Make Claude 10x Smarter For Free (Karpathy's Hack + 4 More)
Five free GitHub repos, one install each, aimed at five specific failure modes in Claude Code: forgotten context, buried answers, AI-sounding prose, token bloat, and unchecked assumptions.
Posted
3 days ago
Duration
Format
Listicle
educational
Views
8.3K
112 likes
57 · 43
Big Idea
The argument in one line.
Five free GitHub tools patch Claude Code's most common failure modes: forgetting context between sessions, burying the answer under hedging, sounding like AI, burning tokens on verbose output, and making unchecked assumptions.
Who This Is For
Read if. Skip if.
READ IF YOU ARE…
You use Claude Code or a similar coding agent daily and keep re-explaining the same project context in every new session.
You've noticed your agent burying the actual answer under paragraphs of hedging before it says anything useful.
You write with AI regularly and want the output to stop reading like it was written by AI.
You're watching token spend climb and want a low-effort way to cut it without changing how you work.
SKIP IF…
You've never used Claude Code, Codex, or a similar coding agent. None of these five tools have anything to do outside that context.
You already run a hand-maintained memory file and a strict CLAUDE.md that covers the same ground as these repos.
TL;DR
The full version, fast.
Claude Code and similar coding agents share the same bad habits: they forget context between sessions, bury the useful answer under hedging, write in AI-sounding prose, burn tokens on verbose output, and quietly overbuild or guess instead of asking. The video covers five free GitHub tools, one per habit: a memory plugin that compresses and recalls past sessions, a skill that forces next-action-first responses, a writing skill that strips AI tells, a proxy-plus-skill combo that cut token counts by roughly a third in the demo, and a single CLAUDE.md file built from a former OpenAI and Anthropic researcher's own coding rules. None require writing code, just a markdown file or a one-line install command.
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.
Cold open naming all five fixes (memory, concise output, humanized writing, token savings, Karpathy's rules file) and the free setup guide.
01:16 – 04:16
02 · Repo 1: Claude Mem
Live demo of a memory plugin that captures, compresses, and recalls facts across sessions and even across projects.
04:16 – 06:41
03 · Repo 2: I Have ADHD
A skill that reorders responses to lead with the next action and strip hedging, demoed on a CRM decision and a broken-site fix.
06:41 – 10:07
04 · Repo 3: Humanizer
A writing skill that detects and removes AI-sounding patterns, demoed rewriting three tweets and shown to support voice-matching.
10:07 – 13:38
05 · Repo 4: Caveman
A skill-plus-proxy combo that shrinks both what the agent writes and what it reads, measured at roughly 31 percent fewer tokens on the same prompt.
13:38 – 14:30
06 · Which one should you use?
Compares I Have ADHD (structure) against Caveman (raw volume) and recommends stacking both.
14:30 – 15:46
07 · Repo 5: Karpathy's CLAUDE.md
A single rules file built from a former OpenAI and Anthropic researcher's own notes on common coding-agent mistakes, distilled into four principles.
15:46 – 17:06
08 · Setting it up
Shows dropping the CLAUDE.md file into a project folder or pasting it into custom instructions, and plugs the bundled setup guide.
17:06 – 17:51
09 · Outro
Wraps with a comparison to Codex and a subscribe ask.
Atomic Insights
Lines worth screenshotting.
Claude Code's context resets between sessions by default, so a memory plugin that compresses and re-injects past session summaries removes the need to re-explain the same background every time.
A skill that forces an agent to lead every answer with the next concrete action cuts response length without cutting the technical content.
AI writing tells like 'not X, it's Y' contrast phrasing, forced rule-of-three lists, and rhetorical-question openers are consistent enough across models that a pattern-matching skill can strip them automatically.
AI coding agents bill per token for both what they read and what they write, so a terser house style lowers cost on every exchange, not just the expensive ones.
A side-by-side token count on the same prompt showed roughly 31 percent fewer tokens with a compression skill active, with savings climbing higher on large file reads.
Two different agent-shrinking skills solve different problems: one targets response structure, the other targets raw word count, and they compound when used together.
A single CLAUDE.md file that states four rules, think before coding, keep it simple, make surgical edits, and work toward a verifiable goal, measurably changes agent behavior without installing anything.
Coding agents left unchecked tend to overcomplicate solutions, build thousand-line abstractions where a hundred lines would do, and quietly delete comments or code they don't fully understand.
A voice-matching writing skill can be retrained over time just by feeding it more of a person's own past writing, so it converges on their natural phrasing without hand-picked examples.
Of the five fixes covered, the memory plugin is the only one meant to run in the background at all times; the rest are meant to be toggled on for specific tasks.
Takeaway
Five small files fix five specific coding-agent habits.
WHAT TO LEARN
Claude Code's worst habits, forgetting context, burying answers, sounding like AI, burning tokens, and guessing instead of asking, each map to one narrow, free fix rather than needing a better prompt.
02Repo 1: Claude Mem
A coding agent's context resets between sessions by default, so anything worth remembering has to be captured, compressed, and re-injected by something outside the model itself.
The plugin stores compressed summaries rather than full transcripts, on purpose, to avoid bloating every future session with everything that was ever said.
03Repo 2: I Have ADHD
Response length and response usefulness are separate problems; a skill that only reorders structure (next action first) can shrink an answer without removing any of its content.
This kind of skill is meant to be toggled on for execution-focused tasks and off for open-ended brainstorming or creative writing.
04Repo 3: Humanizer
AI-sounding writing follows recognizable patterns, forced contrasts, rule-of-three padding, hedged rhetorical questions, consistent enough that a rule-based skill can catch and rewrite them.
A writing skill's voice-matching improves with more of a person's own past writing fed into it over time, rather than needing a curated style guide up front.
05Repo 4: Caveman
Every token an agent reads or writes is billed, so trimming verbosity is a direct cost lever, not just a readability one; a measured test showed about 31 percent fewer tokens for the same answer.
The savings come from two separate mechanisms, a skill that shrinks what the agent says and a proxy that shrinks what the agent reads, that can be run independently or together.
06Which one should you use?
Structure-focused and volume-focused compression skills solve different problems and stack, rather than compete, when used on the same task.
07Repo 5: Karpathy's CLAUDE.md
A short, explicit rules file naming four behaviors to avoid, silent assumptions, overbuilt abstractions, out-of-scope edits, and unverified fixes, changes agent output without any code or install.
Unchecked coding agents default toward overcomplication: bloated abstractions, thousand-line rewrites where a hundred lines would do, and silent edits to code or comments they don't fully understand.
Glossary
Terms worth knowing.
Skill (Claude Code)
A packaged markdown file with instructions that Claude Code loads on demand via a slash command, changing how it structures or writes its responses for that session.
Plugin (Claude Code)
A distributable bundle of skills, hooks, or MCP servers that installs into Claude Code and can keep running in the background across every session automatically.
MCP server
A separate process that exposes tools, resources, or prompts to an AI agent over a standard protocol, giving it capabilities beyond its own built-in tools.
Token billing
AI coding agents charge by the token for both what they read (context, files, logs) and what they write, so longer inputs and outputs directly raise the cost of a session.
CLAUDE.md
A plain-text instructions file that Claude Code automatically reads at the start of a session to apply project- or user-level rules to its behavior.
“Most agents write like a cover letter and read like a fire hose.”
vivid, standalone metaphor about verbose AI output→ newsletter pull-quote↗ Tweet quote
15:02
“Don't assume, don't overbuild, don't touch what you didn't ask it to touch, and tell me if you disagree.”
the whole CLAUDE.md thesis compressed into one line→ newsletter pull-quote↗ Tweet quote
The Script
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.
17px
metaphor
In today's video, I'm going to reveal five GitHub repos that fix Claude's worst habits. I don't know about you, but it seems like a week or two after a new model comes out, it just starts getting really dumb. It happened with Claude Fable.
It happened again with GPT Astro. So in today's video, I'm going to give you five hacks that can actually make Claude smart again. One of them is going to help with context.
So if you're sprawled across multiple chats, it's going to help and tie all of your memory and context together. One of them is a skill that's especially helpful if you have ADHD to stop your coding agent from burying an answer to actually give you the response that you need to see quicker.
One of them is an absolute hack. It's going to help you get better writing outputs and actually humanize your text. The fourth one is going to save you a bunch of money by slashing token expenditure by up to 65%.
And the last one is a system that Andre Kapathi uses. He was in the founding team of OpenAI and then he later joined Anthropic. I'm going to show you one single file that will turn your cloud code from an idiot into an absolute monster.
And the best part is all of the five repos that I'm going to show you today are available for free on GitHub. What I'm going to do is I'm going to compile them all into an MD file with the setup instructions.
So all you need to do is drag and drop the file into your Claude code and it will set all of them up for you. That's going to be available for free down below in my free school community under the resources library, just like every other video here on the channel. Now, the first one I want to show you is called Claude Mem.
This gives your cloud persistent context across sessions for every single agent so it doesn't forget stuff. How much time have you spent re -giving agents context? Even if you have an MD file, sometimes it seems like they don't read the file.
And every time you open a new chat or a new session, you're like re -explaining context or it's getting things wrong. This solution is awesome because it captures everything your agent does during a session. So if you're working on some research for a project, it's going to remember how you did that research.
It's going to compress it with AI and it's going to inject relevant context that it saves. one session into the next session. So this actually doesn't just work with Claw.
This also works with OpenClaw, Codex, Gemini, Hermes, et cetera, but it's a game changer. And there's a reason why it has 94 ,000 stars and over 162 contributors on GitHub. Okay.
So it's all set up. Let me show you how it works. So I'm going to put in some random facts about me.
Obviously these aren't real facts, but we're trying to test it out. So my favorite color is burnt orange. My first car was a 2004 silver Toyota Corolla and a bunch of other responses as well.
Now, usually if you just open a new chat or a new... terminal session in cloud code it wouldn't remember this stuff because this isn't in the same project but watch with the cloud mem installed how it remembers so i'm going to open a new terminal session i'm going to switch the folder to a folder with no data, and I'm going to ask it what my favorite color is, what my dog's name is, what my first car is, and who laughed when I got stung by a jellyfish.
You can see it's searching Claude Mem in the tools, so it's using the plugin, and you can see it just found all the data. My favorite color is burnt orange. My dog's name is Biscuit.
My first car was a Toyota Corolla. My friend Tom laughed when I got stung by a jellyfish. If this weren't installed, it wouldn't have remembered this because it's a new session in a new folder, and if you're using the terminal or VS Code, unless you have all of your memory updated into a memory .md folder, It's not going to remember everything.
So you might be wondering, does it remember everything? Well, it doesn't. And that's by design because otherwise it would bloat Claude too much.
Instead of storing transcripts, the worker inside the plugin compresses the key information into short summaries with the model and it stores those summaries. So instead of the whole raw session, it just remembers the key details, similar to how the Claude chat will remember key details. So if you message a bunch of Claude chats, you'll know it pieces things together, but the same isn't true for coding sessions.
And if you're like me, and if you're utilizing tools all the time and custom... and plugins and repos, then you want that same effect across all of your coding sessions as well. Just keep in mind that it can slow Clawed down a little bit, but I think it's worth the trade -off in most cases.
And it's not always calling on Clawed mem all the time. It's mainly doing so when it needs contextual information and then it will, you know, quickly look through the summaries. Just the same as if you had a folder with a memory .md file, it would look through that summary.
I would say this is best used for someone that works in Clawed code a lot or Codex a lot and you work for multiple days across the same project. then it's going to fix the problem of needing to re -explain context constantly. And that's been a massive problem for me in the past.
So this has been a game changer. And honestly, since installing this, I don't even think about it. It just does it automatically.
And it's one of those things where you might not even realize how bad Chord actually is at keeping memory until you install a plugin like this. All right, now moving on to repo number two. This is great.
It's called I have ADHD and I literally do have ADHD. So this is something that is really helpful for me. It's essentially a skill to stop your coding agent, in this case, Claude, from burying the answer that you want.
So it's like the ADHD friendly version of using AI. We'll test it out ourselves in a second, but you can see the response from Claude before versus after using this repo. So before it uses all this language, especially the new models.
Great question. Let me think about this. Your author has a few moving pieces.
This, this, this. One approach would be this, this, and this. Whereas if you're developing.
a product or if you are trying to get a solution to a problem usually you only want to know what your next step is so instead of this big bloated response it just says run this then edit this open replace run next paste this if the test fails it just makes working so much easier especially if you're coding if you're developing if you're building landing pages all that stuff it really shrinks down the response time and essentially the way it does this is through a skill .md file which you can obviously see inside the folders here which has 10 rules one lead with the next action so it tells you the next action up front instead of going with all this wordy stuff to number multi -step tasks three and with one concrete next step make wins visible no preamble all of the stuff that in the past you had to like manually inject that into your instructions file if you just download this plugin it'll just happen throughout your entire session automatically on the sessions where you want to use it so typically where i would use this is on a coding task anything where i'm not brainstorming or being creative basically whenever i'm doing something with an agent i'll use this instead of just using the raw claude session so we'll start a new session if you want to use
it use forward slash i have adhd remember it's just a skill so just like you trigger any other skill you just want to use the slash command you don't use it all the time obviously if i'm doing creative writing i don't want things compressed but if i'm developing i generally do so now it's invoking the skill you can see that adhd mode is on and i'll use a simple prompt let's say i'm just trying to get some work done and i'm deciding where to put my crm should i do it in notion or google sheets i'm gonna ask it which one it recommends and you can see that it formats in a very specific way google sheets three reasons one two three setup time next Or let's pretend we're developing something like a website.
I said, I'm working on an AI Edge website. Three things are broken. I state the issue.
What do I do first? Walk me through fixing it. So you can see, once again, it gives the output up front.
It gives a list of steps. And then at the end, it tells us what we need to do next. This is much better, more concise than the wordy, shmurdy Claude without the I have ADHD skill.
So once again, won't use it all the time. But when I do, it's when I want to just get stuff done. It's really good.
Now, the third repo, I think, is essential for people because I am sick in. business of getting these AI sounding proposals. I'm sick of seeing AI tweets.
I'm sick of AI language. You think your writing doesn't sound like AI. Well, it does.
If you use AI enough, you can tell what's called, you could tell what's GPT. There is a repo called humanizer, and I'll show you the difference between an output before or after, because it's honestly a game changer for writing human sounding AI language, which is very important, especially if you're into writing, especially if you're creating content, you want stuff to sound like a human wrote it.
You don't want to sound like it's AI. So let's ask Claude to write me a tweet. about why most people are using AI wrong.
Punchy for a founder audience under 280 characters. Most people treat AI like Google with better manners. Founders who get it, treat it like a team.
Context docs, standing instructions, feedback loops, ownership of the whole workflows. Not one of tasks. You don't prompt the team, you manage one.
This contrast phrasing is so obviously AI. Speed is the wrong metric. Leverages.
Like all of these contrast phrasings I hate. Stop asking, how do I do it? Start asking this.
So let's ask it now. Use hashtag humanizer to write these three tweets again. And you'll see the difference between the AI writing and the humanizer writing.
By the way, you can also train it so you can improve upon the basics. skill by rewriting it to sound like your voice so if you go forward slash humanizer here's an example of my writing and then give it a bunch of stuff you've written now humanize it like this you can update the skill so then it will sound more like you in future so i've developed a writing skill that sounds like me to speed up time when it comes to writing stuff and what i'll do is i'll just like voice dump using whisper flow if i want to like write a post or something and then it will just like reword it it already knows my language it already has my natural intonation so the more you actually speak the more you write the more it sounds like you over time and you don't even need to find custom examples of your writing, you can literally just ask Claude to go back into the chats and pick up on how you speak, the vocabulary you use, and then make that voice match on a skill update.
So these are the rewrites. As you can see, it got rid of all of the not X but Y closes that AI just seems to love to use. It got rid of the rows of fragments, context docs, standing structures, feedback loops.
These are classic AI tells. It got rid of the force triads, all of the classic things that AI loves to do in its writing. So for example, if AI is only saving you time, you're underusing it.
The founders pulling ahead, use it for work they could have never hired for or funded. The question changes from how do I do this faster to what can I try now that I couldn't before?
Like it's not perfect, but it definitely sounds a lot better. And it's going to basically do that initial scan to make sure there are no of those classic idiosyncrasies that AI typically uses in its writing. I actually really like the final phrase of this one.
Most founders use AI like a fast intern. Ask, get an answer, move on. The ones getting the most from it, treat it like a co -founder.
They hand it the whole problem, constraints included. and let it argue back. It's slower per question and worth far more per decision.
It just sounds more natural, especially the closing sentences. So definitely worth using if you're writing. You can inject your own style into it, as I said, and then you can make it like a custom writing skill, essentially, and you just adapt it over time.
But it's a good base to start from. And if you're interested, you can go into the GitHub and you can see exactly what it's changed. But there are 25 patterns that it corrects by using the skill.
So this is the beauty of downloading these skills off the internet. People have already put in the work. Like in this example, there's already...
contributors that have put in the work to build this and you can just hop onto it and just make it slightly better. All right, now for the final two, I feel like I've saved the most powerful ones until last. The first one can cut 65 % of your token usage, which will literally save you money.
And then the last one is based on the real system that Andre Kapathi uses, founding member of OpenAI and now at Anthropic. So this skill that can save you money is called Caveman. Why use many token when few token do trick?
Viral skill plus proxy for coding agents that cut 60 % of tokens by talking like a caveman. Your coding agent bills by the word and writes like it knows that. Caveman makes it stop.
So if you guys don't know, token expenditure is actually just based on words. So if a normal agent gives an output like this, it'll give an output of 69 tokens. If a caveman agent is giving an output like that in 19 tokens, then it not only saves you time having to read it, just like the I have ADHD skill, it actually saves you money because AI billing actually bills based on tokens or words.
So your agent pays for every token it writes read. So the more text you send an agent, the more you're being charged, the larger the outputs, the more you're being charged, even if it's slop.
Most agents write like a cover letter and read like a fire hose. K -Man attacks both ends in the agent you run and in the one you build. One rule, the skill shrinks what the agent says, the proxy shrinks what the agent reads.
The middleware does the same inside your own code. Started as a joke, hit 4 ,000 stars in a week, now past 100 ,000 stars and 107 .2k now. So it's clearly gained a lot of popularity and it's simply because it's a really effective way to save money while saving time at the same time.
So if I go forward slash caveman, I can activate the skill inside Cloud Code. Technically, it's a plugin that you download, so it could be persistent across your sessions. So it says caveman mode full, send task.
So we'll show it on native text. I'll ask it, what's the difference between a skill, an MCP server, and a plugin in Cloud Code? When would I use each one?
And you can see it's simplified everything. Use skill when repeatable workflow, house style, review checklist, project convention, cloddery has the tools, cheap, no runtime, no schema costs used. MCP.
And then a rule of thumb, knowledge equals skill, capability equals MCP, distribution equals plugin. So now I've turned off caveman mode and I'll ask it the exact same question. And you can see that it's already much more verbose.
So if we actually run the calculations on tokens, you can see caveman used 409 tokens, normal used almost 600 tokens. Caveman was almost half the words and almost half the characters as well.
So it's saved about 31%. In some cases, like if you were sending it, you know, a massive file to read through because it also changes the way that it reads inputs and obviously outputs as well, you could save up to 60%. So over time, this is saving you money.
In this case, 31 % of tokens. And obviously that'll vary depending on different use cases. Remember, Caveman only shrinks what the agent says, not what the agent does.
So it's still going to operate the exact same. It's not going to dumb down coding, development, scraping, etc. But it's going to make the conversing side of things a lot cheaper.
and quicker. So you might be wondering, what's the difference between I Have ADHD and Caveman? Well, they're both similar in the sense that they can cut down the length of a response, but I Have ADHD primarily focuses on the structure.
So how's it presenting information in what order with what steps? Whereas Caveman purely attacks the volume issue. So you could use both at once.
Both do overlap in the sense that they'll both kill fluff, but they attack different problems. If I had to pick one, I'd probably pick ADHD, but if I was trying to save cost, I'd use Caveman. The best combo that a lot of people have found is using caveman on light mode.
It'll make basic cuts and then use I have ADHD to tackle the structure of your outputs. So at this point in the video, you now have persistent memory from Claude across all of your sessions. You are now structuring outputs in the correct way that make it easy for you to visualize the next steps.
You now have text that actually sounds human and isn't sounding like it's being generated by an AI. And you are now saving a bunch of money through caveman mode. But the final one is much bigger.
This addresses a lot of the pitfalls that Andre Kapathi had noticed he was pushing LLMs to the max when coding. And this is very cool because it's just a single clod .md file and it improves clod code behavior across the board.
So the problem, and this is directly from Andre, is that the models make wrong assumptions on your behalf and just run along with them without checking. They don't manage their confusion. They don't seek clarifications.
They don't surface inconsistencies. They're basically yes men. They don't present trade -offs.
They just, they don't push back when they actually should. This is a major problem with AIs at the moment. They really like to overcomplicate code and APIs, bloat abstractions.
They don't clean up. dead code they implement a bloated construction over a thousand lines when 100 would do and obviously if you're not an actual software engineer you probably don't even pick up on this stuff but obviously andre is they still sometimes even change or remove comments and code they don't sufficiently understand as side effects even if orthogonal to the task so the solution is four principles in a single file that directly addresses these issues principle one think before coding wrong assumptions hidden confusion missing trade -offs principle two simplicity first over complication bloated abstractions principle three Surgical Changes, Orthogonal Edits, Touching Code You Shouldn't, Principle 4, Goal Driven Execution, Leverage Through Tests First, Verifiable Success Criteria.
Now, all of the others you're going to use at certain times. Obviously, the Chord Mem you're probably using all the time for memory, but I have ADHD, you'll toggle on and off. KBAM mode, you'll toggle on and off.
Humanizer, you'll only use it when you're writing text. But this one, this is something that you can use all the time whenever you're coding because these principles remain the same. And this is also the most highly rated GitHub of this entire video, 214.
So to summarize, it's essentially an MD file, so a note that you leave with Claude that says four things. Don't assume, don't overbuild, don't touch what you didn't ask it to touch, and tell me if you disagree. Very basic things that, no matter what you're doing, you will want out of an LLM.
And this fixes some of the biggest issues I have with Claude, which is the fact it's a yes man, the fact it overbuilds, the fact it makes assumptions, and the fact it does stuff I don't ask for. And there's no code, there's no install, it's just a file that you drop into your context file, you can put it into Claude under a custom project modification.
that you could use even in the normal chats, or you can just have it in your folders and use it as an MD file whenever you're working within a specific folder on Cloud Code. And the reason why it's got so many stars on GitHub is because Cloud is annoying for a lot of people, clearly even myself, and this fixes a lot of those issues.
So the installation on this one is quite simple. Remember in my school community, I'll have all of the repos in a single MD file. So you can just drag and drop into Cloud.
Some are more complicated to install than others. They'll just all install at once. Free community, come and join.
It's an amazing hub to learn about AI. build a business with AI. We're all super AI crazy there.
So you can download it from GitHub. And then all you really need to do is drop the Claude .md file into the folder that you're working in. So whenever you're working in a folder, it'll have access to this file.
You can see the file just states the rules that Claude should follow that we went through. And now whenever I talk to Claude, it will follow these instructions. So even if you're just in the Claude chat or you're in cowork and you just want to use projects, you can actually copy and paste this into instructions.
So here's the MD file. Let's just copy. it all let's put it into instructions and it's going to save it in instructions this is like a lazy way to do it obviously if you're using a folder you just put it in the folder that you're using you could also just add it to the context folder but it's going to be less effective than adding it into instructions so it's really that simple but Clearly, this is something that works better if you have it in a folder and if you're just using that folder to work in, which is what I recommend anyway, because that's the only way to have real control over your own memory.
Even ClaudeMem that I showed you today is going to guess what it should remember and doesn't give you full sovereignty, which is good for convenience. You want to have it running, but then you probably want to go over and above and save the stuff that you want to save just so you own your own memory. So those are the five GitHub repos, the five hacks that make Claude not only more usable in 2026, but genuinely turn it in.
into, I think, the best LLM. I mean, I really like Codex as well, but the way I have my Cloud set up with all my skills and all my repos, it works really well for me. It's really good at writing for me and I still get better outputs than Codex unless I'm doing like deep agentic coding work that I do find Codex is better.
But there's a new Cloud model launching very soon as well. So, you know, there's always going to be this race between what's better. One week Codex might technically be better and then in a couple of weeks, Cloud might be better.
But if you are using Cloud, using these five repos, I think is going to help you out a ton and actually make Cloud smart again. I'll see you. you in the next video subscribe if you enjoyed this video in the school community i'll leave the one prompt setup guide for all of these repos so you're good to go see you in the next one peace out
The Hook
The bait, then the rug-pull.
A week or two after every new model release, Claude starts "getting dumb," the video argues, and the fix isn't a better prompt. It's five specific, free repos: one for memory, one for verbosity, one for AI-sounding prose, one for token cost, and one built from a former OpenAI and Anthropic researcher's own rules for keeping a coding agent honest.
Frameworks
Named ideas worth stealing.
14:03list
The Four Principles (Karpathy-inspired CLAUDE.md)
Think Before Coding
Simplicity First
Surgical Changes
Goal-Driven Execution
Four rules in a single CLAUDE.md file meant to stop a coding agent from making silent assumptions, overbuilding, touching code outside the task, and shipping unverified fixes.
Steal forany CLAUDE.md or system-instructions file for a coding agent
05:15list
The 10 Rules (I Have ADHD skill)
Lead with the next action
Number multi-step tasks
End with one concrete next step
Suppress tangents
Restate state every turn
Specific time estimates in minutes, not "a bit"
Make wins visible
Matter-of-fact errors
Cap lists to 5 items
No preamble, no recap, no closers
Ten formatting rules baked into a skill file that reorders every response to put the next action first and cuts hedging language.
Steal forany coding-assistant system prompt or custom-instructions file
CTA Breakdown
How they asked for the click.
VERBAL ASK
17:06subscribe
“you in the next video, subscribe if you enjoyed this video, in the school community I'll leave the one prompt setup guide for all of these repos so you're good to go”
Repeats the free-community setup-guide offer three times across the video (intro, mid, and outro) rather than a single hard pitch, then closes with a plain subscribe ask.
Add Modern Creator as a preferred source and Google shows you more of our breakdowns in Search, Top Stories, and AI Overviews. It only changes what you see, and you can undo it in your Google settings anytime.
Add to Preferred SourcesOpens your Google source preferences with us pre-loaded. Tick the box and you're done.
A tutorial arguing prompt engineering is dying now that models are smart enough to self-correct — and a walkthrough of Claude Code's /goal, /loop, and /schedule commands with a live website-audit and YouTube-monitoring demo.
AI Edge's host installs seven free, high-star GitHub repos live on screen, turning stock Claude Code into a social-research engine, a browser operator, an ads department, and a 279-agent company.
A 13-minute breakdown of the Chinese open-source model that nearly matches Opus 4.8 intelligence at one-fifth the price, and the four-step setup to wire it into Claude Code.
An 18-minute build diary of a custom personal OS: Telegram voice notes, live net worth, habit tracker, CRM, and the Supabase memory layer that ties it all together.
Elon's new agent platform runs a team of AI employees on their own always-on computers — tested here as a CFO, an EA, a Dubai real estate scout, and a YouTube research analyst.
00:00
00:33
00:43
00:56
01:12
01:40
01:53
02:07
02:20
02:33
02:47
02:59
03:14
03:27
03:40
03:54
04:07
04:34
04:47
05:01
05:14
05:27
05:41
05:54
06:08
06:21
06:34
07:01
07:15
07:28
07:41
07:55
08:08
08:22
08:35
08:48
09:02
09:15
09:28
09:42
09:55
10:04
10:22
10:49
11:02
11:16
11:29
11:42
11:56
12:09
12:22
12:36
13:09
13:16
13:29
13:56
14:10
14:23
14:36
14:50
15:03
15:17
15:30
15:46
15:52
16:23
16:37
16:50
17:04
17:17
17:30
21:37
24:49
13:11
20:35
18:08
22:56