Folders, not frameworks: how Taurus makes Claude repeatable for a whole team Giving an AI agent the right context at the right moment is still the hardest part of using coding agents like Claude Code in real, daily work. We've all felt it: the agent is brilliant when it knows where it is, and frustrating when it doesn't. So how do you give it that context — reliably, for more than one person? A small team will work but what happens when you try to on-board 100+ people? The popular answers don't scale. Elaborate memory systems help a single power user, but in an enterprise they become a liability: they're hard to curate, easy to pollute, and brittle the moment you add more people and more projects. And anything built around one person's bespoke setup — their servers, their wiring, their mental model — is expensive to onboard a whole team onto. Honestly, the wheel hasn't been invented yet. Nobody has a clean, proven answer for how context should work at enterprise scale. This is where the Interpreted Context Methodology (ICM) changes the conversation. Its core idea is deceptively simple: folder structure as agent architecture. Instead of orchestration code or a sprawling memory store, the context lives in the folders themselves. A workspace is just numbered folders for each stage, with markdown files (CLAUDE.md, conventions, reference material, working artifacts) that load in layers when an agent starts there. The agent reads downward and stops when it has enough — typically 2–8k tokens instead of 30–50k. You "configure the factory, not the product": set the workspace up once, then every run reuses it with new inputs. Outputs are plain text, editable, reviewable at every step. ICM is elegant because it's filesystem-native and human-readable — a non-developer can reshape a workflow by moving files. But it has one practical dependency that's easy to overlook: When you add more and more folders agents begin to skip information. Guidelines are missed, rules are overlooked. What worked for one person doesn't work for another because the model scans economically and thinks it knows enough. The solution is again simple, the agent has to actually start in the right folder. Start in a central place and the layered context never loads; start in the right place and the agent is instantly grounded. In a team, "just cd to the correct directory" is exactly the kind of invisible, error-prone step that breaks repeatability.

I figured I would test Fable out to build a game. Three prompts later it had produced a fully working game, and it's genuinely blown my mind - this is what frontier models can do now. When Fable first got released, I had some spare usage left at the end of a weekly limit. I opened a Claude chat, started talking it through, drafted out an initial game idea, and two messages later had a v1 prompt ready to put into Fable. I had it design the whole thing - the type of game, the name, everything - because I wanted to test this properly. It came up with a pizza tycoon game: upgrades, building out stores, serving customers, the works. You've probably seen plenty like it before. That v1 prompt alone produced a fully working game with all the foundations in place. I drafted what to improve next and put in a v2 prompt - and that's when the game really came to life. Graphics, everything, all landed well. I could not wait for the next week's usage to reset so I could push it to v3. Then we all know what happened - Fable got restricted. But then Fable came back! Just yesterday I used the rest of a weekly limit to launch a v3 prompt. I went as ambitious as possible, packed in as many features as I could, and pushed it to its limits, because I effectively had free usage.(Claude reset my weekly limit on day five, without changing the overall weekly reset day. I had 0% usage with two days still to go, so I had more available than ever and simply hadn't been doing anything high-tariff with it. Not sure if anyone else's Claude has been this generous lately, but I'm not complaining.) I launched the v3 prompt on Fable 5 Ultra Code. It took 2 hours and 40 minutes to build. This morning I got Fable to put the whole thing on GitHub, add screenshots, and make it all look professional - and even that held up. So go check out the GitHub page, and play the game yourself. Hopefully all the links work now that I've said that :] https://github.com/Masked-Brown/slice-of-life