Show HN: A police department for your Claude Code agents

Y	Hacker News new \| ask \| show \| jobs

	Show HN: A police department for your Claude Code agents (github.com)
	10 points by softie123 17 hours ago

3 comments

tomaytotomato 16 hours ago

Not a criticism, but why would I use this instead of locking down my Claude using the allow/deny permissions list?

    "permissions": {
    "allow": [
      "Bash(npm run lint)",
      "Bash(npm run test *)",
      "Read(~/.zshrc)"
    ],
    "deny": [
      "Bash(curl *)",
      "Read(./.env)",
      "Read(./.env.*)",
      "Read(./secrets/**)"
    ]
  },

link

softie123 14 hours ago

Idea is not to deny permissions to everything but just keep a log on what the agents are doing thats not in line with our permissions and also you have to know what they are bypassing so we can put them in deny list later. Very useful when you spawn many agents working in parallel. This is more of an observability tool.

link

tenuousemphasis 12 hours ago

Well at least you'll know why your data was exfiltrated or your systems compromised, even if you can't stop it...

link

softie123 10 hours ago

thats exactly what i went for. also I am keeping all the logs compressed so may be i can build something to build later

link

FishAngular12 16 hours ago

Where would one put this? In AGENTS.md?

link

abirch 15 hours ago

Your settings file: User settings are defined in ~/.claude/settings.json