By artofrawr
Safety guardrails: destructive command warnings, directory freeze, and combined guard mode
Claude Code Marketplace
/plugin command, hit returnartofrawr/claude-control, hit returnx plugins available to be installed/plugin command, hit returnMay need to use
/reload-pluginsor restart Claude for all updates to take effect.
/plugin command, hit returnuMay need to use
/reload-pluginsfor all updates to take effect.
/plugin command, hit returnMay need to use
/reload-pluginsfor all updates to take effect.
/create-plugin slash command with a name and description:
/create-plugin my-plugin A short description of what it does
plugin.json, SKILL.md, README.md), update the marketplace registry, and update this README/reload-plugins to testYou can also run /create-plugin with no arguments for an interactive walkthrough that supports scaffolding commands, agents, and hooks in addition to skills.
See CONTRIBUTING.md for how to create plugins, validate your work, and submit PRs.
Run the validation script to check all plugins for correct structure and metadata:
bash scripts/validate.sh
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub artofrawr/claude-control --plugin guardrailsPersonal principles that persist across all projects and survive context compaction
Easily create hooks to prevent unwanted behaviors by analyzing conversation patterns
Security reminder hook that warns about potential security issues when editing files, including command injection, XSS, and unsafe code patterns
Security guardrails - credential protection, destructive command blocking, write scope enforcement, supply chain control, browser restrictions
5 essential safety hooks for Claude Code. Blocks rm -rf, force-push, hard-reset, .env overwrites, and package publish. The minimum viable safety net from 800+ hours of autonomous operation.
Block destructive git and filesystem commands before execution
A secure runtime for Claude Code. Intercepts every tool call with policy-based allow/block/ask decisions, evasion detection, path fencing, file snapshots, and audit logging.