Agent skill · security · aradotso
pentestcode-ai-pentest-agent
AI-powered penetration testing agent with multi-agent architecture, engagement state tracking, and autonomous security testing
Why this skill is useful
Adds executable scripts for automated penetration testing workflows and multi-agent coordination that aren't widely available in public documentation.
What it needs
Requires bun installed locally. Requires anthropic, aws, azure, deepseek, fireworks, google, groq, mistral, ollama, openai, together account access. About 8k tokens when loaded. Last updated 2026-08-04. 11 stars on the source repository.
What this skill does
PentestCode AI Pentest Agent Skill by ara.so — Security Skills collection. PentestCode is an AI penetration testing agent that runs in your terminal with a multi-agent architecture. It maintains persistent engagement state, coordinates 13 specialized security agents, and automates reconnaissance through post-exploitation workflows. Built on TypeScript with Effect library. Installation Authentication & Configuration Example configuration: Supported providers: Anthropic, OpenAI, Google, Azure, AWS Bedrock, Ollama, Together, Groq, Fireworks, DeepSeek, Mistral. Core Usage Patterns Interactive Session One-Shot Execution CTF Mode Slash Commands Multi-Agent Architecture PentestCode uses 13 specialized agents coordinated by a strategist: Agents spawn in parallel and share engagement state: Built-in Tools Parser Tools (Mandatory Usage) Analysis Tools Tactical Tools State Management Tools Engagement State Structure The engagement state persists at .pentestcode/state.json: Real Workflow Example Skills System PentestCode loads knowledge packs on demand: Add custom skills by creating SKILLNAME.md: Skills are plain markdown — no code changes needed. Mode-Specific Patterns Auto Mode (Autonomous) Free Mode (Unrestricted) Guided Mode (Step-by-Step) Troubleshooting High Token Usage Agent Loops / Repeats Work Parser Failures Missing Dependencies Scope Violations Environment Variables Integration Patterns With Existing Tools With CI/CD Programmatic State Access Performance Optimization License MIT License - See project LICENSE file for details.
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/pentestcode-ai-pentest-agent