WEBVTT

00:00:00.000 --> 00:00:07.520
So there's this newer slash command called slash goal, which is now native to both Codex and Cloud Code. Most people are using it exclusively

00:00:07.520 --> 00:00:16.305
for technical tasks, like migrating code bases or running batch tests. But the truth is you can use slash goal for pretty much anything, including

00:00:16.385 --> 00:00:23.585
optimizing your existing AgenTic operating systems. And whether you've been building your AgenTic OS for a while or you're just getting started,

00:00:23.825 --> 00:00:56.245
you will hit the familiar problems over and over again. The skill folder that keeps on growing, the claud m d's or agent m d files that keep expanding, and the rules that start contradicting each other. You mean to clean it up, but you never had the time to. So what if you didn't have to carve out time to do all the cleanup yourself? What if you could point slash goal at a folder or your entire computer and give it a series of nontechnical tasks that it executes to perfection? And what if you could bring every dormant side project you've ever had back to life? If you know how to use slash goal properly, these will no longer be hypotheticals.

00:00:56.245 --> 00:01:31.520
So in this video, I'm gonna quickly walk you through what slash goal is and how it works, and then apply it to five real agentic scenarios. One to clean, one to sharpen, one to revive, one to forge, and one to maintain. Just seeing me go through all of them should spark a lot of ideas. Let's get into it. Now just in case you don't know what slash goal is or does, I'll quickly walk you through it. So you start off by giving the AI a goal or objective function in 4,000 characters or less. Once it has this, it goes in a loop and it has a judge side by side. And most people don't know that this judge actually operates out of a different language model. So technically,

00:01:31.600 --> 00:02:05.290
you do have a devil's advocate looking at the work of the primary agent until it gets to its terminal state. So basically, every time the agent thinks it's done, it has another agent looking over its shoulders to confirm, has the condition been met? If it clears, the goal is done and is set to be accomplished, and these can take anywhere between a few minutes all the way up to an hour to complete depending on the complexity. Now most demos of this slash goal use it on something very formulaic, something like go and build me a snake game while I sleep or go and scrape all of these websites until you have a perfect CSV.

00:02:05.450 --> 00:02:28.800
In our case, we're giving the agent a mirror. We're telling it to go through all of the assets, the markdown files, the rules, the agent MDs to see how it could best optimize itself. So the target of the goal is optimizing the very system trying to achieve the goal. The overarching goal of the demos I'm about to walk through are taking a messy workspace and bringing order to it. So if we pop into a terminal here, you'll see that we have a hypothetical folder

00:02:28.880 --> 00:02:30.560
with 47 skills

00:02:30.720 --> 00:02:45.025
as well as seven different rule files. If we scroll down, you'll see that the goal is set here. If it wasn't set, it would tell you that you're over the character limit, and I think due to the specificity of our prompt, it actually completed this in under three minutes. So it took two minutes and fifty seconds,

00:02:45.345 --> 00:02:48.945
and the result is it took 47 skills and made them into 17.

00:02:49.470 --> 00:02:59.870
30 were archived, which is good because we wanted to store anything it removed just in case we disagreed with it. Then it took seven rules and made it into four. It found three rule contradictions,

00:03:00.190 --> 00:03:26.200
and then it said whatever removed from the ClotMD. And by the way, if it's your goal to go infinitely deeper on things like Cloud Code, AgenTix systems, and AgenTix OS systems for your business, then you wanna make sure you check out the first link down below for my early adopters community. My primary focus in there, just like on YouTube, is giving you all the magic without the hype. Maybe I'll see you inside, and let's get back to the video. So we covered the clean use case, but what about sharpening?

00:03:26.200 --> 00:03:41.235
Let's say we have a series of files, one of which is the rubric dot m d file, where you create evaluation criteria ahead of time before you even run slash goal. So let's say that this is all the criteria that I use, which is actually pretty similar to creating thumbnails,

00:03:41.235 --> 00:03:44.115
especially the little clawed mascot themed thumbnails.

00:03:44.275 --> 00:03:48.310
I can paste a goal like this. So I will paste this in,

00:03:48.710 --> 00:03:50.470
and then it reads the following.

00:03:50.710 --> 00:04:12.385
Go through this skill dot m d file for each input. Go through our test inputs so we can basically give it simulation criteria, or we can ask it to create its own simulation criteria. And then simulate the skill's output, then score it against the rubric. And then you can go even deeper here. You could say, go and use a series of sub agents to go simulate and run the skill,

00:04:12.625 --> 00:04:17.630
go through the outputs, and come back to me and tell me how well it does based on this criteria.

00:04:17.790 --> 00:04:22.030
But the one thing you accomplish by creating the rubric yourself is you can guarantee

00:04:22.110 --> 00:04:25.470
that the goal will be accomplished against your specific criteria,

00:04:25.710 --> 00:04:30.665
not some easy made up one by the AI itself. Because if you've tested using AI before,

00:04:30.985 --> 00:04:47.580
usually, it will go easier on itself to try to increase the chances that it accomplishes the goal. And you'll see it started an iteration log so we can take a look at all of the chain of thought and the rationale that it's using, and then it's rewriting the Skill MD to enforce all of the five rubric criteria.

00:04:47.740 --> 00:05:14.820
So let's say you work in a specific domain where all of your skills should always have some form of standard or specific set of outputs. You can make sure that all of the skills in your arsenal always abide by that by constantly optimizing them. Couple minutes, we have the fix and the optimized version of the skill ready to go. Let's say you're one of the many users in the world that have a series of projects, a plethora of half built bridges. You start a project, you work it to 70%,

00:05:14.820 --> 00:05:24.420
but you've never taken it all the way or at least not to a point where it's production ready. Our goal here is to try to revive as many of our existing 22 projects.

00:05:24.845 --> 00:05:27.885
So you can then send this prompt. We could do goal

00:05:28.045 --> 00:05:35.725
and then send this over. So the prompt reads as follows. You're essentially asking Cloud Code to go through every project and every subfolder

00:05:35.725 --> 00:05:39.885
to use, test, and see what existing Git commits,

00:05:39.965 --> 00:05:45.060
tests, Python functions exist to see how it could revive or resurrect

00:05:45.060 --> 00:06:01.805
any of these projects and if they deserve to be resurrected to begin with. Now in my case, I purposely created a series of useless projects so it could catch them as dormant hello world projects. And what it does is remove them and keeps the ones that are actually useful. Now we move from reviving to forging.

00:06:02.045 --> 00:06:18.300
And one interesting use case you can use slash goal for is going through all the transcripts between you and Claude code in every single session and having it pull out which prompting patterns deserve to be something like a skill. Because all these transcripts are stored in what are called JSONL

00:06:18.300 --> 00:06:39.320
files, which are basically fancy JSON files. And I personally even have a skill that's called slash convo review where I ask questions to go through all the conversations through all the folders if I can't remember which folder I worked on and a specific project. But if you wanna find the nuggets that deserve to be skills, then you can write something like this where we'll do slash goal

00:06:39.480 --> 00:06:45.400
and we'll paste this specific command. And this is basically asking it to go through all the transcripts

00:06:45.835 --> 00:06:50.315
in your folder. In your case, you'll want it to go through the tilde, little squiggly line,

00:06:50.635 --> 00:06:54.715
Cloud Code folder because it will go through all the session transcripts globally,

00:06:54.715 --> 00:07:03.870
and then it will go through back and forth to look between user and assistant. Assistant is Cloud Code, user is you, and it will try to find and extract

00:07:03.950 --> 00:07:52.235
three recurring prompts that deserve to be a skill and then naturally we're going to ask it to create said skills. And you'll see in our hypothetical world it found three recurring patterns that don't seem to have skills that should. One of them is the Excalidraw doodle canvases. Those are the images that you see on those canvases I show you in most videos. Now I actually do have a skill that I'm hiding from this folder, but for all intents and purposes, it can't see it on purpose. Number two is auditing content for patterns, obviously, my YouTube content. And number three, it doesn't see my LinkedIn skill that I have in a completely separate folder. So it's seeing a series of transcripts about LinkedIn posts generated from my transcripts with no associated skill. Within a few minutes, we have all three skills ready to go, and you can start testing them and seeing if it hits the mark.

00:07:52.555 --> 00:07:55.355
Now for this last use case, I'm gonna throw you a curveball.

00:07:55.355 --> 00:07:59.755
Because when you use Cloud Code, there are three main ways that you can have it run autonomously

00:07:59.755 --> 00:08:27.725
without you being at your computer. Them is to use slash loop, which will execute some task every x amount of time. It could be every five minutes, every thirty minutes, every hour. The next one is the one we've spent this entire video on, which is slash goal. And the very last one is the tried and true hooks where you can make it run on a specific event or at the very end of a session. So hypothetically, instead of creating something new or leaning things down right now, what if we wanted a regular maintenance of our infrastructure?

00:08:28.125 --> 00:08:32.810
You could theoretically go through the remaining skills we have where we went from 40 to 17,

00:08:33.050 --> 00:08:35.690
and we want this cleanup done on a regular basis.

00:08:36.090 --> 00:08:52.275
So we could write a compound prompt like this where we do slash, loop, and in this case, we put the time interval every thirty minutes. This could be every hour, every ninety minutes. It might be overkill, but it's more so to show you that you can combine them together. And then you could do slash goal.

00:08:52.355 --> 00:08:54.915
Then after that, we paste the rest of the prompt.

00:08:55.315 --> 00:09:01.955
So you could tell it to archive any skill that hasn't been used in the last thirty days and constantly check for different criteria.

00:09:02.600 --> 00:09:37.130
You can make this whatever you want, but the core idea is this sets it up to run-in the background so long as your session is open, and it can keep refreshing things, keep checking are your rules relevant given all the work that you've done? Is your CloudMD as optimized as it can be? And then we ask it to maintain all of the changes or all of the proposed changes in a maintenance log file. So it creates the cron job to run on your computer, and it has the scheduled goal to run every thirty minutes. And naturally, can use slash goal and slash loop for whatever you want. But when it comes to your Genetic OS,

00:09:37.370 --> 00:09:42.175
using it as a way to maintain your infrastructure or at least constantly auditing

00:09:42.175 --> 00:09:44.095
if your skills, CloudMDs,

00:09:44.095 --> 00:09:57.620
and any associated Agenic OS assets are optimized is way easier than having to remind yourself to do it every day. And here's an example of a hypothetical finding where it found one stale skill called drifted skill, which I actually don't know about,

00:09:57.940 --> 00:10:02.820
last used March 31, which is forty five days old and one contradiction.

00:10:02.980 --> 00:10:13.225
So imagine you have this system running and it keeps looping, it keeps writing this maintenance log, and then you can start analyzing your maintenance log to see how well is it maintaining my infrastructure.

00:10:13.385 --> 00:10:53.025
And then it goes through, and you can see it's looping here. It will keep running in this terminal, but you get the idea. So, hopefully, this gives you a good glimpse into how powerful slash goal can be, not just to all of these other tasks like build me a million dollar startup, don't make mistakes, but to actual practical use cases for your Agenic OS systems. If you wanted access to the prompts that I showed you so you could use them or take derivatives of them for your own use case, I'll make them available to you in the second link in the description below. And last but not least, if you wanna go infinitely deeper on things like Clawd Code, AgenTek OS systems, and looking at all the plumbing that needs to happen to run it perfectly, then you wanna check out the first link, and maybe I'll see you in my early adopters community.