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 CarbeneAI/Forge --skill naabugit clone --depth 1 https://github.com/CarbeneAI/ForgeWrote 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/carbeneai/forge/naabu)<a href="https://agentmods.dev/skills/carbeneai/forge/naabu"><img src="https://agentmods.dev/badge/skills/carbeneai/forge/naabu.svg" alt="Measured on agentmods" 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 | $0.00048 | $0.00727 |
| Opus 5 | $0.00024 | $0.00364 |
| Sonnet 5 | $0.00010 | $0.00145 |
| Haiku 4.5 | $0.00005 | $0.00073 |
Grade A, and why
Naabu 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Naabu
Fast port scanner powered by ProjectDiscovery's naabu. Runs locally via MCP server wrapper around the naabu binary.
Capabilities
- TCP SYN/CONNECT port scanning
- Top 100/1000 port presets (nmap-compatible)
- CIDR range scanning
- JSON Lines output for structured results
- Passive scanning via Shodan InternetDB (no packets sent)
- Service version detection (via nmap passthrough)
Workflow Routing
| Action | Trigger | Behavior |
|---|---|---|
| Scan Ports | "scan ports on", "check open ports", "port scan" | Run naabu against target |
| Quick Scan | "quick scan", "top ports" | Scan top 100 ports |
| Full Scan | "full port scan", "all ports" | Scan all 65535 ports |
| Passive Scan | "passive scan", "no packets" | Use Shodan InternetDB |
Examples
Example 1: Scan top ports on a host
User: "Scan the top ports on example.com"
→ naabu -host example.com -top-ports 100 -json -silent
→ Returns JSON list of open ports
Example 2: Scan specific ports on a subnet
User: "Check if SSH and HTTP are open on 192.168.1.0/24"
→ naabu -host 192.168.1.0/24 -p 22,80,443 -json -silent
→ Returns open port findings per host
Example 3: Passive recon (no packets)
User: "Do a passive port scan on example.com"
→ naabu -host example.com -passive -json -silent
→ Returns known open ports from InternetDB without sending packets
CLI Reference
# Key flags
naabu -host <target> # Single host, IP, or CIDR
naabu -list <file> # File with targets (one per line)
naabu -p 22,80,443 # Specific ports
naabu -top-ports 100 # Top 100 or 1000 ports
naabu -json # JSON Lines output
naabu -silent # Suppress banner/info
naabu -passive # Shodan InternetDB lookup (no packets)
naabu -Pn # Skip host discovery
naabu -rate 1000 # Packets per second
naabu -o results.jsonl # Output to file
What ships with it
4 files beside SKILL.md 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.
- 4d ago First seen · 83 lines · 48 tokens per session scan A 0b9f8c0445dd
Naabu is a skill published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 727 once invoked, about $0.0002 per session on Opus 5. 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 2026-09-03.
Other skills, from other repositories
ot-iot-device-security
../../../cloud-infra/ot-iot-device-security/SKILL.md.
firmware
Router / IoT firmware extraction pipeline — unpack nested filesystems, locate web server, identify backdoor credentials.
s7comm
Siemens S7 PLC attack — TCP/102 ISO-TP+S7-COMM, snap7 / python-snap7 enumeration, DB/M/E/A area read+write, PLC stop/start/run, password bypass (S7-300/400 vs S7-1200/1500 differences), CVE chain (e.g., Stuxnet's legacy primitives, CVE-2019-10936).
ics-ot
ICS / OT attack category — Modbus, BACnet, S7Comm, DNP3. Routing skill: fingerprint the industrial protocol by port + Wireshark dissector, then load the matching sub-skill. SAFETY-CRITICAL: always confirm written scope before any write/control class action.
dnp3
DNP3 attack — TCP/20000 (or 19999 serial-over-TCP) outstation enumeration, binary input / analog input poll, control relay output block (CROB) actuation, unsolicited reporting abuse, DNP3 Secure Authentication (DNP3-SA) downgrade, vendor-specific objects.
modbus
Modbus TCP attack — port 502 enumeration, coil/holding-register read/write without auth, function-code abuse (FC8 diagnostic, FC43 read-device-id), Modbus-over-Serial via TCP gateway, write-with-no-confirm DoS, value tampering against PLCs.