Prompts.
Copy. Run in ChatGPT or Claude with one click. Stolen and refined from issues you should be reading.
The Key Keeper Check
Asks what you build, who builds it with you and where your keys sit today, then picks a home for your logins and API keys and gives you a one-hour cleanup plan.
The Agent Leash Audit
Interviews you about the AI agents and automations you use, then names your riskiest permission, one setting to change today, a safe way to test your stop control, and a one-line verdict.
The Agent Inbox Safety Check
Interviews you about who can email your AI agent and what it is allowed to do, then gives a risk verdict, the settings to turn on and the actions that should always wait for a human.
The Remote Hire Verification Checklist
Interviews you about the role, how you found the person and what they'll reach, then builds your own before-you-sign checklist for remote hires, an email to your staffing firm and the warning signs to watch for.
The Exposure Check
Which of your systems are reachable from the open internet, and what happens if one of them is taken? Answer four questions and get a straight verdict.
The Delegation Auditor
Finds the places where an automated system could do something you would have said no to. Interviews you about one setup, then ranks the real gaps by consequence rather than by how easy they are to fix.
Security review for an AI-generated PR
Catch the common classes of bug that LLM-written code ships. Run this BEFORE you merge.
