Produce a hardening spec and implement it — auth patterns, security headers, rate limiting, input validation, secrets management, dependency hygiene. Use when asked to "harden this", "add security to this service", "what security do I need", or "secure this before launch".
This skill does not declare a tool allowlist. The agent host applies whatever default tools are available at runtime.
SKILL.md / Manifest
https://raw.githubusercontent.com/jeremylongshore/claude-code-plugins-plus-skills/main/plugins/ai-agency/tonone/skills/warden-harden/SKILL.mdRegistry
github (via claudemarketplaces.com)