redteam

redteam is a skill for Claude Code from ondrej-svec/heart-of-gold-toolkit. It costs 61 tokens per session (1,447 once invoked), scanned A, original, MIT.

An adversarial code review that tries to break a project and exposes problems with new failing tests. It checks the design, unfinished placeholder code, security boundaries, and whether the requested work is complete.

In plain words
What is it for?
Use it to probe code for security issues, architectural violations, stubs, missing behavior, and incomplete user stories.
Why use it?
It helps reveal weaknesses that normal implementation checks may miss. It keeps the implementation unchanged so another developer can fix the reported problems.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the marvin plugin — 13 skills, 3 agents, 2 hooks shipped together

Good fit Use it to probe code for security issues, architectural violations, stubs, missing behavior, and incomplete user stories.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ondrej-svec/heart-of-gold-toolkit/redteam
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.

Any agent
npx skills add ondrej-svec/heart-of-gold-toolkit --skill redteam
Clone the repo
git clone --depth 1 https://github.com/ondrej-svec/heart-of-gold-toolkit

Made for: Claude Code.

Or install marvin, the plugin that ships this one along with the rest of its 13 skills, 3 agents, 2 hooks.

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/ondrej-svec/heart-of-gold-toolkit/redteam/github.svg)](https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/redteam)
Your own site
<a href="https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/redteam"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/redteam/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for redteam

Your own site · 80×15
<a href="https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/redteam"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/redteam.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,447 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00061 $0.01447
Opus 5 $0.00030 $0.00724
Sonnet 5 $0.00012 $0.00289
Haiku 4.5 $0.00006 $0.00145

Measured 12d ago against content hash cd851103fa99, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, 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 12d 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.

plugins/marvin/skills/redteam/SKILL.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Red Team

Find weaknesses and expose them with failing tests. You are the adversary — your job is to break things, not fix them.

Boundaries

This skill MAY: read all code, write NEW test files, run tests, grep for patterns. This skill MAY NOT: modify implementation code, modify existing tests, fix bugs, delete files.

NEVER modify implementation. Only EXPOSE problems with new failing tests.

Common Rationalizations

Shortcut Why It Fails The Cost
"Just fix the bug — it's a one-liner" You're the adversary, not the implementer. Fixing undermines the feedback loop The implementer never sees the issue, learns nothing
"Skip architecture check — the code works" Working code with wrong architecture is a time bomb Tech debt accumulates invisibly
"The stubs are fine for now" "For now" becomes "forever" without a failing test to enforce it Stubs ship to production
"Security isn't relevant here" Every input boundary is a security boundary Vulnerabilities ship undetected

Priority 1: Architecture Conformance

Skip if no architecture doc is available.

If $ARCH_PATH is set (pipeline mode): Read the architecture doc. If standalone: Search for *.architecture.md near the source code, or ask.

For each dependency in the architecture doc's Dependencies table:

# Check if the dependency is imported in source files
grep -r "from ['\"]${DEPENDENCY}['\"]" src/ --include="*.ts" --include="*.js"

For each missing import: Write a conformance test that fails:

it("should import ${dependency} (per architecture doc)", () => {
  const source = readFileSync("src/services/${file}", "utf-8");
  expect(source).toMatch(/import.*from\s+['"]${dependency}['"]/);
});

For each integration pattern in the architecture doc:

  • Verify the pattern is followed in source code
  • Write a failing test for any violation

Exit: All architecture violations exposed with failing tests.

Read the full file on GitHub · 202 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 202 lines · 61 tokens per session scan A cd851103fa99

Subscribe to this mod's changes

redteam is a skill published in the GitHub repository ondrej-svec/heart-of-gold-toolkit (19 stars, last pushed 22d ago), licensed MIT. It adds 61 tokens to every session and 1,447 once invoked, about $0.0003 per session on Opus 5. 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.