The template integrates three frameworks: Van Clief's routing (the structural backbone), Karpathy's behavioral rules (think before acting, minimum viable scope, surgical changes, goal-driven execution), and IBE intent preservation (the "why" behind every decision). Each tier has a clear job — CLAUDE.md routes, workspace context files carry domain knowledge, skills wire selectively per task. The core addition on top of Jake's routing: a session state pattern (STATE.md) that eliminates cold-start friction. Each session closes by setting the next session's intent. Work becomes a directed sequence rather than a series of isolated conversations. Results from two validations (a meta-framework design project and a non-software operational coordination project): - Zero context re-establishment at session start - Zero intent-misaligned rework - Second project stood up in ~25 min on first attempt, no structural modifications needed Template is public: https://gitlab.com/vigilkeep/ibe-workflow-template Happy to share the ADR that documents the one deliberate deviation from 3.3 guidance (CLAUDE.md runs ~70 lines instead of 40–50 — there's a specific reason).

You just wrote a CLAUDE.md for one of your projects. Vote below, then drop yours in the comments. Bonus points if you ran the same task with and without it and can tell us the difference.

You just used Claude Desktop as a thinking partner instead of a vending machine. Vote below, then tell us in the comments: what was the problem, and what was the insight you walked away with?

Just curious, does everyone write your md files from scratch? Or do you ask claude to help you write, by giving it information? And can I say that the recommendation is to have md files lesser than 150 lines?

Apologies if this topic has already been covered. My thought was to have Jake’s folder structure as my main Ai Operating System and then have a wiki or second brain where I can dump thoughts, ideas, past decisions, mistakes, lessons etc. Combining Jake and Karpathys concepts into one. The second brain knowledge base would be called on when needed for tasks that I call within the folder structure. Bear with me if I’ve gotten some concepts or terms wrong - still learning lots about all of this stuff 😳🤯 Does this make sense or am I missing something important here?