Claude-Red

Claude-Red is a library of offensive security skills that teaches Claude red team methods for authorized security testing.

What it is good for

  • Guiding an AI through authorized penetration testing steps
  • Preparing for capture-the-flag security competitions
  • Triaging bug bounty reports on web applications
  • Learning attack techniques across web, cloud, and network systems

At a glance

Who it is for
Setup
Adds to an AI app you already use

Level 2 of 5. Connects to Claude, ChatGPT, or a similar app you already have, usually through a settings screen.

Cost
Free and open source
Type
Skill or plugin
Tasks
Works with
Claude, Claude Code, Claude.ai

Momentum

Rank this week
Not ranked (last #57, week 43, 2026)
Best rank
#57 week 43, 2026
GitHub stars
10,226

GitHub numbers as of Nov 2, 2026. Updated weekly.

6,488 8,496 10.5k Sep 24, 2026 Nov 2, 2026
GitHub stars for Claude-Red: 6,765 on Sep 24, 2026, 10,226 on Nov 2, 2026. Source: GitHub.

Ranking history

First ranked in week 43, 2026.

Questions

Is Claude-Red free?
Yes. It is free and open source (MIT license).
Do I need to know how to code to use Claude-Red?
No. Connects to Claude, ChatGPT, or a similar app you already have, usually through a settings screen.
What does Claude-Red work with?
According to its own documentation, it works with Claude, Claude Code, and Claude.ai.
What is Claude-Red good for?
Guiding an AI through authorized penetration testing steps, preparing for capture-the-flag security competitions, triaging bug bounty reports on web applications, and learning attack techniques across web, cloud, and network systems.

Similar agents to Claude-Red

  • Agent Reach

    Agent Reach is a command-line tool that lets an AI agent read and search login-only and Chinese platforms like Bilibili, Xiaohongshu, and Twitter for people who need that content.

  • Understand-Anything

    Understand-Anything is a plugin that turns a codebase, knowledge base, or docs into an interactive graph you can explore and ask questions about, for people new to a project.

  • Scientific Agent Skills

    Scientific Agent Skills is a collection of 177 skills that teaches an AI agent scientific tools and databases for research work.

  • Vane

    Vane is a self-hosted AI answering engine that searches the web and gives cited answers for people who want private searches.

  • book-to-skill

    book-to-skill is a skill that turns a technical book PDF into a structured skill your AI agent can search chapter by chapter, for people who want to reuse a book's content while they work.

  • Anthropic-Cybersecurity-Skills

    Anthropic-Cybersecurity-Skills is a set of 817 security skill files that teach AI agents how to run security investigations and assessments for security teams.

Last updated Nov 2, 2026. Tracked since Oct 28, 2026. The summary was written by an AI model from the project's own description and checked against our copy rules. Spotted an error? Tell us.