AI Security Index/Skills & Plugins

Agent Skills & Plugins

Coding agents run with your credentials on your machine. These skills and plugins add EDR-style visibility and governance to Claude Code and other agent harnesses — telemetry, destructive-action detection, and a full inventory of every tool an agent can reach.

Guardion Claude Code Plugin

Open Source
Coding Agent Governance

The official Guardion plugin for Claude Code: hook-based lifecycle telemetry, destructive and denied-action detection, and a session-start scan of every skill, MCP server, plugin, and built-in tool the agent can reach. Installs from the Guardion plugin marketplace in two commands.

/plugin marketplace add GuardionAI/guardion-marketplace
/plugin install guardion@guardion
npx @guardion/guardion token set <token>

Guardion CLI (@guardion/guardion)

Open Source
Agent Security Tooling

The @guardion/guardion npm package: token management, agent-security setup, and the local tooling used by the Claude Code plugin. Distributed on npm; pairs with the Guardion gateway and Guard API.

npx @guardion/guardion
token set <token>

Looking for MCP security instead?

Browse gateways, scanners, and governance tools for Model Context Protocol workloads.

MCP Security Directory