tik4net: Skill for Claude Code

.claude/skills/chr-test-router-init/SKILL.md

chr-test-router-init is a skill for Claude Code from danikf/tik4net. It costs 258 tokens per session (4,535 once invoked), scanned A, original, Apache-2.0.

A setup procedure for restoring a virtual MikroTik CHR router to the configuration required by tik4net’s integration tests. CHR is MikroTik’s virtual-router edition, and integration tests check a system against a live router.

In plain words
What is it for?
Use it after a router reset, restore, reinstallation, or recreation to prepare the test device and confirm that its connections and topology are ready for integration testing.
Why use it?
It brings a reset or newly recreated test router back to a known state and verifies each setup step. This avoids failures caused by missing configuration or stale router details.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool.

This is danikf/tik4net's own configuration. It tells Claude Code how to work on tik4net 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 tik4net configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is configuration reset and the investigation stalled. See [`Docs/HISTORY.md`](../../../Docs/HISTORY.md)..

Reuse

Borrowing it

Nothing to install: this file belongs to danikf/tik4net. 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/danikf/tik4net/master/.claude/skills/chr-test-router-init/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/danikf/tik4net

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 chr-test-router-init

README.md
[![agentmods](https://agentmods.dev/badge/skills/danikf/tik4net/chr-test-router-init.svg)](https://agentmods.dev/skills/danikf/tik4net/chr-test-router-init)
Your own site
<a href="https://agentmods.dev/skills/danikf/tik4net/chr-test-router-init"><img src="https://agentmods.dev/badge/skills/danikf/tik4net/chr-test-router-init.svg" alt="Measured on agentmods" height="20"></a>
Per session 258 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,535 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 6 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 95
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 129
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 138
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 169
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 216
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 238
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
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 $0.00258 $0.04535
Opus 5 $0.00129 $0.02268
Sonnet 5 $0.00052 $0.00907
Haiku 4.5 $0.00026 $0.00453

Measured 8d ago against content hash 5aba8fce63bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

chr-test-router-init scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sI "https://download.mikrotik.com/routeros/$V/all_packages-x86-$V.zip" | grep -iE "^HTTP|content-length"
.claude/skills/chr-test-router-init/SKILL.md · 346 lines

How it starts

The opening of the file, as written. The whole thing — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CHR test-router initialization (tik4net)

Brings a freshly restored CHR back to the state the integration suite assumes. Runs top to bottom; every step ends in a live verification, not just a "command accepted".

Router coordinates are read from tik4net.integrationtests/App.config — that file is the single source of truth (host, user, pass, routerMac). Never hardcode an IP, MAC or credential in this skill or in a command; read the current values from App.config at the start of the run and keep them in shell variables for the session:

# from tik4net.integrationtests/App.config
ROUTER_HOST=…   ROUTER_USER=…   ROUTER_PASS=…   ROUTER_MAC=…

All router calls go through the tik4net MCP (mikrotik_call) — see the mikrotik skill. Using our own library to provision the router is deliberate: it smoke-tests the transports as a side effect.


Step 0 — MNDP scan: find the router and let the user confirm which one it is

Start here, before touching App.config or assuming any IP. After a VM rebuild the IP, the MAC and the identity can all have changed, and there is usually more than one MikroTik reachable (the developer's own home router shares the segment). Never guess which one is the test box.

MNDP is a broadcast listen — no credentials, no IP needed. Use the mikrotik_discover MCP tool:

mikrotik_discover  timeoutSeconds: 6

Leave stopWhenFirstFound off: it returns whichever device broadcast first, and the whole point here is to CHOOSE between the routers on the segment. Zero rows usually means the host firewall is blocking the inbound UDP 5678 broadcast, not that the router is dead — it fails silently and looks exactly like an empty segment. A router on another subnet is invisible too; MNDP does not cross a router.

Typical output — note that guessing here would be a coin flip:

{ "count": 2, "routers": [
  { "identity": "home_rtr", "ipv4": "10.0.0.1", "mac": "AA:BB:CC:DD:EE:FF",
    "version": "7.17rc3 (testing) …", "boardName": "RB4011iGS+5HacQ2HnD" },
  { "identity": "CHR",      "ipv4": "10.0.0.2", "mac": "AA:BB:CC:DD:EE:01",
    "version": "7.23.2 (stable) …",  "boardName": "CHR" } ] }

Read the full file on GitHub · 346 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. 8d ago First seen · 346 lines · 258 tokens per session scan A 5aba8fce63bc

Subscribe to this mod's changes

chr-test-router-init is a skill published in the GitHub repository danikf/tik4net (197 stars, last pushed 2d ago), licensed Apache-2.0. It adds 258 tokens to every session and 4,535 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.