agentmods.dev

ryk

A Claude Code plugin that adds ryk safety hooks and skills. Claude Code is a coding assistant that can run commands and change files; ryk checks those activities against policies.

In plain words
What is it for?
It helps run ryk health checks, policy checks, red-team test fixtures, replay checks, and hook-based safety checks from Claude Code.
Why use it?
It provides checks around agent actions and is configured to stop when its required safety setup is unavailable.

Plugin for Claude Code

39 12d ago A scan tokens not measured original Apache-2.0
View the source file christopherkarani/ryk
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add christopherkarani/ryk
agentmods
npx agentmods add plugins/christopherkarani/ryk/claude-code-plugin
Clone the repo
git clone --depth 1 https://github.com/christopherkarani/ryk

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

ryk scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

integrations/claude-code-plugin/.claude-plugin/plugin.json · 28 lines

What it actually says

{
    "name": "ryk",
    "version": "0.2.22",
    "description": "ryk safety hooks and skills for Claude Code.",
    "author": {
        "name": "ryk"
    },
    "homepage": "https://github.com/christopherkarani/ryk",
    "repository": "https://github.com/christopherkarani/ryk",
    "license": "Apache-2.0",
    "keywords": [
        "security",
        "ai-agents",
        "policy",
        "audit",
        "redteam",
        "ryk"
    ],
    "skills": "./skills/",
    "hooks": "./hooks/hooks.json",
    "interface": {
        "displayName": "ryk",
        "shortDescription": "Runtime firewall helpers for Claude Code.",
        "longDescription": "Run ryk doctor, policy checks, red-team fixtures, replay, and hook-based safety checks from Claude Code. Hooks use canonical ryk installation paths and fail closed when unavailable.",
        "developerName": "ryk"
    }
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 28 lines scan A 160ca20d63c8

Subscribe to this mod's changes

ryk is a plugin published in the GitHub repository christopherkarani/ryk (39 stars, last pushed 12d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

SecurityTestingagent-securityai-agentsclaude-codecodexdeveloper-toolsplugins
Related

Other plugins, from other repositories

a11y-audit

Full accessibility audit with WCAG compliance checking.

rohitg00/awesome-claude-code-toolkit · not measured

backend-architect

Backend service architecture design with endpoint scaffolding.

rohitg00/awesome-claude-code-toolkit · not measured

dev-tooling

Three MCP servers for PHP and JavaScript operations plus an optional PHP language server. PHP (php-tooling): PHPStan, ECS, Rector, PHPUnit, PHPUnit coverage gap analysis, Symfony Console. Administration (js-admin-tooling): ESLint, Stylelint, Prettier, Jest, TypeScript, Vite builds. Storefront (js-storefront-tooling)…

shopwareLabs/ai-coding-tools · not measured

bevy-plugin

Bevy game engine development - ECS, rendering, game architecture.

laurigates/claude-plugins · not measured

aai-plugins

Production-ready workflow framework for Claude Code - structured development patterns, work management, and quality automation.

stefan-jansen/claude-code-toolkit · not measured

development

Code development and quality assurance tools - analyze, test, fix, review.

stefan-jansen/claude-code-toolkit · not measured