Directory · Subagents

pentest-ai-agents

50 Claude Code subagents turning Claude into an offensive security research assistant for authorized penetration testing.

★ 2,330 stars · last updated 2026-10-06 · Free, open source · View on GitHub

Best for

• Authorized penetration testing and red team engagements
• Recon, exploit research, and AD/cloud/web testing
• Detection engineering and pentest reporting

Install

curl -fsSL https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/install.sh | bash

Or as a plugin:
/plugin marketplace add 0xSteph/pentest-ai-agents
/plugin install pentest-ai-agents@pentest-ai-agents

Our take

Installs as plain agent files or a Claude Code plugin, with no servers or Python dependencies beyond copying files. Tier 2 execution-capable agents require a declared scope and include a scope-guard block with hard refusals for DoS, mass scanning, and similar abuse. Includes a SQLite findings database, slash commands, and optional installers for underlying CLI tools; intended strictly for authorized testing.

Similar subagents

• Awesome Claude Code Subagents (VoltAgent): A curated collection of 161+ Claude Code subagent definitions across 10 categories, installable as plugins or individual agent files.
• claude-devtools: Desktop and web app that reads local Claude Code session logs to show tool calls, token usage, subagent trees, and context.
• AI Marketing Suite for Claude Code: Claude Code skills and parallel subagents for marketing audits, copywriting, email sequences, ad copy, and client-ready reports.
• Translate Book: Agent skill for Claude Code, Codex, and OpenClaw that translates whole PDF/DOCX/EPUB books using parallel subagents per chunk.
• Claude Code Sub-Agents (lst97): A collection of 33 specialized Claude Code subagents for full-stack development, plus an agent-organizer for multi-agent orchestration.
• pi-subagents: Pi extension adding Claude Code-style sub-agents, parallel background runs, mid-run steering, and scripted multi-agent workflows.