Gateguard

Forces Claude to gather concrete facts before editing files or running destructive commands. Instead of "are you sure?" self-evaluation (which never works), it blocks the edit and demands specific investigation: list all importers via grep, show the data schema, quote the actual user instruction. Two A/B tests show a +2.25 point quality improvement because the act of investigation creates context that changes what Claude writes. The trade-off is real: every first edit per file gets blocked once, which slows you down but catches the "I assumed ISO dates when your CSVs use %Y/%m/%d" class of bugs. Worth it on codebases where edits ripple across modules.

skills.sh installs: 3.1K
GitHub stars: 229.1K
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add affaan-m/everything-claude-code --skill gateguard --agent claude-code

Installs into .claude/skills of the current project.

Files

GateGuard — Fact-Forcing Pre-Action Gate

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.

When to Activate

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

Core Concept

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:

1. DENY  — block the first Edit/Write/Bash attempt
2. FORCE — tell the model exactly which facts to gather
3. ALLOW — permit retry after facts are presented

No competitor does all three. Most stop at deny.