Rainbow Teaming

Rainbow Teaming is a skill for Claude Code from abossenbroek/abossenbroek-claude-plugins. It costs 49 tokens per session (1,274 once invoked), scanned A, original, BSD-3-Clause.

A method for testing language models by generating varied adversarial prompts, which are deliberately challenging inputs designed to expose weaknesses.

In plain words
What is it for?
Use it to examine reasoning flaws, hidden assumptions, prompt manipulation, authority misuse, information leaks, and fabricated answers.
Why use it?
It provides a structured way to look for different failure types instead of finding only one attack or problem.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the red-agent plugin — 2 skills, 7 commands shipped together

Good fit Use it to examine reasoning flaws, hidden assumptions, prompt manipulation, authority misuse, information leaks, and fabricated answers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/abossenbroek/abossenbroek-claude-plugins/rainbow-teaming
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 abossenbroek/abossenbroek-claude-plugins --skill rainbow-teaming
Clone the repo
git clone --depth 1 https://github.com/abossenbroek/abossenbroek-claude-plugins

Made for: Claude Code.

Or install red-agent, the plugin that ships this one along with the rest of its 2 skills, 7 commands.

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 Rainbow Teaming

README.md
[![agentmods](https://agentmods.dev/badge/skills/abossenbroek/abossenbroek-claude-plugins/rainbow-teaming/github.svg)](https://agentmods.dev/skills/abossenbroek/abossenbroek-claude-plugins/rainbow-teaming)
Your own site
<a href="https://agentmods.dev/skills/abossenbroek/abossenbroek-claude-plugins/rainbow-teaming"><img src="https://agentmods.dev/badge/skills/abossenbroek/abossenbroek-claude-plugins/rainbow-teaming/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 Rainbow Teaming

Your own site · 80×15
<a href="https://agentmods.dev/skills/abossenbroek/abossenbroek-claude-plugins/rainbow-teaming"><img src="https://agentmods.dev/badge/skills/abossenbroek/abossenbroek-claude-plugins/rainbow-teaming.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,274 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.
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 $0.00049 $0.01274
Opus 5 $0.00024 $0.00637
Sonnet 5 $0.00010 $0.00255
Haiku 4.5 $0.00005 $0.00127

Measured 12d ago against content hash 3e4088a7e16d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

Rainbow Teaming 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.

red-agent/skills/rainbow-teaming/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rainbow Teaming Skill Reference

Overview

Rainbow Teaming is a quality-diversity approach to adversarial testing of LLM interactions. Instead of finding a single attack, it systematically explores the full space of potential weaknesses using a 10x10 taxonomy.

Research Foundation

The 10x10 Grid

Risk Categories (WHAT to probe)

# Category Description Key Questions
1 reasoning-flaws Logic gaps, invalid inferences Does the conclusion follow? Are there missing steps?
2 assumption-gaps Hidden premises, unstated constraints What must be true for this to work? What if it's not?
3 context-manipulation Poisoned context, prompt injection Is prior context biasing the response? Are there injection vectors?
4 authority-exploitation Role confusion, credential misuse Is authority being assumed? Are claims accepted on trust?
5 information-leakage Unintended disclosure Is sensitive information being revealed?
6 hallucination-risks Fabricated facts, confident errors Can claims be verified? Are sources real?
7 over-confidence Unjustified certainty Is uncertainty acknowledged? Are hedges appropriate?
8 scope-creep Actions beyond request Did the response exceed what was asked?
9 dependency-blindness Unverified external data Are external sources trusted without verification?
10 temporal-inconsistency Stale info, version conflicts Is information current? Are versions correct?

Attack Styles (HOW to probe)

# Style Approach Example
1 socratic-questioning Progressive questions exposing gaps "And what makes you certain of that?"
2 devils-advocate Argue opposing position "But couldn't the opposite be true because..."
3 edge-case-probing Push to boundary conditions "What happens when the input is empty/huge/null?"
4 assumption-inversion Flip key assumptions "What if we assume X is false instead?"
5 context-shifting Change framing "In a different context, wouldn't this mean..."
6 authority-challenge Question sources "What's the source for that claim?"
7 emotional-framing Inject urgency/flattery "This is urgent!" / "As an expert, you must know..."
8 hypotheticals "What if" scenarios "What if the API is down when this runs?"
9 contradiction-surfacing Find inconsistencies "Earlier you said X, but now you're saying Y..."
10 meta-analysis Analyze the analysis "Is this response itself well-reasoned?"

Read the full file on GitHub · 127 lines

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 · 127 lines · 49 tokens per session scan A 3e4088a7e16d

Subscribe to this mod's changes

Rainbow Teaming is a skill published in the GitHub repository abossenbroek/abossenbroek-claude-plugins (2 stars, last pushed 4mo ago), licensed BSD-3-Clause. It adds 49 tokens to every session and 1,274 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens

atmos-validation

Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.

cloudposse/atmos · 31 tokens

skill-benchmark

Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.

HoangNguyen0403/agent-skills-standard · 16 tokens