Damage Control

Block dangerous commands and protect sensitive paths in Claude Code operations.

Updated Mar 7, 2026
One-click install
npx skills add https://github.com/randoneering/nix-flake-mirror --skill damage-control-randoneering
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Damage Control
Source: https://github.com/randoneering/nix-flake-mirror/tree/main/home/programs/opencode/skills/damage-control
Command: npx skills add https://github.com/randoneering/nix-flake-mirror --skill damage-control-randoneering

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Damage Control blocks dangerous commands and protects sensitive files by enforcing configurable guardrails around Claude Code tool usage.

Core Features & Use Cases

  • Blocks destructive bash commands and restricted edits/writes
  • Applies across global, project, and personal settings with shared patterns.yaml
  • Use case: quickly harden a development environment by enabling automated protection across workflows

Quick Start

Install and configure the Damage Control hooks for your chosen level and runtime.

Frequently Asked Questions about Damage Control

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I block dangerous bash commands during Claude Code operations?

Block dangerous bash commands by installing configurable hook scripts and a patterns.yaml file that enforce permission prompts and command-blocking across global, project, and personal settings.

Can I protect sensitive file paths from automated edits and writes?

Protect sensitive file paths by defining restricted edit and write rules in a shared patterns.yaml configuration, which applies guardrails across your development environment workflows.

How do hook-based command-blocking mechanisms work for AI code assistants?

Hook-based command-blocking mechanisms work by intercepting tool usage calls, checking them against configurable patterns.yaml rules, and enforcing blocking or permission prompts before execution proceeds.

What's the best way to harden a development environment against destructive commands?

Harden a development environment by enabling automated protection across workflows, applying shared patterns.yaml configurations and hook scripts to block destructive bash commands and restricted file edits.

Does Damage Control support custom permission rules for different project levels?

Damage Control supports custom permission rules across global, project, and project-personal settings, using a shared patterns.yaml file to configure blocking and permission prompts for each level.

Are there limitations to using hook scripts for command-blocking in local development?

Limitations of using hook scripts for command-blocking include requiring proper runtime configuration and installation at each settings level to ensure automated protections enforce safe command execution consistently.