safe-self-mod

Community

Safely validate self-modifications in isolation.

Authorzkksdk
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This workflow ensures that changes affecting the main instance (core files under /workspace, including SOUL.md, IDENTITY.md, AGENTS.md, TOOLS.md, MEMORY.md, and configuration or skill files such as openclaw.json and skills/*) are validated in an isolated Clone-01 environment before applying to the main workspace.

Core Features & Use Cases

  • Recognizes write operations that touch core identity/behavior files, configuration, or skill updates.
  • Performs isolated verification using a prepared Clone-01 session to validate changes without impacting the live workspace.
  • Analyzes verification outcomes and reports PASS with risk assessment or FAIL with issues, enabling user consent prior to modification.
  • Requires explicit user confirmation before applying any changes to the main instance.

Quick Start

Initiate a safe-mod workflow by validating a proposed change in Clone-01 and report the verification result.

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: safe-self-mod
Download link: https://github.com/zkksdk/skills/archive/main.zip#safe-self-mod

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.