agent-audit vs everything-claude-code - AI Skills Comparison

Description

Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis. 49 rules mapped to OWASP Agentic Top 10 (2026). Works with LangChain, CrewAI, AutoGen.

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.