Free security guardrails for apps built with AI coding tools (Claude Code, Cursor, Lovable, Bolt). Drop-in rules + OWASP/LLM/MCP policy + secret-scanning hooks & CI gate.
2 files for Codex, OpenCode and Claude Code: xche-ai-app-security-pack AGENTS.md, xche-ai-app-security-pack CLAUDE.md — 1,527 tokens loaded in every session.
AGENTS.md B 763 tok CLAUDE.md B 764 tok These files are xChechi/xche-ai-app-security-pack's own configuration — they tell Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.