By zot24
Prevents catastrophic file deletion by transforming rm commands to trash and blocking dangerous patterns like rm -rf /
Executes bash commands
Hook triggers when Bash tool is used
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 zot24/skills --plugin safe-deleteCrafts high-engagement X (Twitter) content using conversation hijacking, authority building, and strategic hooks
Expert assistant for developing, packaging, testing, and submitting apps for umbrelOS. Handles the complete app lifecycle from scaffolding to PR submission.
Expert at understanding and working with Hermes Agent — its memory system, skills, cron jobs, tools, and behavioral conventions
Expert assistant for building AI applications with Vercel's AI SDK. Covers text generation, streaming, structured outputs, tools, agents, and multi-provider support.
Expert assistant for browser automation with AI agents using Vercel's agent-browser CLI. Covers commands, selectors, sessions, snapshots, and integration patterns.
Safety hooks to block or require user approval for dangerous commands (rm, git operations, .env access, file size limits)
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
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.
Blocks destructive commands outside the project directory. Allows file operations within the project (refactoring, cleanup) but prevents accidental damage outside it.
Pre-execution safety layer that blocks dangerous shell commands and credential file reads using pattern matching + LLM analysis. Fail-closed design.