Claude Code delegates coding to isolated CLI agents it doesn't trust (Codex, OpenCode, Pi, Pythinker), freezes what they produce, verifies it independently, and merges only what a human approves.
Don't let AI destroy your hard work! HardStop is a rock-solid protection for AI-generated commands. Pre-execution safety validation for Claude Code, Claude Cowork. Catches dangerous commands before they run: whether from AI mistakes, hallucinations, prompt injection, or misunderstood instructions. Seatbelts for the agentic AI era.
Self-driving loops for AI coding — a state-machine loop engine plugin for Claude Code & Codex: adversarial red/blue implementation, evidence-gated QA, knowledge engineering. Goal in, merged PR out, gates you control.
Claude skill that turns a single request into a narrated mythic short film in a layered cut-paper diorama style — three-colour cardstock worlds, paper wipes, Unsora MCP + local ffmpeg, one assembled MP4.
TDD + requirements workflow skill for AI coding agents (Claude Code, Codex, Antigravity, Cursor, Windsurf, etc.). Part of the Shelpuk agentic suite alongside Serena, Kindly Web Search, and Lad.