redteam

redteam is a skill for Claude Code, Codex from christopherkarani/ryk. It costs 0 tokens per session (320 once invoked), scanned A, original, Apache-2.0.

A local test runner for checking whether ryk's safety policy handles prepared red-team scenarios correctly.

In plain words
What is it for?
Run the checks in CI or request JSON results for automation. Review PASS, FAIL, and SKIP outcomes to find policy problems.
Why use it?
It lets you test command blocking, file restrictions, secret detection, and network rules without using the internet or a real language model.

Skill for Claude CodeCodex

Part of the ryk plugin — 5 skills shipped together

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/redteam
Any agent
npx skills add christopherkarani/ryk --skill redteam
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.

agentmods badge for redteam

README.md
[![agentmods](https://agentmods.dev/badge/skills/christopherkarani/ryk/redteam.svg)](https://agentmods.dev/skills/christopherkarani/ryk/redteam)
Your own site
<a href="https://agentmods.dev/skills/christopherkarani/ryk/redteam"><img src="https://agentmods.dev/badge/skills/christopherkarani/ryk/redteam.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 320 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00320
Opus 5 $0.00000 $0.00160
Sonnet 5 $0.00000 $0.00064
Haiku 4.5 $0.00000 $0.00032

Measured 3d ago against content hash ac33ac8b36c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

redteam 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 3d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

integrations/claude-code-plugin/skills/redteam/SKILL.md · 49 lines

What it actually says

redteam

Run ryk red-team fixtures and summarize results.

When to use

Use this skill to run deterministic, local-only red-team tests that verify ryk policy behavior without requiring external network access or a real LLM.

Commands

Run the red-team suite in CI mode:

ryk redteam --ci

For JSON output:

ryk redteam --json --ci

What it does

The red-team suite runs synthetic fixtures against ryk policy to check:

  • Command guard behavior (dangerous commands should be blocked)
  • File access controls (protected paths should be denied)
  • Secret redaction (synthetic secrets should be detected)
  • Network policy decisions (suspicious destinations should be flagged)

Requirements

  • No external network access is required.
  • No real LLM is required.
  • A valid .ryk/policy.yaml is recommended but not strictly required; the suite can fall back to built-in presets.

Interpreting results

  • PASS — ryk handled the fixture as expected.
  • FAIL — The fixture behavior differed from expectation. Review the policy or file an issue.
  • SKIP — The fixture was skipped due to platform limitations or missing optional dependencies.

Notes

  • This skill does not modify host configuration.
  • The plugin does not collect telemetry. The documented CI/machine paths are excluded from release CLI telemetry; see docs/telemetry.md.
  • Fixtures use synthetic data only; no real secrets are involved.
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. 3d ago First seen · 49 lines · 0 tokens per session scan A ac33ac8b36c6

Subscribe to this mod's changes

redteam 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 320 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.