gateguard

原文涵盖的主题

• GateGuard — Fact-Forcing Pre-Action Gate
• When to Activate
• Core Concept
• Evidence
• Gate Types
• Edit / MultiEdit Gate (first edit per file)
• Write Gate (first new file creation)
• Questions fit the change

A PreToolUse hook that forces Claude to investigate before editing. Instead of self-evaluation ("are you sure?"), it demands concrete facts. The act of investigation creates awareness that self-evaluation never did. Working on any codebase where file edits affect multiple modules Projects with data files that have specific schemas or date formats Teams where AI-generated code must match existing patterns Any workflow where Claude tends to guess instead of investigating LLM self-evaluation doesn't work. Ask "did you violate any policies?" and the answer is always "no." This is verified experimentally. But asking "list every file that imports this module" forces the LLM to run Grep and Read. The investigation itself creates context that changes the output. Three-stage gate: No competitor does all three. Most stop at deny. Two independent A/B tests, identical agents, same task: | Task | Gated | Ungated | Gap | | --- | --- | --- | --- | | Analytics module | 8.0/10 | 6.5/10 | +1.5 | | Webhook validator | 10.0/10 | 7.0/10 | +3.0 | | Average | 9.0 | 6.75 | +2.25 | Both agents produce code that runs and passes tests. The difference is design depth. MultiEdit is handled identically — each f

这里只展示节选，请以完整原文和当前要求为准。