system-rules

Community

Strict OS guardrails for safe automation.

Authorscanbott
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Strict guardrails for the Rawgrowth OS ensure safe, compliant, and auditable agent execution across data loading, output quality, security, and self-improvement workflows.

Core Features & Use Cases

  • Guardrails for data loading: restrict reading to relevant files, prefer grep/glob, and avoid data leakage.
  • Output quality and safety: enforce non-hallucination, require explicit approvals when necessary, and log activity for governance.
  • Compliance and auditing: enforce file placement rules, versioning, CLAUDE.md constraints, and activity logging.

Quick Start

Follow the guardrails whenever you build or audit an agent to ensure safe and auditable behavior.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: system-rules
Download link: https://github.com/scanbott/claude-skills/archive/main.zip#system-rules

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.