active-recon

active-recon is a skill for Claude Code from MingyiSecLab/Mingyi-Atlas. It costs 30 tokens per session (3,881 once invoked), scanned C, original, Apache-2.0.

A collection of methods for actively checking target systems by sending network requests, scanning ports, identifying services and testing web paths and known weaknesses.

In plain words
What is it for?
Use it for port and service scans, UDP checks, web-directory discovery, banner and TLS checks, and vulnerability scans.
Why use it?
It helps reveal which services are reachable and where a target may have exposed or outdated components, while noting that scans can be detected.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it for port and service scans, UDP checks, web-directory discovery, banner and TLS checks, and vulnerability scans.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mingyiseclab/mingyi-atlas/active-recon
Install

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.

Any agent
npx skills add MingyiSecLab/Mingyi-Atlas --skill active-recon
Clone the repo
git clone --depth 1 https://github.com/MingyiSecLab/Mingyi-Atlas

Made for: Claude Code.

Wrote 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.

agentmods badge for active-recon

README.md
[![agentmods](https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/active-recon/github.svg)](https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/active-recon)
Your own site
<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/active-recon"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/active-recon/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.

agentmods 80×15 button for active-recon

Your own site · 80×15
<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/active-recon"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/active-recon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,881 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.03881
Opus 5 $0.00015 $0.01940
Sonnet 5 $0.00006 $0.00776
Haiku 4.5 $0.00003 $0.00388

Measured 9d ago against content hash 4a36b5021b8e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade C, and why

active-recon scanned grade C with 2 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 9d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -s http://<target>:9200/ | python3 -m json.tool

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

### curl for HTTP Services
src/skills/standard/recon/active-recon/SKILL.md · 400 lines

How it starts

The opening of the file, as written. The whole thing — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Active Reconnaissance Knowledge Base

Active reconnaissance directly interacts with target systems. Every packet sent may be logged, detected, or trigger alerts. Use active techniques only after passive reconnaissance has identified specific targets that warrant further investigation.

Quick Reference — Common Scan Patterns

# Stealth SYN scan with version detection (recommended starting point)
nmap -sS -sV -p 22,80,443,8080,8443 <TARGET> -oN nmap_<TARGET>.txt -oX nmap_<TARGET>.xml

# Full top-1000 port scan
nmap -sS -sV --top-ports 1000 -T2 <TARGET> -oN nmap_full_<TARGET>.txt

# Script enumeration on discovered ports
nmap -sC -sV -p <PORTS> <TARGET> -oN nmap_scripts_<TARGET>.txt

# UDP scan (DNS, SNMP, NTP)
nmap -sU -p 53,161,123 <TARGET> -oN nmap_udp_<TARGET>.txt

# Web directory fuzzing
ffuf -u https://<TARGET>/FUZZ -w /usr/share/wordlists/dirb/common.txt -mc 200,301,302,403 -o ffuf_<TARGET>.json

# Vulnerability scan
nuclei -u https://<TARGET> -severity critical,high -o nuclei_<TARGET>.txt

1. OPSEC Principles for Active Scanning

Detection Avoidance

  • Never scan entire ranges blindly — target specific IPs/ports identified during passive recon
  • Rate limiting: Slow scans blend with normal traffic; fast scans trigger IDS/IPS
  • Timing: Scan during business hours when traffic volume provides cover
  • Source management: Be aware your sandbox IP is the scan origin
  • User-Agent rotation: Vary HTTP user agents for web scanning tools

Scan Justification

Before every active scan, document:

  1. What you're scanning and why
  2. What passive intel led to this decision
  3. Expected noise level and detection risk

2. Port Scanning with Nmap

Stealth SYN Scan (Default for Recon)

# Targeted port scan — specific ports from passive findings
nmap -sS -p 22,80,443,8080,8443 <target_ip>

# Top 1000 ports with service detection
nmap -sS -sV --top-ports 1000 <target_ip>

# Full 65535 port scan (slow, use only when justified)
nmap -sS -p- --min-rate 1000 <target_ip>

# Save results
nmap -sS -sV -p 22,80,443 <target_ip> -oN nmap_scan.txt -oX nmap_scan.xml

Read the full file on GitHub · 400 lines

Changes

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.

  1. 9d ago First seen · 400 lines · 30 tokens per session scan C 4a36b5021b8e

Subscribe to this mod's changes

active-recon is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 3,881 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.