ai-dev-guardrails

Universal AI agent development guardrails with five defense layers: instruction gate, project monitoring, delivery reliability, code quality audit, and scope fidelity enforcement. Prevents blind compliance, hallucination, scope creep, unrealistic promises, code quality degradation, and over-engineering. Designed for Claude Code, Codex, Gemini CLI, and any AI coding agent.

by @nagi-226 (Nagi_226)·MIT-0