14:03Chase AI · Listicle
10 CLI Tools That Make Claude Code Unstoppable
A 14-minute listicle that makes the case for CLIs over MCPs and hands you the stack to prove it.
March 21stThe argument in one line.
A Claude Code Agentic OS is only as valuable as the codified skill library underneath it — the dashboard is a facade, and building it before the backbone is why most of these setups deliver nothing.
Read if. Skip if.
READ IF YOU ARE…
- You use Claude Code daily but still describe tasks from scratch in each new session instead of invoking named skills.
- You want repeatable, testable outputs from Claude Code rather than one-off conversational responses.
- You are considering building a command center or dashboard for your AI workflows and want to know what actually makes it useful.
- You want to package Claude Code workflows for non-technical team members or clients who will never open a terminal.
SKIP IF…
- You are looking for a ready-made dashboard template or UI walkthrough — this is architecture-first, not UI-first.
- You already have a mature skill library and are genuinely working at the memory or observability layer.
The full version, fast.
A Claude Code Agentic OS has three layers: skill backbone, memory organization, and dashboard. Most people build them in the wrong order. The skill backbone — codifying your repeatable daily tasks into named, testable skills — is the only layer that generates real leverage. Obsidian provides an 80-percent memory solution without RAG complexity, and index files at every folder level are the key structural pattern. The dashboard only matters once the first two are solid; the choice between an Obsidian-embedded dashboard and a Streamlit web app comes down to solo ergonomics versus team distribution.
Free for members
Chat with this breakdown — free.
Sign in and you get 23 free chat messages on us — ask for the hook, quote a framework, find the exact transcript moment, generate a markdown action plan. Bring your own key when you want unlimited.
Create a free account →Where the time goes.
00:00 – 03:35
01 · The Real Power
Hook establishes the anti-dashboard argument and introduces the three-layer Agentic OS model: skill backbone, memory layer, dashboard. Argues the backbone is where all real value lives.
03:35 – 10:42
02 · Creating the Backbone
Walks through the skill triage process: open terminal, describe daily workflows, ask Claude to extract and codify skills. Introduces the skill creator skill for A/B benchmarking. Demonstrates higher-order workflow skills (Content Cascade). Covers the local vs. cloud automation decision tree.
10:42 – 13:53
03 · What’s the Point of Obsidian
Clarifies that Obsidian is an organization layer, not RAG or a vector database. Walks through the Karpathy vault structure (raw/wiki/output) and argues that index files at every subfolder level are the single most important pattern for navigating at scale.
13:53 – 17:30
04 · The Command Center
Compares two dashboard paths: Obsidian-embedded (ergonomic, integrated terminal, harder to distribute) vs. Streamlit web app (simple skill-button panels, trivially distributable). Recommends solo operators go Obsidian; anyone packaging for clients go web app.
17:30 – 20:04
05 · The Landscape
Addresses the cost concern around headless -p Claude Code runs now billed to API credits. Concludes it is a non-issue at normal usage. Notes Codex CLI as a ten-minute drop-in engine swap if costs become a problem.
Lines worth screenshotting.
- The dashboard of a Claude Code Agentic OS is only as powerful as the skill architecture underneath it — without a skill backbone, it is just a button panel that does nothing.
- Most people use Claude Code as a slightly better ChatGPT: they describe tasks from scratch every session instead of codifying repeatable work into named, invokable skills.
- Turning a task into a skill does two things: it compresses a paragraph of description into a single word, and it makes the task testable so you can A/B benchmark the skill against no-skill.
- A single higher-order workflow skill can chain nine individual tasks into one invocation — the Content Cascade skill downloads a transcript, writes a blog post, LinkedIn post, Twitter post, and publishes them all.
- Obsidian is not RAG. It does not embed anything or use a vector database — it is an organization layer that gives humans and AI a navigable folder structure.
- Index files at every Obsidian subfolder level are the single most important structural pattern — without them you will be lost at 5,000 documents.
- The Karpathy vault structure (raw to wiki to output) is a good baseline, but the specific folders matter less than having consistent index files throughout.
- Local automations run when your computer is on and have access to all your files and CLIs. Default to local unless you need always-on scheduling without your machine.
- The Obsidian-embedded dashboard trades easy distribution for personal ergonomics and an integrated terminal. Choose it if you are a solo operator who will never hand this off.
- The Streamlit web app dashboard trades ergonomics for trivial distribution — a non-technical client or team member can execute skills with a button click.
- The -p headless Claude Code flag now bills to API credits rather than subscription limits, but at normal usage you would have to aggressively spam automations to hit $200/month.
- Codex CLI is a drop-in engine replacement for headless Claude Code — switching takes roughly ten minutes and eliminates the API cost concern entirely.
- The skill architecture is engine-agnostic: everything built on Claude Code as the backbone can be pointed at Codex or any other CLI-accessible model with a simple refactor.
- Skill creation is most powerful when personalized — browsing mega repos of community skills is less valuable than codifying the 20 things you actually do every single day.
- An 80 percent solution that is in place beats a perfect knowledge graph that never gets built — Obsidian with index files is that 80 percent solution for most people.
Build the backbone before you build the dashboard.
WHAT TO LEARN
A Claude Code Agentic OS is only as useful as the skill library underneath it — the command center is a presentation layer, not the product.
- Codifying a repeatable task into a named skill does two things at once: it compresses the invocation from a paragraph to a single word, and it makes the task benchmarkable so you can verify it actually improves output quality.
- Higher-order workflow skills that chain multiple tasks into one invocation compound the leverage — a single skill can replace nine separate steps without requiring nine separate invocations.
- Obsidian is an organization layer, not a knowledge graph. It does not embed or retrieve semantically. Its value is navigability at scale, and index files at every folder level are what make that navigability possible.
- When deciding where to run an automation, default to local: local automations have access to your files, CLIs, and installed skills. Cloud automations run on provider servers and have none of that.
- The choice between an Obsidian-embedded dashboard and a web app dashboard is a distribution question, not a power question. Solo operators gain ergonomics from Obsidian; anyone distributing to teams or clients gains simplicity from a web app.
- The skill architecture is engine-agnostic. Whatever you build on Claude Code as the backbone can be redirected to Codex or another CLI model in a single refactor session — the system outlives any one provider.
Terms worth knowing.
- Agentic OS
- A personal or team operating system built around an AI coding agent, consisting of a skill backbone, a memory/organization layer, and an optional dashboard for visibility and distribution.
- Skill backbone
- The collection of codified, named, and testable skills that represent the repeatable tasks in a workflow. The foundational layer of an Agentic OS.
- Skill triage
- The process of narrating your daily workflows to Claude Code domain by domain and having it identify and codify the repeatable patterns into named skills.
- Headless Claude Code
- Running Claude Code programmatically via the -p flag without an interactive session, typically to power automation buttons in a dashboard or scheduled routines. Now billed to API credits.
- Karpathy vault structure
- A three-tier Obsidian folder pattern — raw, wiki with index files at every level, and output — designed to stay navigable at large document scale.
- LightRAG
- A retrieval-augmented generation implementation using a full knowledge graph with embeddings. The fancy end of the memory-layer spectrum, contrasted with the simpler Obsidian approach.
- GWS CLI
- Google Workspace Command Line Interface — enables Claude Code to perform actions in Gmail, Google Drive, and Google Calendar as skills.
- Content Cascade
- An example higher-order workflow skill that takes a YouTube video and automatically generates and publishes a blog post, LinkedIn post, and Twitter post in a single invocation.
Things they pointed at.
11:52conceptKarpathy RAG vault structure
19:00toolCodex CLI
08:56toolGWS CLI (Google Workspace CLI)
01:36toolLightRAG
Lines you could clip.
00:00
“Your Claude Code Agentic OS sucks, and it’s because you’re focused on the wrong things.”
07:25
“You’re pretty much just using it as a slightly better ChatGPT.”
17:23
“If you don’t have that, this is just some fancy nonsense. You need some actual meat to this.”
07:37
“Anytime we can make things less random, the better. By codifying these things you do day to day and turning them into skills, that’s one giant step forward.”
Word for word.
Read-along
Don't just watch it. Burn it in.
See every word as it's spoken — crank it to 2× and still catch all of it. The same dual-channel trick behind Amazon's Kindle + Audible.
00:00Your Cloud Code AgenTic OS sucks, and it's because you're focused on the wrong things. You're spending all your time on fancy dashboards and command centers like this one and this one instead of focusing on what actually drives value in a Cloud Code AgenTic OS. And that's this, a skill and automation backbone that actually drives everything.
00:22The problem is creating something like this at a high level takes time, isn't flashy, and can be kind of boring, when we compare it to these wild looking command centers that bring in a ton of views. But the truth is to get any value out of a Claude coded Gentec OS, especially when we're talking about the observability piece, the dashboard piece, the command center thing, it's only going to happen if this is locked in.
00:47And that's because a strong AgenTic OS has three parts to it. The first is what you see right here. It's the skill and automation backbone.
00:54It's the idea that we are going to take Claude code and turn it into a system that can give us reliable outputs. We are gonna take your daily or your teams or your clients' workflows and tasks, turn those into skills, turn those skills into automations where it makes sense, and in the process, build out a cohesive system like you see here so we can do the same thing over and over again at a high level and get consistent outputs.
01:21The second part of an AgenTek OS is the memory layer. How do we handle the idea of context engineering? Well, there's a number of ways we can do it.
01:28We can do something super fancy with full blown knowledge graphs and do something like LightRag, or we can keep it simple and just use something like Obsidian, which is a 80% solution that's more than enough for the vast majority of people. And it's only once we've locked all that in does any sort of dashboard or command center for an OS make sense.
01:48Because the value of a dashboard really comes in two parts. First is the observability side. That's the idea that I can kinda cover some of the weaknesses of being in a terminal.
01:58Things like seeing my metrics for my social media channel, being able to quickly dive into different audience metrics, have all my research shown to me on one tab. The second half of that value comes from here, all these sort of buttons. And that's the idea that if I want to bring the power of Cloud Code to a team member or to a client who's never gonna jump into the terminal, I can instead build out that skill architecture for them, assign it to these buttons, and they can essentially just execute them on command by just clicking them.
02:26And so today, I'm gonna show you how to properly set up this skill backbone. And then we're gonna talk about the dashboard side of it because there is a lot you actually can do in this scenario, and there's really two paths you can go down. Like you've been seeing, I've kind of been showing you two versions.
02:40There's the one you see here, which is literally a part of Obsidian itself, which is pretty cool because we also get an integrated terminal. And there's this web app version, which is really built for distribution if you're someone who's trying to bring in other team members or packages for clients. But before we jump into the nitty gritty of how to do it, a quick word from today's sponsor, me.
02:59So as you know, inside of Chase AI plus, I just released the ClaudeCode masterclass, which is the number one way to go from zero to AI dev. But I have also just added an agentic OS masterclass inside as well. So everything you see in today's video, the prompts, the dashboards, the setups, all that can be found at a much deeper level inside of chase.aiplus.
03:20There's a link to that in the pinned comment. Also, today, I guess, when this video comes out, I'll be running a free webinar of how to set up an AgenTic OS for yourself going through all three layers.
03:30So if you want to join, make sure to check out the pinned comment as well. I'll have a link for both of those.
03:36So if this is where all the value lies, how do we set this up and why is it set up like this? Why does it look like an org chart? Well, the whole org chart setup like you see here where we have stuff broken out into different sections like productivity and research and content, This is just to help you visualize something that is ultimately invisible.
03:53This is just for your mental model, and it's the idea that you do a bunch of different things across a bunch of different domains in your day to day, week to week flows, and whether it's in your business or just in your personal life. For me, that is split up amongst things like my productivity.
04:07So things like Google, research, content, my community, my agency, my sales, on and on and on. And what we need to do for you is we need to take the giant morass of things you do in a day to day, right, all these different tasks, and we need to break them out, and we need to turn them into skills.
04:27Why do we need to turn them into skills? Well, chances are the way you work right now with Cloud Code, when you needed to do something, you just spin up Cloud Code in the terminal and you kinda tell it what to do. You're pretty much just using it as a slightly better chat GPT.
04:42And if you're doing this all the time, why are we not codifying this into a skill? Because when we codify it into a skill, there's a few things that gives us.
04:51One, it's convenient. I'm taking that entire task, and instead of talking about it over the course of a paragraph, I just tell it to do skill whatever. It could be a single word, and it does it.
05:01So the convenience is one piece. The second piece is that since we have codified it, we can also test it. Using something like the skill creator skill, we are able to actually benchmarks this benchmark the skills we create so we can see if a, does the skill even make sense because it will a b test it against us using the skill versus not having the skill at all.
05:23And over time, if this skill is good, we're gonna start getting more deterministic outputs from a system that is inherently nondeterministic.
05:32Like, when we talk about LLMs, there's a certain randomness to it, just inherent to how it works.
05:38Anytime we can make things less random, the better. And by codifying these things you do day to day and turning them into skill, that's one giant step forward in doing so. And while that makes sense to a lot of people, if you were to ask them if they'd actually ever sat in front of their terminal, turned their mic on, opened up Claude, and said, hey.
05:56Here's my daily plan. Here's what I do. Can you pull some skills out of that and then turn them into skills using the skill creator skill?
06:06You could probably count the percent, like, on one hand, which is wild because this is one of the easiest yet most powerful upgrades to how you use Cloud Code. And this visualization is kinda just there to help you think about it because we do a bunch of different things in a bunch of different domains. And oftentimes, we can even combine a lot of the tasks we do into quote unquote, like workflow skills or higher order skills that have it do a bunch of different things at once.
06:33For example, I have a skill called the content cascade skill. This skill for all intents and purposes is a content repurposer.
06:42When I create a YouTube video and I call on the content cascade skill, it does a number of things for me. It downloads the transcript. It creates a blog post.
06:50It creates a LinkedIn post. It creates a Twitter post. It spins up Playwright.
06:54It then posts those things for me. That's a bunch of different individual tasks all in one.
07:00But instead of breaking out into nine different skills, well, now it's just one skill. And that's something that can be a huge, like, productivity boost.
07:10But if you've done that with all the different things you do in your day to day, probably not. And it's this process of sort of walking through what you do step by step and codifying it. That's the power of an agentic OS.
07:22Everything we do outside of this, the memory layer, the dashboard, it's kinda just a nice little bow around it. And if you're someone who's not trying to work with team members, someone who's not trying to package these things and sell it, you could probably stop here and you're at, like, you know, the 80% solution, and you're way ahead of the pack.
07:39And so to actually execute this process is pretty simple. At its core, you're just going to do what I said, open the terminal, start a new session, and just start talking.
07:50And at the end, say, hey. Can we turn this into any sort of skills? Now I have an entire prompt that breaks this down at a very detailed level of how to do this skill triage, but at its core, that's all we're doing.
08:01Here's what I do. Turn it into skills. Sweet.
08:04Okay. Let's test the skills. Let's move on to the next domain in my business, in my team.
08:09And the thing is, this is gonna be extremely customized and specific to you.
08:15I think we get kind of lost in the morass of, like, the 10,000,000,000 skills that are floating around. We go to these mega repos, like awesome Claude skills, and we look through 10,000,000 different skills thinking this is what's gonna change, you know, my day to day outcomes with Claude code. And it's like you're kinda looking for a diamond in the rough here.
08:33When instead, knowing that one of the most powerful parts of Claude code is how easy it is to customize it for you, like, why aren't we leaning into that more in a systemized way? But outside of the custom stuff, I think there's a few things that almost everyone can get some value out of, I think, on the productivity side.
08:50A big one is if you're in the Google ecosystem. I've kinda talked about it before using things like the GWS CLI to basically allow you to do anything inside of the Google ecosystem and turning those into skills, whether that's like email triage, Google Drive work, or stuff on the calendar.
09:06But the truth is you can also just use the standard MCP connectors that come with Cloud Code. And I'm just talking about the basic claude.a I Gmail, Google Calendar, and Drive. The only things you're really losing there is you're not gonna be able to send emails, but you can still do drafts, which for a lot of people is good enough since they don't want it to actually send them off, and that takes thirty seconds to do.
09:29And, like, it's such a productivity boost that, again, very few people actually do. Now after you've gone through this skill creation process, next becomes the decision tree when it comes to automations. For each skill, it doesn't need to be on demand, or is it something we can turn into routine inside of Cloud Code?
09:44Remember, when we talk about routines and automations with Cloud Code, it's broken down into two different parts. That's going to be local automations versus automations running in the cloud.
09:56If you don't know which is which, just stick with local. That basically means it's gonna run when your computer's on and you have some version of CloudApp. On the cloud, that means it's gonna be run on Anthropix servers, and you're gonna be limited to how many you can do because they're basically paying for it.
10:10And if you're on the cloud, hey. It doesn't have access to your actual computer. It's not running on your computer.
10:15It doesn't have your CLIs, skills, your files. So most of the time, it's just gonna be a local automation if you're in doubt.
10:22And this is the process by which you create the backbone for a Claude code AgenTek OS. And I keep saying Claude code. The truth is Claude code is just the engine, and we'll talk about this a little bit a little bit more.
10:32You could replace this with codecs. You could replace this with really anything. You know, we're building the chassis for this.
10:39We can swap out the engine at any time. So everything I say here also applies to something like Codex. Now let's talk about Obsidian and memory very quickly before we dive into the command center observability dashboard piece because I think a lot of people get confused about what Obsidian's actually buying you and the point of it all.
10:55Remember, the point of Obsidian is simply an organization layer. Obsidian isn't doing anything special to all these markdown files.
11:04It's simply giving us, the human being, a way to kind of figure out what the heck is going on in our files and gives us a simple way of sort of connecting them. It isn't inherently changing the memory.
11:16This isn't rag. It's not embedding anything. There's no, like, vector database despite, you know, these, like, cool graphics.
11:24Like, this isn't a true knowledge graph in that sense. That being said, being organized, especially when we talk about being organized at scale with thousands and thousands of documents, is very important, and it's not important just to you being able to figure out where stuff is.
11:37It eventually becomes important to cloud code at a certain scale in terms of token efficiency for finding things. That's why everyone brings up this. Right?
11:45The Carpathi rag. I'll go through it very quickly. It's just the idea that we have a vault, which is where Obsidian lives, and some series of subfolders.
11:52Carpathi says, hey. We have raw for, like, unstructured data. We have wikis, which kinda break the take the unstructured data and turns it into, like, reports, articles, and then we have outputs for, like, deliverables.
12:05So, hey. I did some research on AI agents, which which went to raw. That research got turned into an article about AI agents in my AI agent wiki.
12:13Hey. I turned that into a slide deck. That's sort of the idea.
12:17The truth is you don't have to do that at all. Alls you need to do is you need to figure out something that makes sense to you, and it needs to be created in a way that you and Claude code could snake your way through the folder system if there was a 100,000 files in there.
12:33A baseline like this is a good start, especially because there are things called master index files and index files all over the place. These index files are essentially at every level of Obsidian.
12:45Remember, Obsidian is just a folder, so we're talking about every subfolder we go down. There's some sort of folder that's acting like a table of contents. So if I'm in the vault I click on the Wiki folder, inside the Wiki folder is a table of context called an index file, which tells me, oh, inside here, we have agents, rag systems, and content creation wikis.
13:07Cool. I know where to go. I go inside the AI agent folder.
13:10What's inside there? There's another index. There is another table of contents saying, hey.
13:16Inside the AI agents folder, we have this document and this document. That's the biggest thing I would take out of Carpathi is the idea of indexes and indices and the idea that for every layer I go down in Obsidian in my file structure, there's some sort of master document that points me in the right direction.
13:33If you don't have that in the beginning, have fun figuring that out when you're 5,000 documents deep. For me, in my scenario, I have several folders. I have an archive, content, notes, dashboard, inbox, ops, project systems, Wiki.
13:46Makes sense for me. I have an index. I understand what's going on.
13:49You, like all these things, need to customize it so it makes sense for you. And speaking of customizations, now let's go into the dashboard piece, these command centers for these agentic operating systems. We talked a little bit already about the value play there.
14:03Right? It's the idea that there's visibility and I can actually see things that I couldn't see in the terminal, and we have sort of like these skill panels that anyone could use.
14:12The next question becomes why the heck are there two of them? Why do you have this one inside of Obsidian itself? Because I'm inside of Obsidian here.
14:19And why do you have this one as a Streamlit app on a local host that's essentially a web app? What's the difference between these two? Which makes sense for what?
14:26Well, I think the value play for the Streamlit applications or really any sort of web app that's your dashboard layer for Jentec OS is for distribution. If I wanna bring this to a team or really if I wanna package this for clients, having it set up like this is super easy. I can have the template inside of a GitHub and I can clearly or very quickly distribute that to anyone anywhere.
14:48Setting this up takes literally seconds. And if this is meant for a nontechnical team member or a nontechnical client, keeping it as simple as possible like this and just having clear buttons that are mapped to skills and execute some, that's great. That's all they want.
15:01The Obsidian forward dashboard is a little bit different. You're trading distribution for really ergonomics at this point. And I would argue a little bit more power because it's super easy, as you can see here, to also have an integrated terminal inside of your Obsidian command center, which basically means I now have the best of both worlds.
15:22Not to mention because it's inside of Obsidian, all my stuff is right here for me to play around with. And Obsidian is infinitely customizable like over here. Right?
15:30You know, I have my full calendar, but this isn't like a calendar plugin. This is literally me just having the Google Calendar web page open and put here on the right hand side.
15:41On the overview, I have a very clear idea of what's going on that day, what my tasks are, what's going on with the activity feed, and, like, where I'm at across different communities. I wanna dive deeper into audience stuff. I have a tab for that.
15:52If I wanna dive deeper into research, I have a tab for that that shows, like, trending GitHub repos, stuff going on Hacker News, as well as some of my breeze, which are also tied to skills, things like headlines, things going on x in YouTube, and, like, content opportunities. Again, having this if I'm in a pure terminal setup is just a little bit clunky.
16:12It's a little more difficult. The problem though with the Obsidian setup, I kind of alluded to it, is the idea of distribution. How could I distribute something like this to a team or to a client?
16:23You can kind of do it because this whole dashboard command center is essentially just a custom plugin that Claude Code created, but it's a little more, again, clunky and awkward to set this up for somebody else. It's not just like, oh, clone it.
16:38You're good to go. It's like, okay. Clone it.
16:39Now go into Obsidian. Now enable these plug ins. Now move this here.
16:43Move this there. Do all this stuff. So there's a certain awkwardness to it.
16:48So if you're someone who's like a solo operator and you're like, hey. I want an AgenTic OS with Cloud Code.
16:54I want all these cool customizable buttons, whatever they may be, and I also want the terminal, like, clearly available all on the same pane, the Obsidian forward route is perfect. If on the other hand, you're someone who's like, I'm just trying to package this for teams and clients and turn this into actual product, the web app is the way to go.
17:12But understand, these systems are only as powerful as the skill architecture it's built upon. It's just a nice layer on top of Cloud Code.
17:19Because if you don't have that, this is just some fancy nonsense. That's all it is.
17:26Right? You need some actual meat to this. So don't forget where you make your money.
17:30So I'm gonna wrap it up there. I hope I was able to make it a little bit clear as to where I think the value in these agentic OS systems are at. I see a certain contingent of people who really rail on these and say they're worthless.
17:41I don't think that's a fair assessment at all. Um, when they do, it's usually kind of purely targeted on the dashboard side of it, which makes sense if you're arguing against the dashboard or the command center in the vacuum, but that's not where the power really is.
17:56Right? The dashboard also somewhat of a facade, like what's going on is behind it. And that's where sort of the focus I think should be.
18:03And if we focus on that and the idea of skills and everything, it's like, we then arguing that you shouldn't have a system of skills that are codified that are based on what you do in your day to day life? Think you have a hard time arguing against that. Oh, one last thing.
18:17Something other people brought up, the idea of costs, which is an important one, especially if you've paying attention lately and the idea that the dash p command doing headless Claude code runs is something that apparently Anthropic doesn't like anymore.
18:31And by doesn't like, I mean they're throwing you $200 to use exclusively on that, but it's on API costs. Is there an issue with that in this whole setup? Because as you can imagine, all this is running headless cloud code under the hood.
18:45Yes and no. For $200 a month, you would have to be kind of like spamming these to get to that point.
18:52And so I think in reality, it's probably not gonna be issue. If it was an issue and you felt like you were hitting usage issues or clients were hitting usage issues, I think the simple solution is you just move this all over to something like Codec CLI.
19:06Because Codecs is great, and they don't have these issues as well. And you get more you get more bang for your buck.
19:12And switching everything under the hood here for for Codecs, very simple. I mean, you could use Cloud Code to do it.
19:18You would just point it at the code and be just like, alright. We'll switch it.
19:23So now it calls the codec CLI instead of Claude. So this is something you could essentially, like, refactor in a matter of ten minutes. And you can even put, like, a button on the dashboard, which I might do.
19:33It's like, alright. Let's go to the codecs version. So just something to be aware of.
19:37In reality, I think for ninety nine point nine nine percent of people, it has no effect. So that's where I'm gonna leave you.
19:43Again, everything you saw here, if you want the actual, like, my exact setup for the Obsidian command center and everything else, you can find that inside of Chase AI plus. And make sure to check out the webinar, uh, that's going on, you know, in, I don't know, like, twenty hours from this video being posted.
20:01So besides that, I'll see you around.
The Hook
The bait, then the rug-pull.
Most Claude Code Agentic OS videos show you the dashboard first. This one starts by telling you the dashboard is the least important piece — and then proves it by showing you the skill architecture underneath every impressive-looking command center you’ve seen.
Named ideas worth stealing.
00:46model
Three-Layer Agentic OS
- Skill and automation backbone
- Memory layer (Obsidian)
- Dashboard / command center
The three components of a Claude Code Agentic OS in order of importance. The backbone is where all real value lives; the other two layers only matter once it is solid.
Steal forFraming any AI workflow system pitch or building a client AI OS package
11:52model
Karpathy Vault Structure
- raw/ — unstructured input data
- wiki/ — processed articles with _master-index.md + _index.md at every subfolder
- output/ — deliverables
A folder hierarchy for an Obsidian knowledge vault that stays navigable at 100k+ files. The key practice is maintaining index files at every level so both humans and Claude can traverse the structure efficiently.
Steal forSetting up any long-term document or knowledge system that Claude Code will read from
09:33concept
Local vs. Cloud Automation Decision Tree
Local automations run when your computer is on and have full access to your CLIs, files, and skills. Cloud automations run on provider servers with no local access and limited quantity. Default to local unless you need always-on scheduling without your machine.
Steal forDeciding where to run any Claude Code routine or scheduled task
07:43concept
Skill Triage Session
The process of opening a Claude Code session, narrating your daily workflow domain by domain, and then asking Claude to identify and codify the repeatable patterns into named skills. Run one session per domain.
Steal forAny onboarding session when setting up Claude Code for a new person or role
How they asked for the click.
MENTIONED ON CAMERA
FROM THE DESCRIPTION
PRIMARY CTAWhere the creator wants you to go next.
OTHER LINKSAlso linked in the description.
