safety-guard

原文涵盖的主题

• Safety Guard — Prevent Destructive Operations
• When to Use
• How It Works
• Mode 1: Careful Mode
• Mode 2: Freeze Mode
• Mode 3: Guard Mode (Careful + Freeze combined)
• Unlock
• Enforcement

When working on production systems When agents are running autonomously (full-auto mode) When you want to restrict edits to a specific directory During sensitive operations (migrations, deploys, data changes) Three modes of protection. They are instructions the agent follows, not enforced blocks (see Enforcement). Before it runs a destructive command, the agent stops and warns: When detected: shows what the command does, asks for confirmation, suggests safer alternative. Locks file edits to a specific directory tree, for example: "freeze edits to src/components/". The agent does not Write/Edit outside src/components/, and explains why when a change would need it. Useful when you want an agent to focus on one area without touching unrelated code. Both protections active, for example: "guard mode, write only to src/api/, read anything". The agent can read anything but only writes to src/api/, and asks before any destructive command. Tell the agent to stop applying the rules. This skill is advisory. ECC ships no /safety-guard command and no hook for it, so nothing blocks a tool call that breaks these rules. For blocking that does not depend on the agent, use Claude Code permission den

这里只展示节选，请以完整原文和当前要求为准。