Red Team

Red Team is an AI Engineering skill for Claude Code, published by gaasher in Agent-Loop-Skills.

166 stars19 forkson gaasher/Agent-Loop-SkillsAdded 2026/09/08+2% in starsRepository updated 2026/06/30

agent-skillsagentic-loopsagentic-workflowsai-agentsanthropicautoresearchclaudeclaude-codedata-analysisliterature-reviewllm-agentsmachine-learningml-autoresearchopen-sourceprompt-engineeringred-teamingscientific-writingskillssubagents

Install in seconds

Install Red Team

Copy Red Team into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/red-team ~/.claude/skills/red-team

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/gaasher/Agent-Loop-Skills.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: loops/red-team/SKILL.md in gaasher/Agent-Loop-Skills
Installs to: ~/.claude/skills/red-team
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 3670 skills

What Red Team does

Red Team stress-tests a guardrail, classifier, prompt, or API you own or are authorized to test. It generates adversarial inputs, compares target results against an oracle, and catalogues distinct failure classes with reproducible examples.

Red Team is cataloged under AI Engineering on DirSkills. Red Team comes from a repository tagged agent-skills, agentic-loops, agentic-workflows, ai-agents and anthropic.

Documentation

README

Excerpt

Red Team

An adversarial loop-until-dry. The artifact is a target system; the feedback signal is the count of distinct failure classes you can surface. Each round you craft adversarial inputs aimed at new weaknesses and run them through the target and a ground-truth oracle via tools/harness.py, which records every disagreement as a failure and de-dupes by the class (technique) you label each input with. You loop until fresh rounds stop finding anything new. This is only the find half of a find→fix setup: it catalogues failures and never patches the target (see Pairing).

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Red Team

What else does gaasher publish alongside Red Team?
Red Team is one of 25 skills that DirSkills catalogs from gaasher/Agent-Loop-Skills, the repository it ships in. Its siblings there include Alpha Evolve, Anomaly Investigation and Blue Team. Each one is a separate skill with its own page in this directory, installs the same way Red Team does, and is maintained by gaasher in that same repository. The rest of the collection is listed on the gaasher/Agent-Loop-Skills page.
How does Red Team compare to other AI Engineering skills?
Red Team ranks #3346 by stars among the 3670 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Red Team against them. Open each page to compare what they document and how they install.