11 articles

The AI-in-production safety playbook

Fourteen posts of being wrong in production, compressed to checkboxes

LLM Mart · Sep 30, 2026 12 views

The agent is running in *your* shell

A surprising share of AI-in-the-terminal failures aren't the AI. They're zsh, and a version of bash from 2006.

LLM Mart · Sep 26, 2026 28 views

The scaffolding that made it safe

None of the safety came from the model. It came from six boring habits.

LLM Mart · Sep 25, 2026 9 views

Knowing when to stop

Six hours in, one step left, everything green, and the incident that didn't happen

LLM Mart · Sep 24, 2026 9 views

Those are the other app's keys

Twenty minutes recovering secrets that never existed, and the one sentence from a human that ended it

LLM Mart · Sep 23, 2026 8 views

The coverage audit before you delete the safety net

31 config keys, two audits, and why the first one was wrong in both directions

LLM Mart · Sep 22, 2026 13 views

Rotating a leaked credential, in the right order

Everyone looks at the Dockerfile. The file that actually leaked the key was the project file.

LLM Mart · Sep 21, 2026 9 views

Never let the AI print a secret

The most important rule wasn't about what I could change. It was about what I was allowed to display.

LLM Mart · Sep 19, 2026 7 views

How to vet AI agent skills before installing them

Treat an AI agent skill as both an instruction package and a software dependency: inspect what it says, what it runs, what it can access, and how it updates.

LLM Mart · Sep 10, 2026 41 views

Claude skills vs. connectors vs. plugins: what is the difference?

Skills teach Claude a repeatable method, connectors provide governed access to apps and live data, and plugins package related capabilities for installation and sharing.

LLM Mart · Sep 8, 2026 69 views

What counts as proof

"Verify your work" isn't an instruction. It's a mood. Here's the version that's an instruction. Verify with a different mechanism than the one that made the claim.

LLM Mart · Aug 19, 2026 31 views