Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/Stickman230/claude-pentestWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/stickman230/claude-pentest/pentest)<a href="https://agentmods.dev/plugins/stickman230/claude-pentest/pentest"><img src="https://agentmods.dev/badge/plugins/stickman230/claude-pentest/pentest/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/stickman230/claude-pentest/pentest"><img src="https://agentmods.dev/badge/plugins/stickman230/claude-pentest/pentest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
pentest scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "pentest",
"version": "2.2.6",
"description": "Full penetration testing framework - 63 attack categories across 11 domains covering OWASP, injection, authentication, cloud, and more",
"author": {
"name": "Stickman230",
"url": "https://github.com/Stickman230"
},
"repository": "https://github.com/Stickman230/claude-pentest",
"license": "MIT"
}
What it installs
The manifest is a name and a version. 7 skills, 5 commands, 15 agents travel with it, and installing the plugin installs all of them — 1,551 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill mks A 54 tokens
- Skill pentest A 50 tokens
- Skill authenticating A 54 tokens
- Skill common-appsec-patterns A 42 tokens
- Skill web-application-mapping A 38 tokens
- Skill cve-testing A 36 tokens
- Skill domain-assessment A 23 tokens
- Command pentest A 58 tokens
- Command pentest-attacks A 60 tokens
- Command pentest-scope A 51 tokens
- Command pentest-kali A 43 tokens
- Command pentest-exit A 26 tokens
- Agent Pentester Executor A 37 tokens
- Agent Pentester Orchestrator A 75 tokens
- Agent csp-bypass-tester A 78 tokens
- Agent injection-tester A 60 tokens
- Agent inventory-api-discovery A 76 tokens
- Agent inventory-javascript-mapper A 80 tokens
- Agent prototype-pollution-tester A 60 tokens
- Agent domain-assessment A 60 tokens
- Agent inventory-directory-scanner A 73 tokens
- Agent inventory-software-catalog A 71 tokens
- Agent inventory-surface-analyzer A 89 tokens
- Agent xss-tester A 86 tokens
- Agent cve-tester A 57 tokens
- Agent patt-fetcher A 58 tokens
- Agent csrf-tester B 56 tokens
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 12 lines scan A 647a3e0e11ad
pentest is a plugin published in the GitHub repository Stickman230/claude-pentest (119 stars, last pushed 4mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other plugins, from other repositories
tsm
Touch-ID-gated secrets for AI coding agents. Provides safe credential injection for tools and MCP servers.
cybersecurity-pro
Professional cybersecurity skill: 22 domains covering IR, DFIR, DevSecOps, SOC+SOAR, GitOps, Code Security, Container/Supply Chain, Threat Modeling, Compliance Frameworks, Cloud Security & CSPM, Zero Trust Architecture, AI/ML Security, API Security, Vulnerability Management, Threat Intelligence, Cross-Domain…
tyrell
Tyrell — leak database hunter plugin with Hexstrike MCP integration for Kali Linux. Exposed database discovery, data acquisition, cross-plugin pipeline to elliot.
fsociety
fsociety — engagement workspace setup and cross-plugin orchestration. Interactive /setup wizard for targets, goals, scope, and plugin selection.
blackbox-htb
Black-box and grey-box penetration testing plugin for HackTheBox machine challenges. Provides automated reconnaissance, enumeration, exploitation guidance, and privilege escalation for Linux, Windows, and Active Directory environments.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.