pentest-ai-agents
Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized penetration testing plan engagements, analyze recon, r
What is pentest-ai-agents?
Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized penetration testing plan engagements, analyze recon, research exploits, build detections, audit STIGs, and write reports.
Overview of pentest-ai-agents
What it is
pentest-ai-agents is a collection of 50 Claude Code subagents that turn Claude into an offensive security research assistant. Each agent carries deep domain knowledge in specific areas such as recon, web, Active Directory, cloud, mobile, wireless, social engineering, payload crafting, reverse engineering, exploit chaining, detection engineering, forensics, and more. No servers, no Python dependencies, no setup beyond copying files.
Key features
- 50 specialized subagents covering recon, web, AD, cloud, mobile, wireless, social engineering, payload crafting, reverse engineering, exploit chaining, detection engineering, forensics, and more.
- Installable as a Claude Code plugin with two commands or via a one-line curl installer.
- No servers, no Python dependencies, no setup beyond copying files.
- Scope-guard mechanism on execution-capable agents to enforce authorized boundaries.
- Findings database with version 2 supporting filtering by tool and indexes on CVE and tool_used.
- Slash commands: /recommend routes tasks to the right agent, /agents-for filters catalog by domain.
- Hardened CI validator that validates agent frontmatter, scope-guard blocks, plugin manifests, and smoke-tests installer.
Use cases
- Authorized penetration testing engagements: plan, recon, exploit, post-exploitation, detection, and reporting.
- Security research: analyze recon data, research exploits, build detections, audit STIGs, write reports.
- Offensive security training and CTF solving.
- Red team operations with C2 profile tuning, container breakout, opsec anonymization, and LLM red teaming.
Getting started
One command install: bash curl -fsSL https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/install.sh | bash Or install as a Claude Code plugin: /plugin marketplace add 0xSteph/pentest-ai-agents /plugin install pentest-ai-agents@pentest-ai-agents Then open Claude Code and describe a task. Claude routes to the appropriate agent.
License and pricing
Licensed under MIT. Open source (free).
Based on the project's public README and repository metadata.
