Damage Control
Install, configure, and manage the Claude Code Damage Control security hooks system. Use when user mentions damage control, security hooks, protected paths, blocked commands, install security, or modify protection settings.
Install
With your agent
Install OMGSkills skill "disler/claude-code-damage-control:.claude/skills/damage-control" into this agent's normal skills directory: call the OMGSkills MCP get_install_plan tool for your agent and run the script it returns (it installs only the pinned commit and verifies SKILL.md), and stop if MCP or the pin is unavailable. Do not overwrite or change existing skills without asking me.
Manual command
git clone https://github.com/disler/claude-code-damage-control /tmp/claude-code-damage-control && ln -s /tmp/claude-code-damage-control/.claude/skills/damage-control ~/.claude/skills/Damage ControlFrom README
Damage Control Skill Defense-in-depth protection system for Claude Code. Blocks dangerous commands and protects sensitive files via PreToolUse hooks. Overview This skill helps users deploy and manage the Damage Control security system, which provides: Command Pattern Blocking: Blocks dangerous bash commands (rm -rf, git reset --hard, etc.) Ask Patterns: Triggers confirmation dialog for risky-but-valid operations (ask: true) Path Protection Levels: zeroAccessPaths - No access at all (secrets/credentials) readOnlyPaths - Read allowed, modifications blocked noDeletePaths - All operations except delete Skill Structure After The workflow copies hooks and creates settings based on the chosen level: Global Hooks Project Hooks Project Personal Hooks --- Cookbook This section defines the decision tree for handling user requests. Based on what the user says, read and execute the appropriate workflow prompt.