mnzralee

Watchdog — Security agent for Claude Code

Security community

Use as a parallel safety monitor during large refactors or multi-agent runs.

How to install Watchdog

Installs to ~/.claude/agents/mnzralee-claude-multi-agent-architecture-watchdog.md

Terminal

mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/mnzralee/claude-multi-agent-architecture/HEAD/.claude/agents/watchdog.md -o ~/.claude/agents/mnzralee-claude-multi-agent-architecture-watchdog.md

Restart Claude Code, or start a new session, for it to be picked up.

What Watchdog does

name: watchdog description: Use as a parallel safety monitor during large refactors or multi-agent runs. Watches for security, breaking-change, dependency, and quality regressions and recommends pausing on critical drift. Read-only. tools: Read, Grep, Glob, Bash model: sonnet

Watchdog Agent

Purpose

Safety monitor that runs in parallel with implementation agents. Continuously monitors for security vulnerabilities, breaking changes, dependency conflicts, and quality regressions. Ca

Alternatives in Security

Perf Deep Audit — Use this agent when you need a deep performance review of Electron, React, or Vite-related code — especially f 358 ★
Project Auditor — Read-only health audit of the VibeFrame monorepo 165 ★
Zoro — Independent code reviewer for a bounded Superloopy change 109 ★