I created my folder system for my travel business, which sells excursions on Roatán Island. My CLAUDE.md included who I am, the brands I run, and the hard rules (never deploy without my OK, never git add a whole folder). My CONTEXT.md explained where everything lives and where to go for each kind of task. My reference files (AGENTS.md, LEADS.md, WRITING_STYLE.md) gave Claude my working style, how to handle leads, and how I write. When I asked Claude to build an automatic broken-link checker, the response was different because it found my existing memory link checker through the folder contracts. It reused that design and its past measurements instead of starting from scratch, and it respected a decision I had made two months earlier. Before, I had to explain my rules and what already exists every time. Now Claude already has that information. Key takeaway: the files are only as good as their upkeep. Claude follows the structure when the contracts are short and current, and drifts when they grow or go stale.

🙋 A little about me: I’m a Québécois running travel brands that sell excursions and tours on Roatán Island, Honduras. I’m not a developer, but I run most of my business with Claude Code: websites, SEO, lead follow-up, automations. 🎯 My current goal: Sell more excursions with less manual work, by having AI agents handle the repeating tasks reliably. 💪 What I’m currently building/working on: One ICM workspace that holds all my brands, plus the shared automation and resources. Every folder has its own CONTEXT.md contract. This week I added an automatic check that catches broken links the moment an agent creates them. 🤔 My biggest struggle or question right now: Keeping the structure clean when several agent sessions work in parallel. Each one drops files in the wrong place and nobody cleans up. How do you keep your ICM from drifting over time? Let’s get it! 🚀

📣 Update (10/22/26): Comp 15 Rules Added Current Challenge: Competition 15 The Challenge 💪 - Rebuild a past comp entry. Yours or someone else's. Then prove that its better. Rules & submissions 🗒️ -https://www.skool.com/cliefnotes/weekly-comp-15-the-rebuild Good luck everyone! --- What this thread is: I’ve seen a number of people either not know competitions are going on or know how to find them so here is a quick single source thread where you can get to them all. I’ll keep this updated as new challenges are released. See the current challenge as well as all past challenges below! Format for community challenges: https://www.skool.com/cliefnotes/how-competitions-work-from-now-on?p=84912d60 Weekly leaderboard competition: Alongside the biweekly challenges, there is a weekly leaderboard challenge where the member at the top of the 7 day rolling leaderboard wins a free upgrade to their membership. This winner is announced on Mondays typically. --- Past Challenges Competition 1 The Challenge 💪 - Build a brand voice document for a pet grooming business Rules & submissions 🗒️ - https://www.skool.com/cliefnotes/first-ever-weekly-competition-is-live?p=90f50bf9 Results🏆 - https://www.skool.com/cliefnotes/weekly-comp-1-winner-ian-barriopedro?p=0501b57e Competition 2 The Challenge 💪 - Build an artifact of a financial advisor client intake system Rules & submissions 🗒️ - https://www.skool.com/cliefnotes/weekly-comp-2-the-artifact-sprint?p=15145a68 Results🏆 - https://www.skool.com/cliefnotes/weekly-comp-2-winner-virgilio-robinson

This community is large and it moves fast. That's the good part and it's also the problem: valuable posts get buried, the same questions get re-asked instead of found, and spammers show up wherever there's an audience. These guidelines are what keeps the room worth showing up to. Read them once. You won't need them again, because most of this is what you'd do anyway. New here? Start with Jake's welcome post and the Foundation course. This post is about how we behave, not where to begin. 1. Build in public. Post the thing while it's half working. A half-finished build is more useful to everyone else than the polished writeup you'll never get around to, and you'll get corrected before you've spent a week going the wrong way. 2. Teach what you learn. The day you figure something out is the day you're best at explaining it, because you still remember exactly what confused you. A month later you've forgotten the hard part and your explanation gets worse. If you cracked something this week, that's a post. Nobody has to earn the right to ask a question here, but this place only works because people come back and answer them once they can. 3. Ask good questions. Specific beats polite. "How should I structure this?" gets three vague answers. "I have a 40 file client folder, the model keeps loading the wrong context file, here's my CLAUDE.md" gets a real one. Say what you tried, what happened, and what you expected instead. A more in depth guide: https://dontasktoask.com The flip side of this: "Anyone here?", "Help please", and one line questions with no context may get removed. Not to be harsh, but because nobody can answer them. 4. Give credit. If you built on someone's skill, template, folder structure or comment, tag them. It costs you nothing and it's the reason people keep publishing their work here instead of keeping it. A lot of the best material in this community started as somebody's reply on somebody else's post.

I just watched the Jake Van Clief breakdown, and the biggest thing that stood out to me was that folder structure can replace orchestration code. It clicked because I already run my travel brands from one structured workspace, and the video explained why the structure matters and why the agent still drifts from it. My main takeaway was that one agent reading the right files at the right moment can do what a multi-agent framework does, with fewer tokens and a system I can open and read myself. The experiment at the end helped me understand. Going forward, I’m going to run my next new process through the ICM workflow first, with a contract file and a check at every step, before I write any automation code. Why the AI doesn’t follow the ICM structure 1. The structure is advice, not enforcement. The agent only obeys a CONTEXT.md if it opens it. Nothing forces that, so under time pressure it reads the entry file and starts working. 2. The entry file gets too big. The method says the entry file should stay under about 60 lines and only route. Rules buried in a long file get skipped, and they are the first thing lost when a long session is summarized. 3. No check at the end of a step. Without a check, a misplaced file is never caught. The method’s answer is that every step ends at a check, and a fail stops the run. 4. Nobody owns cleanup. The agent drops new files next to whatever it has open instead of on the right shelf. With several sessions running at once, each one adds mess and none removes it. Your git add <directory> incident is this same problem in git. 5. Cleanup is risky, so agents avoid it. Moving a file means finding everything that points at it, including things outside the tree. Skipping the move is the safe choice for the agent. How to make it clean up Run the method’s own Restructure steps, with you approving at one point: 1. Inventory only. List the tree and what points at each file. Nothing moves yet. 2. Classify every file as catalog, contract, factory, product or dead. 3. Propose a migration map (old path, new path, role, referrers). You approve it. 4. Copy, verify, then remove. Dead files go to _archive/, never deleted. 5. Run the walk test. An agent with no memory must orient itself from the files alone. python -I _tools/links.py checks that every link and input path still resolves.