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 tikoci/routeros-skills --skill routeros-scriptinggit clone --depth 1 https://github.com/tikoci/routeros-skillsWrote 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/tikoci/routeros-skills/routeros-scripting)<a href="https://agentmods.dev/skills/tikoci/routeros-skills/routeros-scripting"><img src="https://agentmods.dev/badge/skills/tikoci/routeros-skills/routeros-scripting/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/tikoci/routeros-skills/routeros-scripting"><img src="https://agentmods.dev/badge/skills/tikoci/routeros-skills/routeros-scripting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00090 | $0.01874 |
| Opus 5 | $0.00045 | $0.00937 |
| Sonnet 5 | $0.00018 | $0.00375 |
| Haiku 4.5 | $0.00009 | $0.00187 |
Grade A, and why
routeros-scripting 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 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.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- routeros-scripting — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RouterOS Scripting & CLI Config
RouterOS scripts (.rsc, /system/script, scheduler on-event, Netwatch hooks, and
interactive CLI snippets) use RouterOS's own language. It is not shell, Lua, Python,
or Tcl. For the syntax baseline, see references/syntax.md.
This skill focuses on the traps that LLMs are likely to confidently get wrong.
Do Not Use Interactive Row Numbers in Scripts
Interactive print output shows temporary row numbers (0, 1, 2...) for the
current console buffer. They are not stable object IDs and are not usable inside
scripts.
# WRONG in scripts — "1" is only an interactive print-buffer row number
/ip/route/set 1 gateway=3.3.3.3
# Better — internal IDs have a * prefix, but can change if objects are removed/re-added
/ip/route/set *1 gateway=3.3.3.3
# Best — resolve the target at runtime
/ip/route/set [find dst-address="0.0.0.0/0"] gateway=3.3.3.3
For generated config, use stable selectors such as comment=, name=, or a unique
address/list value. Internal IDs are visible in print as-value as .id=*HEX.
Treat [find] Results as ID Arrays
[find ...] returns zero, one, or many internal IDs. Many commands accept that
array directly (set, remove, disable), but code that needs exactly one object
should check the count before get.
:local ids [/interface/find where name="ether1"]
:if ([:len $ids] = 1) do={
:put [/interface/get ($ids->0) name]
} else={
:error ("expected exactly one interface, got " . [:len $ids])
}
Use [find comment="my-tool-tag"] for idempotent cleanup, not broad selectors such
as [find dynamic=no] that can delete unrelated user configuration.
Quote IP Prefixes in find / where
RouterOS does aggressive type conversion, but not always in the direction you expect.
For /ip/address, the address property is stored as a string including the prefix
length. An unquoted literal like 111.111.1.1/24 is an IP-prefix value and may match
nothing.
What ships with it
1 file 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.
- 9d ago First seen · 210 lines · 90 tokens per session scan A 63758235bb57
routeros-scripting is a skill published in the GitHub repository tikoci/routeros-skills (58 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 1,874 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
lab-hardware-cad
Design custom laboratory hardware as parametric build123d models and export fabrication-ready STEP, STL, and DXF files - microfluidic chips and molds, optomechanical mounts and breadboard adapters, cuvette and microplate holders, tube racks, animal-behavior rigs, and 3D-printed instrument fixtures. Use when a research…
pylabrobot
Develop and review PyLabRobot lab-automation resources, liquid-handling plans, offline simulations, and supported-device integrations. Use for PyLabRobot protocols or API questions; keep physical execution behind an explicit operator safety gate.
offensive-wifi
Wireless / 802.11 attack methodology for red team engagements and wireless security assessments. Covers monitor-mode setup, WPA/WPA2-PSK handshake capture and PMKID attacks, WPA3 SAE downgrade and Dragonblood, WPA-Enterprise (EAP) attacks (MSCHAPv2 cracking, EAP-TLS cert theft, evil-twin RADIUS), Karma / Known Beacons…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
offensive-iot
IoT and embedded device security testing methodology. Covers hardware reconnaissance (UART, JTAG, SWD, SPI flash, I2C EEPROM, eMMC chip-off), firmware acquisition (vendor portals, OTA capture, flash dump, binwalk extraction), firmware analysis (filesystem mounting, binary triage, hardcoded secrets, default credential…
offensive-bluetooth-classic
Bluetooth Classic (BR/EDR) attack methodology — device discovery, service enumeration via SDP, LMP/L2CAP layer attacks, legacy PIN cracking (BlueBorne / KNOB), Bluetooth file-transfer abuse (BlueSnarfing legacy), unauthenticated profile abuse (HSP, HFP, OPP), and modern relevance against older industrial / automotive…