I just dropped a new Claude Code skill in The Armory that I used to make this exact video. You give it a finished voiceover, and it helps build the full vertical explainer around it: - Storyboarded scenes - Word-timed captions - Custom sound effects - Audio mixing - Chunked Remotion rendering - Final verification sheets This is not a prompt that spits out a random slideshow. It is the actual workflow, scripts, design system, and working source files behind the finished video. Download it from The Armory, install it in your Claude Code skills folder, and use the included project as a working example.

If you have tried the new skill out let me know how it’s been working out for you in the comments!

I just dropped the first resource in the new Skills and Prompts section of the classroom. That section is where I’m putting the files and prompts I actually use, ready to copy. The first one is a prompt that builds a skill. You paste it into Claude, it interviews you with ten questions, and it hands back a SKILL.md file. A rulebook any AI has to follow when it writes for you. Your banned phrases, your rhythm, your real stories, and a hard rule against inventing anything you didn’t give it. My own posts run through the file this exact prompt built. It’s in the classroom for paying members. More is coming to that section. It’s in the classroom section. This space is exclusive to the paying members.

Course 0 — the terminal basics. Full video walkthrough included, plus a mini-capstone and checkpoint at the end so you can prove to yourself you actually get it. Just Keep Building.

Somebody spent $321 on a 5-hour Claude session and posted the receipt calling it a scam. It's going around right now. Look at the wrong number and you'll agree with him. Look at the right one and you'll never make his mistake. He selected Fable. Some of the work got done by Opus. He called that a silent bait-and-switch. It wasn't. Fable hands certain queries to Opus on purpose. It's a safeguard and it's written in the docs. He wasn't scammed, he was safeguarded. Now here's the number he skipped right past: 252 million cache reads on Opus. In one session. What a cache read is Every time you send another message, the model has to re-read your whole conversation to answer. Your files, your history, everything you've stacked up so far. That re-read is a cache read and you pay for it every turn. Short session, small context, it's cheap. Sit in one session for five hours and never clear anything out, and you're paying to re-read a phone book on every single reply. 252 million reads means he never got out of the chat and never cleaned up his context. That's not the model reaching into his wallet. That's him re-reading his own mess a few thousand times and footing the bill for it. The real mistake A lot of people think the model is the machine. It's not the machine. It writes the machine. You have the model write the script one time. Then you run the script. The script is code. It costs nothing to run and it does the same job every time you fire it. The second you keep the model in the loop doing the actual work over and over, you're paying top dollar to reinvent something you already have sitting in a file. The answer's done. You're just too deep in the chat to go run it. You probably didn't need the API at all This whole $321 bill came off the API. Most of what people are running on the API doesn't need to be on the API. The agentic operator knows you can do almost all of this on your subscription. Twenty bucks a month, flat. Build your workflow, write your scripts, run your terminal sessions, all under the plan you already pay for.