This is a new style as well that I'm testing and I'm talking about systems thinking a little bit more in it and how I think that you can do more as a company now, especially if you're a consultancy. If you're thinking of starting your own or already have one, this video might be huge value for you! It's on my YouTube so if you can go like it there and leave a comment that would be amazing I'll probably create a text companion and make a few more videos and add this to a new series called systems thinking In the classroom! We shall see.

You just saw how the folder structure adapts to different use cases. Vote below, then drop your customized setup in the comments. What did you name your workspaces and why?

If you're in social media, you're probably already building this, so why don't we do it TOGETHER in this community? 🤩✨ The OUTCOME looks like this (for me, please challenge it): During the day inspiration will arrive, so you save your half-cooked voice notes in your phone. You submit them to your Script Agent to refine the idea. No inspiration to post today? No problem, you have a Scraping Team that tells you what's trending, what adds more value to your channels and what to remix from other sources. The ARCHITECTURE should handle the full automated process for your business including: script, video with call-to-action, lead capture, lead nurturing, sale and post sale. The STAGE I'm currently at: Yesterday I automated that when a viewer leaves a comment (preferably with a specific keyword) the system captures such lead in the CRM database, replies to same comment saying "Hey [user]! To unlock your gift* please confirm your info here: [link]". Once the form is submitted the system merges the database to complete the user profile. *When I say gift I refer to your Lead Magnet value (PDF, eBook, Template, etc). I know you're at least curios about this topic, so please leave your comment and share if you have a better system🤘

Same $5 per million input tokens. Same $25 per million output. The pricing page says nothing moved from 4.6. But if you're on Max, your weekly Opus quota drains faster than it did a month ago. Same prompts, same code, same workload. The number on the invoice didn't change. The number of tokens per request did. Buried in Anthropic's own pricing doc, as a footnote under the model pricing table: "Opus 4.7 uses a new tokenizer compared to previous models, contributing to its improved performance on a wide range of tasks. This new tokenizer may use up to 35% more tokens for the same fixed text." Read that again. Same fixed text. Up to 35% more tokens. That's not a price change you'd see on the sticker. It's a price change on every single request you send. And honestly, that's only the first silent bump. When Claude Code v2.1.117 shipped, the default effort level on Opus 4.7 moved to xhigh. Opus 4.6 and Sonnet 4.6 still default to high. If you never ran /effort to check, every call you've sent since the update has been reasoning harder, and burning more thinking tokens, than the same call a month ago. Haiku doesn't support effort levels at all, which honestly isn't a limitation. It's flat-rate reasoning you can actually budget against. Two bumps stacked on the same workload. The Opus weekly cap on Max feels smaller because it effectively is. The obvious move is to use Opus less. That's the wrong frame. The right frame is that most of what you're running on Opus shouldn't be on Opus in the first place. Open /agents in any recent Claude Code session and look at what Anthropic's own built-in subagents run on. Explore runs on Haiku. Claude Code Guide runs on Haiku. statusline-setup runs on Sonnet. Only Plan and general-purpose inherit whatever your main conversation is using. Anthropic shipped the cost routing pattern directly into the product. Every custom subagent in your .claude/agents/ or ~/.claude/agents/ that doesn't set a "model:" field just inherits Opus and pays Opus rates for whatever it does.

I got my folders set up for the therapy business, and I created a skill at the right level in one of the folders to score a 106-question psych screener. We do them often, and they're a pain to hand-score. Using the folder structure, I can now see how I can package this along with other things as a part of our intake/screening process.