Claude Code

Audit Your Claude Managed Agents Security Settings With One Command

Claude Code 2.1.304 added a command that compares your Managed Agents agent with Anthropic's security guide and changes nothing. The command, a prompt to run it, and the settings it looks at

Alex ChenAlex Chen@nocodealex · 50,000+ follow on Instagram
2min read
1prompts to copy
3numbered steps
4sections

Claude Code 2.1.304 added /claude-api managed-agents-secure. It compares a Managed Agents agent's settings with Anthropic's published security guide, and it does not change anything. Here is how to run it and what the guide checks.

Free, for your emailGet the full setup steps + the copy-paste setup prompt

Free, for your email

Get the full setup steps + the copy-paste setup prompt

The rest of this guide (4 more sections, 1 copy-paste prompt) opens right here. The setup prompt, one paste into Claude that sets it all up, comes by email only. Use your real address.

Unlocks: Step 1: update and run it · What Anthropic's guide covers · The catch · Sources

50,000+ follow where these guides come from. No spam, reply “unsubscribe” any time.

Read next

3 Official Claude Plugins to Install First: Setup, CLAUDE.md and Security
Anthropic ships plugins in its own marketplace that audit your setup, keep CLAUDE.md honest and review the code Claude writes. The install command for each, what it does, and the catch with the security one
2 min
Stop Hidden Orders in Your Files From Tricking Claude: Set Up the Free /trojan Detector in 2 Minutes
A file can hide a sentence in text you can't see, and when you hand that file to Claude, Claude can follow the hidden order and try to steal things like your passwords. Anthropic, the makers of Claude, call this kind of prompt injection one of the most significant security challenges for browser-based AI agents. This free Claude Code skill checks a file before Claude reads it: three checks, the hidden text shown in red. How to set it up, ready-made prompts, and what an answer looks like
11 min
Meet Dot, the ChatGPT Agent That Works While You Sleep
Dots are always-on agents inside ChatGPT with their own computer. What they do, a starter prompt to try, and the one catch
2 min