Every Rule in My CLAUDE.md Is a Mistake I Made Once
Six months of AI collaboration produced 2,487 lines of context files. Every rule started as a failure. Here’s what broke, what I learned, and why your CLAUDE.md is governance, not documentation.
-
-
So You’re Good at AI? Build This Skill Before You Get Sued
— Information Security — April 2026 Here’s a pattern I’ve been watching emerge as AI-assisted content creation takes off across the security industry: well-intentioned professionals embedding fingerprints of their real organizations into the templates, tutorials, and open-source repos they share. It’s not carelessness. It’s efficiency. AI lets you generate pages of content in minutes, building…
-
Context Engineering: How I Taught an AI to Coach Pinball
GoofyGoober walks up to the kiosk at Midwest Aleworks. He’s been ranked #1 in this month’s pinball league for two weeks straight, but the gap is shrinking. He opens the hamburger menu, taps Player Strategy Report, and stares at his name on the screen. The page knows things. It knows he’s classified as “The Grinder”…
-
How 25 Pinball Machines Talk to a Database (Without Anyone Touching a Keyboard)
It’s a Tuesday night at Midwest Aleworks. Someone — I’ll call her Pinball Tina — just nudged a 4.2 billion score on Iron Maiden. She doesn’t know me. I don’t know her. I’m not even in the building. But within ten minutes, her score is on a public leaderboard, her name is ranked against 329…
-
Why I Treat My AI Context Like Infrastructure
I spent months using Claude wrong. Not wrong in a way that produced bad results — I was getting answers, writing drafts, summarizing documents. It worked. But I was using it like a search engine: open a session, ask something, close it. Every conversation started from zero. Every session began with five minutes of re-explaining…
-
Give Claude a Memory
Every time I open Claude, it starts with a blank slate. No memory of who I am. No idea what I’m working on. No knowledge of decisions I’ve already made, tools I use, or how I like to communicate. So I re-explain. It guesses. I correct it. By the time we’re actually working, five minutes…
-
Don’t worry! It’s Not a Secret!
// The API Key Problem Nobody Saw Coming For over a decade, Google told developers that API keys weren’t secrets. Embed them in your JavaScript. Paste them into your HTML. Ship them in your client-side code. Firebase’s own security checklist had a green checkmark next to “API keys for Firebase services are not secret.” Google…
-
Ever Lost your Soul?
I’ve sat in that chair. Not Dario Amodei’s specifically — mine had worse lumbar support and the coffee was from a Keurig — but the same chair. The one where you’re the security person trying to explain to a room full of excited stakeholders why we need to slow down. Why the thing they want…
-
Free Legal Advice – Users of AI
— Information Security — April 2026 Here’s a pattern I’ve been watching emerge as AI-assisted content creation takes off across the security industry: well-intentioned professionals embedding fingerprints of their real organizations into the templates, tutorials, and open-source repos they share. It’s not carelessness. It’s efficiency. AI lets you generate pages of content in minutes, building…
-
An Elegant Coach Claude
Will Larson’s An Elegant Puzzle has a chapter on presenting to leadership that changed how I think about structured communication. A 7-step framework for making recommendations that actually land. Clear, repeatable, effective. Problem is, frameworks you don’t use are just bookmarks. So I did what any self-respecting terminal dweller would do: I turned it into…