By nsheaps
Pre-tool-call safety evaluation using Claude CLI (haiku) with script-style hooks
Matches all tools
Hooks run on every tool call, not just specific ones
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 nsheaps/ai-mktpl --plugin safety-evaluation-scriptIntelligent skill that helps Claude parallelize Task tool calls when working on repetitive or batch operations, optimizing throughput based on task complexity
Relentlessly fix a PR until CI passes — iterates through review, fix, push cycles until green
Skills for managing Proxmox VE hosts and LXC containers — creating containers, running Docker in LXC, and hosting services like cloudflared.
Launch independent Claude sub-agents in tmux sessions with custom configurations, tool restrictions, and iTerm integration
Automatically syncs todos and plans from ~/.claude/ to the current project's .claude/ directory
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.
Smart command safety filter for Claude Code — parses shell pipelines and evaluates per-command safety rules to auto-approve safe commands and block dangerous ones
Production safety hooks for autonomous Claude Code operation. Context monitoring, syntax checking, branch protection, activity logging, and more.
Block destructive git and filesystem commands before execution
Create custom behavioral rules through markdown configuration files - prevent unwanted behaviors with pattern matching
Achieve flow state safely with Claude Code. Auto-approves routine work, gates risky actions, hard-blocks dangerous patterns. Dual enforcement (skill + hooks), token cap for cost governance, full audit trail. Zero dependencies.