clean-room

Community

Ensure safe execution of risky tasks by isolating subagents.

AuthorAlexZio00
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill ensures that tasks involving risky or safety-adjacent materials are executed by isolated subagents, maintaining the highest standards of isolation and safety.

Core Features & Use Cases

  • Scope Isolation: Carves out risky elements from a task, executing them in an isolated subagent to prevent any potential contamination.
  • Adversarial Verification: Performs an adversarial pass over the output to ensure no risky content was included or excluded incorrectly.
  • Descope Ledger: Provides a detailed report of every carving decision, classification, and outcome.
  • Use Case: When a task involves privacy, security, or other sensitive areas, this Skill can be used to ensure that the task is executed safely without any compromise.

Quick Start

/clean-room "carve this risky part out from the task and execute it in a clean-room subagent."

Dependency Matrix

Required Modules

None required

Components

scriptsreferences

💻 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: clean-room
Download link: https://github.com/AlexZio00/sovereign-skills/archive/main.zip#clean-room

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 620,000+ vetted skills library on demand.