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.
npx skills add LuuOW/meridian-mcp --skill port-scannergit clone --depth 1 https://github.com/LuuOW/meridian-mcpWrote 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/skills/luuow/meridian-mcp/port-scanner)<a href="https://agentmods.dev/skills/luuow/meridian-mcp/port-scanner"><img src="https://agentmods.dev/badge/skills/luuow/meridian-mcp/port-scanner/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/skills/luuow/meridian-mcp/port-scanner"><img src="https://agentmods.dev/badge/skills/luuow/meridian-mcp/port-scanner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00028 | $0.01075 |
| Opus 5 | $0.00014 | $0.00537 |
| Sonnet 5 | $0.00006 | $0.00215 |
| Haiku 4.5 | $0.00003 | $0.00108 |
Grade B, and why
port-scanner scanned grade B with 1 finding 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 8d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo nmap -O -sV target-ip How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
port-scanner
Targeted nmap and masscan patterns for validating firewall posture, discovering open services, and fingerprinting what is actually exposed on a host. Use after provisioning a VPS to confirm only intended ports are reachable.
1) Common nmap Recipes
# Quick scan — top 1000 TCP ports
nmap -F target-ip
# All TCP ports
nmap -p- target-ip
# With service version detection
nmap -sV -p 22,80,443,8080 target-ip
# OS detection + service version (requires root)
sudo nmap -O -sV target-ip
# Aggressive scan (OS, version, scripts, traceroute)
sudo nmap -A target-ip
# Scan a subnet
nmap -sn 192.168.1.0/24 # ping sweep (no port scan)
nmap 192.168.1.0/24 # port scan all hosts
# UDP scan (slow — limit to key ports)
sudo nmap -sU -p 53,123,161 target-ip
# Save output
nmap -oN scan.txt target-ip # normal
nmap -oG scan.grep target-ip # greppable
nmap -oX scan.xml target-ip # XML (for scripted parsing)
2) Firewall Validation
# Confirm only expected ports open from the outside
# Run from a different machine, not localhost
nmap -p 22,80,443 your-vps-ip
# Verify internal ports are NOT reachable from outside
# These should all show filtered:
nmap -p 5432,6379,9002,8080 your-vps-ip
# Check if a specific port is filtered vs closed
nmap -p 3306 --reason your-vps-ip
# "filtered" = firewall dropping packets (good)
# "closed" = no firewall, just nothing listening (less good)
3) masscan (High-Speed)
# Install
apt install masscan
# Scan entire internet space on port 80 (rate-limited)
sudo masscan -p80 0.0.0.0/0 --rate=100000 --exclude 255.255.255.255
# Scan a range quickly
sudo masscan -p22,80,443 192.168.1.0/24 --rate=1000
# Output to JSON
sudo masscan -p80,443 10.0.0.0/8 --rate=500 -oJ output.json
4) nmap Scripting Engine (NSE)
# Check for known vulnerabilities
nmap --script vuln target-ip
# HTTP title and server header
nmap --script http-title,http-server-header -p 80,443,8080 target-ip
# Check SSL cert details
nmap --script ssl-cert -p 443 target-ip
# Detect open proxies
nmap --script http-open-proxy -p 8080 target-ip
# Banner grabbing
nmap --script banner -p 22,25,110 target-ip
# SSH auth methods
nmap --script ssh-auth-methods -p 22 target-ip
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.
- 8d ago First seen · 122 lines · 28 tokens per session scan B ff3483f212d4
port-scanner is a skill published in the GitHub repository LuuOW/meridian-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 1,075 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
Reconnaissance & OSINT Automation
Passive and active reconnaissance, subdomain enumeration, DNS analysis, technology fingerprinting, and OSINT data correlation for authorized security assessments.
port-mass-scan
Port scan /8-/24 with Masscan+RustScan and nmap banners.
edgeone skill scanner
A local static scanner that checks agent-skill files for security risks before they are installed or used. Static analysis examines files without running them.
human-agent-trust-exploit-detection
Detect social engineering, deceptive responses, false assurances, or prompts that induce unsafe user actions.
owasp-asi
OWASP Top 10 for Agentic Applications 2026 (ASI) classification framework. Use for mapping security findings to standardized risk categories.
inter-agent-comm-security-detection
Detect data leakage, missing boundaries, or privilege mismatch in inter-agent communication.