completed. I turned it off because it was just popping up all the time, but if that's something you like, you can have it run as well. 00:15:30.695 --> 00:15:36.455 And now all three tasks are done, and let's see if it actually fixed the problem. So you see this 00:15:36.615 --> 00:15:40.135 is out of place. Let's turn it off and run it again. Alright. 00:15:40.455 --> 00:15:44.375 And the time frame wording is gone completely, and 00:15:44.880 --> 00:15:49.520 that's been fixed. So happy with that. And for the gamification, 00:15:49.600 --> 00:15:50.960 it's giving me 00:15:51.600 --> 00:15:53.440 some suggestions on 00:15:53.920 --> 00:16:04.655 adding basically a badge and milestones, and I kinda like the idea. So let's try to build it. So I turn on the build mode right now. I'll switch back to GPT 5.2. 00:16:05.055 --> 00:16:09.935 Yes. Yes. Proceed with this plan, and then let's see what happens. So you can run 00:16:10.255 --> 00:16:14.320 multiple sessions at the same time, but let me show you something else. 00:16:14.960 --> 00:16:18.240 I don't have just one product, but I have multiple products. 00:16:18.880 --> 00:16:21.040 I can open another project, 00:16:21.360 --> 00:16:44.340 and in there, I can also run multiple sessions. So I can be working on two projects at the same time, and each project can be running multiple sessions at the same time as well. So you can be running many, many things at the same time. Alright. And it's added the streaks, and so let's go back into the app, and let's check it out. And there it is. I've added a street count, three days, seven day, fourteen day, 00:16:44.660 --> 00:16:45.620 thirty day. 00:16:45.940 --> 00:16:49.460 Looking really good. I think I could do a little bit more 00:16:49.940 --> 00:16:53.300 by showing more than just three, seven, fourteen, and thirty, 00:16:54.095 --> 00:17:01.535 but no, it's done a good job. So looking very good. Okay. Now let's look into some of the more advanced features it offers 00:17:02.175 --> 00:17:02.975 and 00:17:03.055 --> 00:17:05.855 one of the secrets is that you can type the slash command 00:17:06.450 --> 00:17:11.890 and a lot of cool things show up. Okay. Let's start with the first command, is the init instruction. 00:17:11.970 --> 00:17:26.275 It creates an agents dot m d file. I would highly recommend doing this because OpenCode will read all your files and your folder structures and create a file that makes it more efficient to run-in the future. So if you wanna save your tokens and do more faster, 00:17:26.675 --> 00:17:34.580 definitely worth running this command. And now it's running, and you can see that it's running some code style guidelines, 00:17:34.980 --> 00:17:37.460 formatting, naming conventions, error handling, 00:17:37.540 --> 00:17:43.380 and creating this agents dot MD file. And just to showcase this parallel 00:17:43.380 --> 00:17:48.205 feature, I'm gonna start a new session, and let's do the second thing, which is review. 00:17:48.205 --> 00:17:53.805 What does a review command do? It basically looks at your code, checks for security vulnerabilities, 00:17:53.805 --> 00:17:55.805 any potential bugs or issues 00:17:55.965 --> 00:17:57.245 or styling issues, 00:17:57.800 --> 00:18:10.200 And it just goes through your code and make sure it's in a good state. And I run this from time to time and I also refactor my code from time to time if I'm adding a whole bunch of features. Because sometimes you might add in some code that's not used anymore 00:18:10.635 --> 00:18:17.275 and you wanna remove that to keep your file size smaller. And here it's come back with some issues 00:18:17.355 --> 00:18:18.075 and 00:18:18.155 --> 00:18:26.650 that's great. You know, it's realized there's a issue in my current streak and, uh, it should fix that. I think it's a good idea to fix it. Can you please fix it? 00:18:27.690 --> 00:18:33.290 And then here's the agents dot m d, and let's take a look. It's realized as an Xcode 00:18:33.530 --> 00:18:34.170 project, 00:18:34.410 --> 00:18:34.810 and 00:18:35.290 --> 00:18:36.810 it's just all these things, 00:18:37.545 --> 00:18:47.225 naming conventions, concurrency error handling. And so this this is actually really useful because in the future, it will reduce the tokens required to run my project. 00:18:47.545 --> 00:18:54.750 So useful to run and always initialize a new project. Okay. Next thing we're gonna do is look into MCPs. 00:18:54.990 --> 00:18:58.190 So you can toggle on and off your MCPs, 00:18:58.190 --> 00:18:59.870 and here I've added Playwright. 00:19:00.110 --> 00:19:16.695 It has ability to open a browser and pretend to be user and click around and do stuff for me using an AI agent. The MCP I want to add is Context seven and basically is an MCP that will help me save tokens again by allowing it to read API documentation and libraries 00:19:16.935 --> 00:19:23.810 at a much lower cost than reading everything at once. So to use context seven, I need to sign up and generate an API key, 00:19:24.210 --> 00:19:26.050 and then I need to add this 00:19:26.690 --> 00:19:29.010 to the configuration file. 00:19:29.330 --> 00:19:34.995 So if I come to open code, it says you have to add something like this to my configuration 00:19:34.995 --> 00:19:42.835 file. And now I have a hack here where I can use warp dot dev that I mentioned earlier, and I wanna say find 00:19:43.315 --> 00:19:52.840 the global open code dot JSON. That's where the configuration file is because I hate clicking around and finding the right directory and the right file, 00:19:53.240 --> 00:19:57.960 and this allows me to kind of quickly find the global file. Once it's 00:19:58.040 --> 00:20:03.175 found a global file, I'm going to ask it to add this bit of code inside, 00:20:03.495 --> 00:20:14.935 and I will share the code in the description. You can get it there as well. I'm adding the contact seven MCP to the open code file, and then I accept the change. Can you open the file 00:20:15.610 --> 00:20:19.290 using Sublime note editor so I can add in the API key? 00:20:22.170 --> 00:20:24.650 So here you see that it's 00:20:24.650 --> 00:20:35.145 added this to my config file, and all I need to do is copy and paste my API key. I signed up for contact seven, and I get, like, a free API key with a thousand requests. 00:20:35.305 --> 00:20:36.825 So I'm gonna generate 00:20:36.825 --> 00:20:39.785 that and put it in. I'm gonna label it open code. 00:20:41.465 --> 00:20:50.070 Paste it in. Save. And then let's close and restart open code and see if it's added successfully. So I'll come here, MCP, 00:20:50.070 --> 00:20:51.430 toggle MCPs. 00:20:51.590 --> 00:20:55.110 There you have it. 7 is added. Even though I added 7, 00:20:55.110 --> 00:21:00.550 I keep forgetting to call 7. You have to say use 7 00:20:59.925 --> 00:21:00.885 specifically. 00:21:01.285 --> 00:21:05.685 So inside the documentation, actually, suggests adding a rule. 00:21:05.925 --> 00:21:08.805 Always use 7 when I need library documentation. 00:21:08.805 --> 00:21:16.140 So how do you add this rule to OpenCode? So remember the agents dot m d file when we initialize the project? 00:21:16.540 --> 00:21:20.380 Well, we're gonna go do that. I'm gonna go to OpenCode and say, 00:21:20.700 --> 00:21:22.060 this rule 00:21:22.380 --> 00:21:23.420 to the 00:21:23.820 --> 00:21:25.235 agents dot 00:21:25.315 --> 00:21:25.875 d. 00:21:28.115 --> 00:21:40.650 And there you go. It's added the rule to the agents dot m d file, and from now on, it's gonna save me tokens and call contact 7 on its own without me calling it. And so that's how you add MCP servers 00:21:41.050 --> 00:21:41.770 to 00:21:42.250 --> 00:21:47.290 improve your coding experience combined with rules. Now that we've gone through the desktop app, let's go through the 00:21:47.770 --> 00:21:57.705 terminal app and check out the command line interface. I'm gonna use warp here, but you don't have to use warp. You can just open terminal or you can use ghosty or whatever terminal 00:21:57.705 --> 00:22:04.585 app you use. And the first thing I need to do is to open my directory. So I go to CD, go to projects, 00:22:04.900 --> 00:22:08.180 and then I drag and drop the location. 00:22:08.500 --> 00:22:11.700 This means change directory, and then it'll ask you to optimize 00:22:12.180 --> 00:22:12.820 and, 00:22:13.060 --> 00:22:14.660 of course, I do wanna optimize. 00:22:15.060 --> 00:22:30.685 Okay. Now how do you bring up OpenCode? All you need to do is type in OpenCode and voila. You're in. So you can do the same things you can do on your desktop app, but now you need to use these keys. So control t allows me to control 00:22:31.005 --> 00:22:45.610 the variant. So how many tokens kept? I can press tab to change agent, so planning or building, and then control p allows me to switch models. So I can choose and you can see that the desktop version allows me to have more selection. 00:22:46.010 --> 00:22:49.770 The desktop only gives me three options, but the terminal is way more powerful, 00:22:50.485 --> 00:22:59.445 Allows me to choose way more options than the desktop app. Super powerful stuff here. So that's why you would use the terminal because it's just got way more functionality. 00:22:59.445 --> 00:23:00.565 Also, I 00:23:01.045 --> 00:23:02.165 type the slash button, 00:23:02.900 --> 00:23:05.460 I have more options to choose from. 00:23:05.780 --> 00:23:07.380 So I can choose a theme, 00:23:07.620 --> 00:23:08.660 so let's say 00:23:09.060 --> 00:23:11.140 Tokyo Night Solarized, 00:23:11.860 --> 00:23:13.220 I can go orange. 00:23:13.700 --> 00:23:28.255 I'm gonna stick with the original because I like it, but you can change the color scheme. I can see the status and I can go to sessions and I can see all the sessions are happening right now. Right now, I can only run one task at a time. What if I wanna be like the desktop 00:23:28.415 --> 00:23:29.375 and run multiple 00:23:30.070 --> 00:23:39.750 sessions at the same time? Well, what I can do is I can go to split pane right and I can keep clicking it and open three or four panels 00:23:39.910 --> 00:23:48.595 and then I do open code, open code, open code, and all of a sudden I have four tabs open and I can run four sessions 00:23:49.075 --> 00:23:56.115 at the same time in the same project. What if I wanna run another project? Well, I can just click here and open a new tab 00:23:56.595 --> 00:23:58.515 and I can open another 00:23:58.515 --> 00:23:59.315 project 00:23:59.520 --> 00:24:03.520 and I could have multiple sessions within that project as well. 00:24:04.000 --> 00:24:12.560 So you can do the same thing you did in desktop app and run multiple sessions and agents at the same time as well. So much like Claude, 00:24:12.560 --> 00:24:19.075 you can also add skills to your open code. So what are skills? Skills are reusable sets of instructions. 00:24:19.075 --> 00:24:20.035 So if you're 00:24:20.355 --> 00:24:21.795 running certain commands 00:24:22.275 --> 00:24:23.795 over and over again, 00:24:24.115 --> 00:24:29.160 it might be useful to turn it into a skill. So let's try to add that skill inside OpenCode. 00:24:29.160 --> 00:24:34.840 Can you help me create a skill for Xcode refactor patterns and help me add it to the skills.md? 00:24:37.640 --> 00:24:52.865 And now it's created a refactoring skill which is gonna help clean up my code and make it run better. To run the skill, would need to restart. I'm gonna close this, come back to open code. Yeah. Let's try it. Can you run the Xcode refactor 00:24:52.865 --> 00:25:02.740 pattern skill? Alright. Turns out I'll I added an extra s to the MD file. It needs to be skill and not skills. Don't make the same mistake I made. So now it's recognized 00:25:02.740 --> 00:25:03.380 my 00:25:03.540 --> 00:25:04.900 Xcode refactor 00:25:04.900 --> 00:25:08.500 pattern skill and is now running the refactoring. 00:25:10.885 --> 00:25:16.005 Pick one for me and run it. And there you have it. It's running the skill. I wanna show you our commands. 00:25:16.645 --> 00:25:22.565 So what are commands? When you tap on the slash button, all of these options are commands, 00:25:23.520 --> 00:25:28.720 and you can add to them. So I think a useful command for me is git commit and push. 00:25:29.200 --> 00:25:33.120 So I'm going to try and add that. So I'm gonna copy 00:25:33.200 --> 00:25:42.505 open code dot a I doc slash commands. Using this as a reference, can you add a command called that git commits and pushes for me? 00:25:44.665 --> 00:25:50.905 Let's see if we can add the command. So we successfully added the command so let's give it a shot. I open up OpenCode. 00:25:50.905 --> 00:25:52.745 This looks for git 00:25:52.825 --> 00:25:56.660 git push and there you have it. I have a new command. 00:25:57.140 --> 00:26:05.860 Now I'm gonna show you an advanced feature. Imagine you can run OpenCode on your mobile phone just like this. I'm gonna show you how to do it using Termius. 00:26:06.260 --> 00:26:19.185 Let's get started. So to run open code on your iPhone, you need to set up your Mac as a server where it's running the open code. Then you need to download Termius, the app, and connect VISSH 00:26:19.345 --> 00:26:26.080 to basic run open code on your computer but displayed on your iPhone screen. Now in this demo, I'm just gonna show you 00:26:26.560 --> 00:26:29.360 how to make it run when you're on the same network within this 00:26:29.920 --> 00:26:40.415 in the same house or in the same office. If you wanna run it remotely while you're out and taking a bus ride or driving a car, you'll need to set up more stuff to create a 00:26:40.975 --> 00:27:04.995 split tunnel so then you can connect remotely to your computer. But that's going to be another video because it's not easy at all. And if you're interested, stay tuned for my next video where I'll go through how to use Cloudflare to do that. But to get started, you need to set up SSH connection on your MacBook. So first thing you need to do is go to system settings, and then go to sharing, 00:27:04.995 --> 00:27:06.275 and you need to enable 00:27:06.675 --> 00:27:18.380 remote login. And then you need to add a user account. And when you log in, you just type in a name and the password you use to log in to your Mac. And now you've enabled remote connection to your Mac using SSH. 00:27:18.380 --> 00:27:23.820 You need to download the Termius app. So on your iPhone, search for Termius 00:27:24.185 --> 00:27:29.705 and download the free app. After you've downloaded Termius app, open it and go to hosts. 00:27:29.785 --> 00:27:31.865 Click on discover local devices. 00:27:32.665 --> 00:27:36.105 You should see your Mac here as long as you're connected on the same Wi Fi network. 00:27:37.100 --> 00:27:47.820 Click on it. Click tick. Enter the username and then the same password you used to log in to your Mac. You should see a terminal, and then all I need to do is type open code and boom. 00:27:48.300 --> 00:27:56.015 We've got open code running. Like I said, this only works if you're on the same WiFi network. I will produce another video to show you how you can connect remotely 00:27:56.015 --> 00:27:59.135 when you're outside traveling on the bus or whatever 00:27:59.375 --> 00:28:01.615 using Cloudflare and split tunnels. 00:28:01.855 --> 00:28:08.620 Stay tuned for my next video. I hope you enjoyed this video and gained a better understanding of OpenCode. If you enjoyed the video, please like and subscribe 00:28:09.100 --> 00:28:23.905 to my channel. If you wanna learn more about AI, feel free to join my free AI community. You can join my community for free inside the description. I also have a vibe coding course. If you wanna learn how to code, you can also find that inside my community. See you inside.