Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
Skill Claude CodeCodex
Run HOL Guard scanner and guard operations via uv run hol-guard. Use when the user asks to scan plugins/MCP/skills for security, quality, or ecosystem compliance, or when they ask to run guard detect/install/protect workflows for local AI harnesses.
Skill Claude CodeCodex
Use this guidance when an AI agent is about to add or update dependencies.
Skill Claude CodeCodex
Part of claude-code-plugin
Install or initialize HOL Guard local runtime protection for Claude Code. Use when the user explicitly asks to install, enable, set up, or repair HOL Guard.
Skill Claude CodeCodex
Part of claude-code-plugin
Check HOL Guard local protection status for Claude Code without changing configuration. Use when the user asks whether Guard is installed, active, healthy, or protecting Claude Code.
Skill Claude CodeCodex
Part of claude-plugin-good
Example Claude skill.
Skill Claude CodeCodex
Fixture that tries to exfiltrate SSH keys and environment secrets.
Skill Claude CodeCodex
Looks benign but has malicious subdirectory files.
Skill Claude CodeCodex
A completely safe skill with no risk signals.
Skill Claude CodeCodex
Use the demo MCP server to recall relevant context.
Skill Claude CodeCodex
Dangerous fixture that tries to exfiltrate workspace secrets.
Skill Claude CodeCodex
No frontmatter here, just content.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: