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-firewallgit 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-firewall)<a href="https://agentmods.dev/skills/tikoci/routeros-skills/routeros-firewall"><img src="https://agentmods.dev/badge/skills/tikoci/routeros-skills/routeros-firewall/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-firewall"><img src="https://agentmods.dev/badge/skills/tikoci/routeros-skills/routeros-firewall.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 | $0.00092 | $0.01884 |
| Opus 5 | $0.00046 | $0.00942 |
| Sonnet 5 | $0.00018 | $0.00377 |
| Haiku 4.5 | $0.00009 | $0.00188 |
Grade A, and why
routeros-firewall 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 12d 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-firewall — 100% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RouterOS Firewall
Rule Ordering — Sequential, Not Priority-Based
Rules are evaluated top-to-bottom — first match wins. This is the biggest source of iptables confusion.
place-before=0inserts at the top; defaultaddappends at the bottom- An
action=acceptrule must appear BEFORE anyaction=dropfor the same traffic - Non-terminal actions do NOT stop evaluation:
action=add-src-to-address-list,action=add-dst-to-address-list,action=log, and any rule withpassthrough=yescontinue to the next rule. Adroprule below anadd-src-to-address-listwill still fire.
# WRONG — drop fires before accept can match
/ip/firewall/filter/add chain=input action=drop
/ip/firewall/filter/add chain=input src-address=10.0.0.1 action=accept
# CORRECT — accept first, drop catches the rest
/ip/firewall/filter/add chain=input src-address=10.0.0.1 action=accept place-before=0
/ip/firewall/filter/add chain=input action=drop
Address-Lists as Dynamic Selectors
LLMs rarely suggest this pattern — they write one rule per IP address instead. Address-lists scale to hundreds of IPs with a single firewall rule.
# Build the list (static or dynamic with auto-expiry)
/ip/firewall/address-list/add list=trusted-mgmt address=192.168.1.0/24
/ip/firewall/address-list/add list=trusted-mgmt address=10.0.0.5 timeout=1h
# One rule handles all list members
/ip/firewall/filter/add chain=input src-address-list=trusted-mgmt action=accept \
comment="myapp-accept-mgmt"
Dynamic entries with timeout= expire automatically — the primary pattern for DoS blacklists.
Interface-Lists as Rule Selectors
in-interface-list= / out-interface-list= — powerful RouterOS pattern LLMs never propose. Eliminates duplicate rules when multiple interfaces serve the same role.
# Define the group once
/interface/list/add name=WAN
/interface/list/member/add list=WAN interface=ether1
/interface/list/member/add list=WAN interface=pppoe-out1
# One rule applies to all WAN interfaces
/ip/firewall/filter/add chain=input in-interface-list=WAN action=drop \
comment="myapp-drop-all-wan"
What ships with it
2 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.
- 12d ago First seen · 160 lines · 92 tokens per session scan A 4ada00c81fa0
routeros-firewall is a skill published in the GitHub repository tikoci/routeros-skills (59 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 1,884 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
self-improvement
Captures lessons and promotes recurring patterns.
building-mcp-servers
Authors an MCP server with the official SDK and gates.
requirements-elicitation
Turns vague intent into testable requirements.
using-superpowers
Activates the dojo framework at the start of a session.
verify-before-done
Proves work with tests, diffs, and logs before sign-off.
architecture-sketching
Defines types and boundaries before implementation.