Instructions for running a Claude Code workflow under ryk supervision, where ryk monitors the agent process and applies safety checks. It also explains the limits of plugin hooks compared with running the process through ryk itself.

Checking ryk setup, starting Claude Code through ryk, and understanding the protection provided by the Claude Code plugin.

It clarifies how to use the strongest available protection and prevents treating advisory hooks as a complete safety boundary.

protect — Skill for Claude Code and Codex by christopherkarani: Instructions for running a Claude Code workflow under 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.

agentmods

npx agentmods add skills/christopherkarani/ryk/protect

Any agent

npx skills add christopherkarani/ryk --skill protect

Clone the repo

git clone --depth 1 https://github.com/christopherkarani/ryk

Made for: Claude Code, Codex.

Or install ryk, the plugin that ships this one along with the rest of its 5 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/christopherkarani/ryk/protect.svg)](https://agentmods.dev/skills/christopherkarani/ryk/protect)

Your own site

<a href="https://agentmods.dev/skills/christopherkarani/ryk/protect"><img src="https://agentmods.dev/badge/skills/christopherkarani/ryk/protect.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 292 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00292
Opus 5	$0.00000	$0.00146
Sonnet 5	$0.00000	$0.00058
Haiku 4.5	$0.00000	$0.00029

Measured 4d ago against content hash 004814116ba2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

protect 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 4d 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/skills/protect/SKILL.md · 45 lines

What it actually says

protect

Explain how to run the current Claude Code workflow under ryk protection.

When to use

Use this skill when you want to ensure the current Claude Code session or command runs inside ryk supervision.

Strongest protection

The strongest local protection is running the Claude Code process itself through ryk:

ryk run -- <claude-code-command>

If the exact Claude Code invocation is unknown, run the Claude Code CLI through ryk using the command you normally use to start Claude Code.

What the plugin provides

The Claude Code plugin adds:

Native skills for doctor, init, protect, redteam, and replay.
Lifecycle hooks that call ryk hook claude <event> for safety checks.

Important limitation

The Claude Code plugin adds native skills and lifecycle hooks. The strongest protection remains running the agent process through ryk run.

Hooks are advisory and additive. They do not replace the supervision that ryk run provides over the child process.

Quick check

Verify ryk is ready:

ryk plugin doctor claude

Notes

This skill does not modify host configuration.
The plugin does not collect telemetry. A user-invoked ryk run wrapper may record only fixed anonymous CLI metadata; see docs/telemetry.md.
Hooks call the ryk CLI; they do not duplicate policy logic.

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.

4d ago First seen · 45 lines · 0 tokens per session scan A 004814116ba2

Subscribe to this mod's changes

protect is a skill published in the GitHub repository christopherkarani/ryk (39 stars, last pushed 14d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 292 tokens. 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.

Security agent-security ai-agents claude-code codex developer-tools plugins

protect

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

protect

When to use

Strongest protection

What the plugin provides

Important limitation

Quick check

Notes

What this file has done since we first saw it

Other skills, from other repositories

deploy-service

markdown-formatter

data-processor

keyring-reference

underdeclared-agent

create-custom-grader