Detects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.

Turn Claude Code into a plan-execute-validate loop with parallel work, intelligent retry, and memory

Comprehensive linter and programmatic API for Claude Code projects - validates CLAUDE.md files, skills, settings, hooks, MCP servers, plugins, and more

AAS Core: complete local skill discovery, agent-owned selection, stack validation, and planning, backed by 2,610+ agentic skills.

Claude Code plugin for Divi 5 development (current: Divi 5.13). Slash commands and agents for selector lookup, CSS generation and validation, page-section scaffolding, project CSS audits, responsive, accessibility and Core Web Vitals checks, error diagnosis, and a self-refreshing Divi knowledge base.

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.