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/Mikaru0Mystic/sectinelWrote 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/mikaru0mystic/sectinel/anthropic-cybersecurity-skills)<a href="https://agentmods.dev/plugins/mikaru0mystic/sectinel/anthropic-cybersecurity-skills"><img src="https://agentmods.dev/badge/plugins/mikaru0mystic/sectinel/anthropic-cybersecurity-skills/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/mikaru0mystic/sectinel/anthropic-cybersecurity-skills"><img src="https://agentmods.dev/badge/plugins/mikaru0mystic/sectinel/anthropic-cybersecurity-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
cybersecurity-skills 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 10d 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
89% identical to cybersecurity-skills — 4 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": "cybersecurity-skills",
"description": "753 cybersecurity skills covering web security, pentesting, DFIR, threat intelligence, cloud security, malware analysis, and more.",
"version": "1.0.0"
}
What it installs
The manifest is a name and a version. 56 skills travel with it, and installing the plugin installs all of them — 3,391 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill analyzing-indicators-of-compromise A 106 tokens
- Skill analyzing-malware-family-relationships-with-malpedia A 48 tokens
- Skill analyzing-packed-malware-with-upx-unpacker A 79 tokens
- Skill analyzing-certificate-transparency-for-phishing A 39 tokens
- Skill analyzing-browser-forensics-with-hindsight A 53 tokens
- Skill analyzing-campaign-attribution-evidence A 38 tokens
- Skill analyzing-command-and-control-communication A 80 tokens
- Skill analyzing-apt-group-with-mitre-navigator A 48 tokens
- Skill analyzing-bootkit-and-rootkit-samples A 94 tokens
- Skill analyzing-lnk-file-and-jump-list-artifacts A 56 tokens
- Skill analyzing-network-covert-channels-in-malware A 49 tokens
- Skill analyzing-active-directory-acl-abuse A 36 tokens
- Skill analyzing-linux-system-artifacts A 35 tokens
- Skill analyzing-malware-persistence-with-autoruns A 44 tokens
- Skill analyzing-outlook-pst-for-email-forensics A 56 tokens
- Skill analyzing-prefetch-files-for-execution-history A 34 tokens
- Skill analyzing-cloud-storage-access-patterns A 79 tokens
- Skill analyzing-powershell-script-block-logging A 88 tokens
- Skill analyzing-api-gateway-access-logs A 72 tokens
- Skill analyzing-ios-app-security-with-objection A 49 tokens
- Skill analyzing-pdf-malware-with-pdfid A 84 tokens
- Skill analyzing-email-headers-for-phishing-investigation A 44 tokens
- Skill analyzing-malicious-pdf-with-peepdf A 43 tokens
- Skill analyzing-malware-behavior-with-cuckoo-sandbox A 78 tokens
- Skill analyzing-mft-for-deleted-file-recovery A 70 tokens
- Skill analyzing-network-traffic-of-malware A 81 tokens
- Skill analyzing-ransomware-leak-site-intelligence A 46 tokens
- Skill analyzing-azure-activity-logs-for-threats A 68 tokens
- Skill analyzing-kubernetes-audit-logs A 71 tokens
- Skill analyzing-macro-malware-in-office-documents A 90 tokens
- Skill analyzing-cobalt-strike-beacon-configuration A 42 tokens
- Skill analyzing-malicious-url-with-urlscan A 48 tokens
- Skill analyzing-memory-forensics-with-lime-and-volatility A 71 tokens
- Skill analyzing-network-flow-data-with-netflow A 76 tokens
- Skill analyzing-cyber-kill-chain A 99 tokens
- Skill analyzing-dns-logs-for-exfiltration A 73 tokens
- Skill analyzing-golang-malware-with-ghidra A 40 tokens
- Skill analyzing-malware-sandbox-evasion-techniques A 46 tokens
- Skill analyzing-ransomware-encryption-mechanisms A 79 tokens
- Skill analyzing-network-traffic-for-incidents A 91 tokens
- Skill analyzing-network-packets-with-scapy A 39 tokens
- Skill analyzing-linux-elf-malware B 88 tokens
- Skill analyzing-disk-image-with-autopsy B 32 tokens
- Skill analyzing-cobaltstrike-malleable-c2-profiles A 55 tokens
- Skill analyzing-android-malware-with-apktool A 50 tokens
- Skill analyzing-linux-audit-logs-for-intrusion B 93 tokens
- Skill acquiring-disk-image-with-dd-and-dcfldd B 38 tokens
- Skill analyzing-ethereum-smart-contract-vulnerabilities A 49 tokens
- Skill analyzing-network-traffic-with-wireshark B 49 tokens
- Skill analyzing-office365-audit-logs-for-compromise A 46 tokens
- Skill analyzing-heap-spray-exploitation A 46 tokens
- Skill analyzing-powershell-empire-artifacts A 54 tokens
- Skill analyzing-linux-kernel-rootkits B 65 tokens
- Skill analyzing-persistence-mechanisms-in-linux B 50 tokens
- Skill analyzing-memory-dumps-with-volatility C 80 tokens
- Skill analyzing-docker-container-forensics D 34 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.
- 10d ago First seen · 6 lines scan A 50b0805f000c
cybersecurity-skills is a plugin published in the GitHub repository Mikaru0Mystic/sectinel (11 stars, last pushed 2mo 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 89% identical to cybersecurity-skills, differing in 4 lines, and is treated as a copy.
Other plugins, from other repositories
pentest-ai-agents marketplace
Marketplace for pentest-ai-agents — specialist Claude Code subagents for authorized penetration testing.
Claude-BugHunter
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 in.
appsec-advisor
Code-derived threat modeling plugin: the architecture model is derived from the repository, not maintained by hand. Provides AppSec-focused agents and skills for threat modeling, STRIDE analysis, dependency scanning, QA review, and security context resolution.
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…
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.