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.
/plugin marketplace add Zyrexnn/Cybermesnpx agentmods add plugins/zyrexnn/cybermes/claude-bughuntergit clone --depth 1 https://github.com/Zyrexnn/CybermesWrote 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/zyrexnn/cybermes/claude-bughunter)<a href="https://agentmods.dev/plugins/zyrexnn/cybermes/claude-bughunter"><img src="https://agentmods.dev/badge/plugins/zyrexnn/cybermes/claude-bughunter.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
Claude-BugHunter 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 5d 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.
This is a copy
88% identical to Claude-BugHunter — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
{
"name": "claude-bughunter",
"description": "82-skill bug-hunting & external red-team bundle for Claude Code — 57 hunt-* web/vuln-class + framework skills, enterprise platform attack chains (M365/Entra, Okta, SharePoint, vCenter, SSL-VPN, APK/iOS), recon/OSINT, reporting & validation gates, and Burp MCP integration. Skills auto-load by topic; 15 slash commands included.",
"version": "2.1.0",
"author": {
"name": "Sachin Sharma",
"url": "https://github.com/elementalsouls"
},
"homepage": "https://elementalsouls.github.io/Claude-BugHunter",
"repository": "https://github.com/elementalsouls/Claude-BugHunter",
"license": "MIT"
}
What it installs
The manifest is a name and a version. 11 skills, 15 commands travel with it, and installing the plugin installs all of them — 2,409 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill hunt-ato A 241 tokens
- Skill evidence-hygiene A 190 tokens
- Skill hunt-api-misconfig A 207 tokens
- Skill bugcrowd-reporting A 171 tokens
- Skill hunt-aspnet A 98 tokens
- Skill apk-redteam-pipeline A 145 tokens
- Skill enterprise-vpn-attack A 158 tokens
- Skill cloud-iam-deep B 238 tokens
- Skill bb-methodology C 90 tokens
- Skill bb-local-toolkit F 460 tokens
- Skill bug-bounty F 371 tokens
- Command report A 0 tokens
- Command web3-audit A 0 tokens
- Command recon A 0 tokens
- Command hunt A 0 tokens
- Command token-scan A 0 tokens
- Command autopilot A 0 tokens
- Command validate A 0 tokens
- Command triage A 0 tokens
- Command intel A 0 tokens
- Command scope A 0 tokens
- Command surface A 0 tokens
- Command memory-gc A 40 tokens
- Command pickup A 0 tokens
- Command remember A 0 tokens
- Command chain C 0 tokens
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 13 lines scan A d4754be854e8
Claude-BugHunter is a plugin published in the GitHub repository Zyrexnn/Cybermes (668 stars, last pushed 5d ago), licensed Apache-2.0. 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. It is 88% identical to Claude-BugHunter, differing in 2 lines, and is treated as a copy.
Other plugins, from other repositories
shor
Shor — autonomous AI web pentester. Provides the /shor-setup slash-command: an interactive wizard that guides you from zero to a running scan (black-box or white-box, GCP deployment included).
claude-cybersecurity
AI-powered cybersecurity code review with 8 specialist agents, OWASP Top 10:2021, CWE Top 25:2024, MITRE ATT&CK v15, and framework-aware false-positive suppression.
pentest-ai-agents marketplace
Marketplace for pentest-ai-agents — specialist Claude Code subagents for authorized penetration testing.
web-app-security-skill
Audit and harden authorized Web projects with explainable, reproducible evidence.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.