Agent Capability Analysis
The safety-guard skill by affaan-m is an open-source official AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance. Optimized for ai-agents, anthropic, claude-code.
Ideal Agent Persona
Ideal for Autonomous Agents requiring advanced protection against destructive operations in production systems
Core Value
Empowers agents with Careful, Freeze, and Guard modes to intercept and block harmful commands, such as rm -rf, git push --force, and docker system prune, ensuring safe execution of Bash, Write, Edit, and MultiEdit tool calls
↓ Capabilities Granted for safety-guard
! Prerequisites & Limits
- Requires PreToolUse hooks implementation
- Limited to Bash, Write, Edit, and MultiEdit tool calls
- Needs active logging to ~/.claude/safety-guard.log
Browser Sandbox Environment
⚡️ Ready to unleash?
Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.
! Thin Content Warning
This skill repository lacks comprehensive documentation and has been blocked from search indexing. Double check the source code before installing.
safety-guard
Install safety-guard, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.
FAQ & Installation Steps
These questions and steps mirror the structured data on this page for better search understanding.
? Frequently Asked Questions
What is safety-guard?
Ideal for Autonomous Agents requiring advanced protection against destructive operations in production systems
How do I install safety-guard?
Run the command: npx killer-skills add affaan-m/everything-claude-code/safety-guard. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.
What are the use cases for safety-guard?
Key use cases include: Preventing accidental data loss during migrations and deploys, Restricting edits to specific directories for focused development, Blocking destructive commands in autonomous full-auto mode.
Which IDEs are compatible with safety-guard?
This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.
Are there any limitations for safety-guard?
Requires PreToolUse hooks implementation. Limited to Bash, Write, Edit, and MultiEdit tool calls. Needs active logging to ~/.claude/safety-guard.log.
↓ How To Install
-
1. Open your terminal
Open the terminal or command line in your project directory.
-
2. Run the install command
Run: npx killer-skills add affaan-m/everything-claude-code/safety-guard. The CLI will automatically detect your IDE or AI agent and configure the skill.
-
3. Start using the skill
The skill is now active. Your AI agent can use safety-guard immediately in the current project.
