settings

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Security

Grade C, and why

settings scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

.claude/settings.json · 44 lines

What it actually says

{
  "hooks": {
    "SessionStart": [
      {
        "hooks": [
          {
            "type": "command",
            "command": "/home/ubuntu/.claude/asp/hooks/clean-allow-list.sh"
          },
          {
            "type": "command",
            "command": "/home/ubuntu/.claude/asp/hooks/session-audit.sh"
          }
        ]
      }
    ]
  },
  "permissions": {
    "allow": [
      "Bash(*)"
    ],
    "ask": [
      "Bash(docker deploy *)",
      "Bash(docker push *)",
      "Bash(git push *)",
      "Bash(git push)",
      "Bash(git rebase *)",
      "Bash(git rebase)",
      "Bash(rm -r *)",
      "Bash(rm -rf *)"
    ],
    "deny": [
      "Bash(docker deploy *)",
      "Bash(docker push *)",
      "Bash(git push *)",
      "Bash(git push)",
      "Bash(git rebase *)",
      "Bash(git rebase)",
      "Bash(rm -r *)",
      "Bash(rm -rf *)"
    ]
  }
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

Related

Other settings, from other repositories