agentmods.dev

MikroCLAW: Skill for Claude Code

.claude/skills/mikrotik-sentinel/SKILL.md

mikrotik-sentinel is a skill for Claude Code from Syamsuddin/MikroCLAW. It costs 131 tokens per session (903 once invoked), scanned A, original, Apache-2.0.

A read-only MikroTik network monitor that looks for suspicious device behaviour from connection patterns. It considers device context, such as whether a client is a camera, phone, computer, or server.

In plain words
What is it for?
Use it to look for IoT botnets, crypto miners, spam bots, or scanning devices on a MikroTik network.
Why use it?
It can highlight possible compromised devices without relying on a list of known malware signatures. The same connection pattern may be normal for one device type and suspicious for another.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is Syamsuddin/MikroCLAW's own configuration. It tells Claude Code how to work on MikroCLAW itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything MikroCLAW configures →

not rated 0repo 2mo ago A scan 131 tokens original Apache-2.0
View source ↗ Syamsuddin/MikroCLAW
Reuse

Borrowing it

Nothing to install: this file belongs to Syamsuddin/MikroCLAW. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Syamsuddin/MikroCLAW/main/.claude/skills/mikrotik-sentinel/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Syamsuddin/MikroCLAW

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 mikrotik-sentinel

README.md
[![agentmods](https://agentmods.dev/badge/skills/syamsuddin/mikroclaw/mikrotik-sentinel/github.svg)](https://agentmods.dev/skills/syamsuddin/mikroclaw/mikrotik-sentinel)
Your own site
<a href="https://agentmods.dev/skills/syamsuddin/mikroclaw/mikrotik-sentinel"><img src="https://agentmods.dev/badge/skills/syamsuddin/mikroclaw/mikrotik-sentinel/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 mikrotik-sentinel

Your own site · 80×15
<a href="https://agentmods.dev/skills/syamsuddin/mikroclaw/mikrotik-sentinel"><img src="https://agentmods.dev/badge/skills/syamsuddin/mikroclaw/mikrotik-sentinel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 131 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 903 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00131 $0.00903
Opus 5 $0.00066 $0.00451
Sonnet 5 $0.00026 $0.00181
Haiku 4.5 $0.00013 $0.00090

Measured 11d ago against content hash a9fc372f6ad6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

mikrotik-sentinel 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 11d 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.

.claude/skills/mikrotik-sentinel/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MikroTik Sentinel — Sidik-Jari Perilaku Perangkat

Membangun profil perilaku tiap klien dari connection-tracking lalu menilai deviasi dalam konteks tipe perangkat — menangkap perangkat yang dikompromi tanpa bergantung pada signature. Read-only.

Tool yang dipakai

  • mcp__mikroclaw__analyze_client_behavior — inti: profil per-IP (tujuan unik, port, protokol) dari /ip/firewall/connection, tebak kelas perangkat via OUI, lalu nilai pola jahat (botnet Telnet, miner, spam, scan) berkonteks perangkat. Beri ip untuk fokus satu klien, atau kosong untuk semua.
  • (konteks opsional) dhcp_leases, arp_table, firewall_connections untuk detail mentah; address_lists untuk cek apakah sudah dikarantina.

Prosedur

  1. Pindai. Panggil analyze_client_behavior (tanpa ip) untuk laporan semua klien, terurut tingkat keparahan. Perhatikan keparahan_tertinggi.
  2. Telaah tiap temuan. Untuk klien mencurigakan, baca temuan[] dan profil (mis. 30 koneksi Telnet keluar dari sebuah Hikvision = ciri kuat botnet IoT). Tekankan konteks perangkat: perilaku yang wajar untuk PC bisa sangat mencurigakan untuk kamera/IoT.
  3. Verifikasi. Bila perlu, lihat firewall_connections mentah untuk mengonfirmasi tujuan/port, dan arp_table/dhcp_leases untuk identitas fisik.
  4. Rekomendasi berlapis. Sarankan tindakan: karantina via address-list, blokir IP, isolasi VLAN, ganti kredensial default perangkat IoT, update firmware.
  5. Tawarkan remediasi (gated). Eksekusi nyata (mis. add_address_list_entry untuk karantina, add_firewall_drop) butuh MIKROCLAW_ALLOW_WRITE=true dan konfirmasi user. Sarankan config_snapshot sebelum mengubah.

Format laporan

## Sentinel — Analisis Perilaku Perangkat
**Status:** ⚠️ 2 perangkat mencurigakan (tertinggi: critical)

| IP | Perangkat | Kelas | Keparahan | Temuan utama |
|----|-----------|-------|-----------|--------------|
| 192.168.1.50 | cam1 (Hikvision) | kamera/CCTV | 🔴 critical | 30 koneksi Telnet keluar — rekrutmen botnet |
| 192.168.1.30 | pc-gudang | tak dikenal | 🟠 warning | koneksi ke port pool penambang kripto |

**192.168.1.50 — detail:** profil 30 tujuan unik, semua port 23. Kamera normal
hanya bicara dengan 1 NVR → sangat tidak wajar. **Saran:** karantina segera +
ganti password default + cek firmware.

Read the full file on GitHub · 55 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. 11d ago First seen · 55 lines · 131 tokens per session scan A a9fc372f6ad6

Subscribe to this mod's changes

mikrotik-sentinel is a skill published in the GitHub repository Syamsuddin/MikroCLAW (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 131 tokens to every session and 903 once invoked, about $0.0007 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 2026-08-31.

Security
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens