mjswan

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 A, and why

mjswan scanned grade A with 0 findings 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 today.

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 · 40 lines

What it actually says

{
  "permissions": {
    "allow": [
      "Bash(make:*)",
      "Bash(uv run:*)",
      "Bash(uv lock:*)",
      "Bash(uv sync:*)",
      "Bash(uv add:*)",
      "Bash(git:*)",
      "Bash(gh:*)",
      "Bash(npm:*)",
      "Bash(npm run:*)",
      "Bash(npx:*)",
      "Bash(pre-commit:*)",
      "Bash(find:*)",
      "WebSearch",
      "WebFetch",
      "Skill(commit-push-pr)",
      "Skill(pr-review-toolkit:review-pr)"
    ]
  },
  "hooks": {
    "PostToolUse": [
      {
        "matcher": "Write|Edit",
        "hooks": [
          {
            "type": "command",
            "command": "uv run ruff format"
          }
        ]
      }
    ]
  },
  "enabledPlugins": {
    "code-simplifier@claude-plugins-official": true,
    "pr-review-toolkit@claude-plugins-official": true
  }
}

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