# Gateguard

> Enforces Law 1 (Research Before Executing) of the 7 Laws of AI Agent Discipline. Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.

## Facts
- Page: https://tashan.sh/capability/skill-naimkatiman-gateguard
- tashan id: skill:naimkatiman/gateguard
- Source: https://github.com/naimkatiman/continuous-improvement
- Type: skill
- Category: other
- tashan score: 42.0 / 100
- Adoption: 14.0
- Upkeep: 64.0
- Freshness: 100.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- License: MIT
- Official: no

## Install

```sh
cp -r gateguard ~/.claude/skills/
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-08-16 by tashan (https://tashan.sh) from public evidence. Scorer s5.