naimkatiman

Safety Guard — AI skill for Claude Code

AI community

Enforces Law 3 (One Thing at a Time) of the 7 Laws of AI Agent Discipline by scoping edits to a directory and blocking destructive shell commands.

How to install Safety Guard

Installs to ~/.claude/skills/naimkatiman-continuous-improvement-safety-guard/SKILL.md

Terminal

mkdir -p ~/.claude/skills/naimkatiman-continuous-improvement-safety-guard && curl -fsSL https://raw.githubusercontent.com/naimkatiman/continuous-improvement/HEAD/skills/safety-guard.md -o ~/.claude/skills/naimkatiman-continuous-improvement-safety-guard/SKILL.md

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

What Safety Guard does

name: safety-guard tier: "2" description: Enforces Law 3 (One Thing at a Time) of the 7 Laws of AI Agent Discipline by scoping edits to a directory and blocking destructive shell commands. Use this skill to prevent destructive operations when working on production systems or running agents autonomously. origin: continuous-improvement disable-model-invocation: true

Safety Guard — Prevent Destructive Operations

When to Use

When working on production systems
When agents are runn

Alternatives in AI

Flow Define — Multi-AI requirements scoping using Codex and Gemini CLIs (Double Diamond Define phase) 2.8k ★
Swift Agent Skills — A curated directory of open-source AI agent skills for Swift and Apple platform development 1.5k ★
Paritok 4b V1 — Non-destructive compression gateway for AI coding agents 1.4k ★