For those of you who are in academia and would like to cite any of my research. I just pushed my ICM paper and had it submitted to preprint. You'll notice that the working title is called ICM but I refer to the workspaces MWP, I am pushing an update right now removing all mention of MWP but Model workspace protocol was the original name I had called it. However I think Interpretable Context Methodology makes more sense for what is actually happening. Enjoy! https://arxiv.org/abs/2603.16021

So I'm just curious how everyone is handling security and review around some of these tools that are becoming available unbelievably quickly. I'm sure everyone here knows about all the drama around Open Claw and the fake project and all the mayhem that Created. @David Vogel just posted a pretty great tool in a Comment called "Claude Code Users, You're Wasting Tokens." When I reviewed it, it definitely looks amazing. It's a huge project and it's been around for a little while. Some of these viral tools concern me because of the possibility of just one errant line of code that would allow for the unseen prompt injection. When you happen to trigger it, who knows what it gives access to. I myself spend a lot of time as a consultant in the corporate implementation and also teach as an adjunct professor at a small college here locally. I just completed some SecAI+ "Teach the Teacher" training so this is also top of mind right now. They don't really have any specifics either other than you must do your due diligence so I'm just curious. At this time I'm pretty careful to avoid brand new tools and tools that have instant virality because it just seems like there hasn't been enough time yet for that to be validated. I haven't found a tool that I believe in yet to do it and I don't have the time, or in a lot of cases the knowledge, to do it myself. That's it. I love everybody's input. I feel like this is a critical topic in this space and it can be often overlooked.

Just stumbled on the resource 87K stars on Github. The performance optimization system for AI agent harnesses. From an Anthropic hackathon winner. "Not just configs. A complete system: skills, instincts, memory optimization, continuous learning, security scanning, and research-first development. Production-ready agents, hooks, commands, rules, and MCP configurations evolved over 10+ months of intensive daily use building real products. Works across Claude Code, Codex, Cowork, and other AI agent harnesses." -from the repo https://github.com/affaan-m/everything-claude-code Cheers

You just finished the setup lesson. Vote below so we know where everyone is starting from. If you picked "Something else," drop a comment and tell us what.

This is a long update but PLEASE read through it, this will get you updated on everything Jake and I have been building. We realized we needed structure, easy access and more content. Every lesson links to the lessons around it. Every module builds on the one before it. You can start anywhere that makes sense for you, but everything connects back to everything else. It's the same architecture we teach you to build for your own workflows. Where to Start The Foundation is the starting point. The concepts. The folder architecture. The prompting framework. If you haven't done this, do this first. Everything else assumes you have. Implementation Playbooks (Level 2) is where you use what you learned. Each module is a complete build guide for a specific domain. Building Animations. The Ultimate Browser. Pick the one that matches your work. Finish with something real. Building Your Stack (Level 3) is where you build the tools. Custom UIs. Remote access. Infrastructure that wraps around your workflows. You're not adapting to someone else's setup anymore. You're assembling your own. They're abstraction layers. Each one builds on the last. How Lessons Work Now Every lesson follows the same structure. What you'll get, the content, resources, cross-links, and at the bottom: a discussion post with a poll. The polls are there for a reason. We want to know where you are. We want you talking to each other. When you finish a lesson, scroll down, vote, and drop a comment. If you're stuck, say so. If something clicked, share what it was. The community gets better when you use it. New Categories We reorganized the community posts. Here's where things live now: Announcements - Updates from us. New content drops. Changes to the course. General Discussion - Conversation that doesn't fit elsewhere. Questions, ideas, whatever's on your mind. Show Your Work - Post what you built. Animations, automations, folder setups, custom tools. This is where the community challenges live. Share your stuff.