Claude Skill

gadievron/raptor

Raptor transforms Claude Code into an AI security agent using Claude.md. Create rules, sub-agents, and skills to orchestrate security tools for adversarial research, attack, and defense operations.

Overview

Stars1,021
Forks121
LanguagePython
Last pushed2026-01-23
Last synced2026-06-04
View on GitHub

Repository

Ownergadievron
Repositoryraptor
Full namegadievron/raptor
Repo ID1,078,171,437

Install this Skill

git clone https://github.com/gadievron/raptor.git

Registry

Typecursor_rule
Quality score85/100
Verificationreadme_parsed
Last verified2026-06-04
Platforms
ClaudeCursor
Capabilities
browsercode-reviewpdfmemorysearchimageterminalworkflow
Detected files
README.mddocsrequirements.txttest
Config keys
ANTHROPIC_API_KEYOPENAI_API_KEYGEMINI_API_KEYMISTRAL_API_KEY
Install methods
  • git clone https://github.com/gadievron/raptor.git
  • pip install -r requirements.txt
  • npm install -g @anthropic-ai/claude-code
  • pip install semgrep
  • docker run --privileged -it raptor:latest

Summary

Raptor is a Python-based Claude Skill that transforms Claude Code into a general-purpose AI security agent for offensive and defensive operations. It utilizes Claude.md to create rules, sub-agents, and skills, orchestrating security tools to enable adversarial thinking and execute research or attack/defense tasks.

Chinese description

Raptor将Claude Code转变为通用型AI攻防安全代理。通过运用Claude.md并创建规则、子代理与技能,协调安全工具的使用,我们配置该代理具备对抗性思维,以执行研究或攻防操作。

Key features

  • Transforms Claude Code into a security-focused AI agent
  • Uses Claude.md for rule, sub-agent, and skill creation
  • Orchestrates security tool usage for coordinated operations
  • Configurable for adversarial thinking and security research
  • Supports both offensive and defensive security operations

Use cases

  • Security research and threat analysis
  • Penetration testing and red team exercises
  • Defensive security monitoring and response
  • Adversarial simulation and attack modeling
  • Security tool orchestration and automation

README excerpt

```text ╔═══════════════════════════════════════════════════════════════════════════╗ ║ ║ ║ ██████╗ █████╗ ██████╗ ████████╗ ██████╗ ██████╗ ║ ║ ██╔══██╗██╔══██╗██╔══██╗╚══██╔══╝██╔═══██╗██╔══██╗ ║ ║ ██████╔╝███████║██████╔╝ ██║ ██║ ██║██████╔╝ ║ ║ ██╔══██╗██╔══██║██╔═══╝ ██║ ██║ ██║██╔══██╗ ║ ║ ██║ ██║██║ ██║██║ ██║ ╚██████╔╝██║ ██║ ║ ║ ╚═╝ ╚═╝╚═╝ ╚═╝╚═╝ ╚═╝ ╚═════╝ ╚═╝ ╚═╝ ║ ║ ║ ║ Autonomous Offensive/Defensive Research Framework ║ ║ Based on Claude Code (v3.0.0) ║ ║ ║ ║ Gadi Evron, Daniel Cuthbert, Thomas Dullien (Halvar Flake) ║ ║ Michael Bargury, John Cartwright ║ ║ ║ ╚═══════════════════════════════════════════════════════════════════════════╝ ⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢀⣠⣤⣤⣀⣀ ⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⣾⣿⣿⠿⠿⠟ ⠀⠀⠀⠀⠀⠀⠀⠀⢀⣀⣀⣀⣀⣀⣀⣤⣴⣶⣶⣶⣤⣿⡿⠁⠀⠀⠀ ⣀⠤⠴⠒⠒⠛⠛⠛⠛⠛⠿⢿⣿⣿⣿⣿⣿⣿⣿⣿⣿⠟⠁⠀⠀⠀⠀ ⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠉⠛⣿⣿⣿⡟⠻⢿⡀⠀⠀⠀⠀⠀ ⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢀⣾⢿⣿⠟⠀⠸⣊⡽⠀⠀⠀⠀⠀ ⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢸⡇⣿⡁⠀⠀⠀⠉⠁⠀⠀⠀⠀⠀ ⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠈⠻⠿⣿⣧⠀ Get them bugs.....⠀⠀⠀⠀⠀ ``` <a href="https://smithery.ai/skills?ns=gadievron&utm_source=github&utm_medium=badge"><img src="https://smithery.ai/badge/skills/gadievron"></a> <a href="https://github.com/gadievron/raptor/actions/workflows/github-code-scanning/codeql"><img src="https://github.com/gadievron/raptor/actions/workflo

Topics

No topics yet.

Explore more

Data from GitHub. Synced on 2026-06-04