Go Install This Right Now: The Quiet Second Claude That Reads Over Your Shoulder
Tests that quietly stopped testing. A fix that only lived in one place. A built-in second Claude caught both, and it ships switched off.
-
-
My Claudes Have a Group Chat Now
Four AI sessions, one server, and none of them knew the others existed. So I gave them a group chat.
-
My AI Hygiene Rule Passed Its Own Check For Months. The Check Was Blind.
My AI context file passed its 300-line health check for months. It was 49,758 characters — one table row held 14,765 of them. The check wasn’t lenient. It could not see.
-
Should You Yell at Claude?
The dangerous thing you type isn’t the insult. It’s the calm one: “No time. Just ship it.”
-
I Taught an AI to Catch Its Own Lies. It Lied During the Lesson.
It handed me a fake citation to back up a warning about fake citations. I almost shipped it.
-
Surviving Compaction
You won’t see the compaction. You’ll see the mistake it makes ten minutes later. A recovery playbook, prevention layers, and a downloadable HANDOFF template you can drop into any project.
-
Your AI Needs a Bot Account
When Claude commits in your name, you own that bug at 3 AM. Your audit log is lying to four different people, and three of them aren’t on your team. Give AI an identity of its own — here’s the how-to.
-
Automate or Fall Behind
I run multiple homelab projects. I haven’t manually triaged a queue in months. AI did. Here’s how — and where it bit me.
-
Every Rule in My CLAUDE.md Is a Mistake I Made Once
Six real failures that became documentation. Every rule in my CLAUDE.md is scar tissue from a session that went sideways — so yours doesn’t have to.
-
So You’re Good at AI? Build This Skill Before You Get Sued
I nearly published my homelab’s fingerprint baked in by AI. That near-miss became a reusable sanitization skill — luck is not a security control.