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.
curl -O https://raw.githubusercontent.com/danikf/tik4net/master/.claude/skills/mikrotik-tests/SKILL.mdgit clone --depth 1 https://github.com/danikf/tik4netWrote 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/danikf/tik4net/mikrotik-tests)<a href="https://agentmods.dev/skills/danikf/tik4net/mikrotik-tests"><img src="https://agentmods.dev/badge/skills/danikf/tik4net/mikrotik-tests.svg" alt="Measured on agentmods" 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 | $0.00110 | $0.05876 |
| Opus 5 | $0.00055 | $0.02938 |
| Sonnet 5 | $0.00022 | $0.01175 |
| Haiku 4.5 | $0.00011 | $0.00588 |
Grade A, and why
mikrotik-tests 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MikroTik integration tests
Covers the integration suite only — tik4net.integrationtests/ (MSTest, net48), which needs a
live router and never runs in CI. Router-free tests live in tik4net.unittests/ (net8.0) and run in
CI on every push; if a new test does not actually need hardware, write it there instead.
dotnet test tik4net.unittests/tik4net.unittests.csproj
Router coordinates come from tik4net.integrationtests/App.config (host, user, pass,
routerMac, plus the topology keys consumed by TestConstants.cs). That file is the single source of
truth — read it, never restate its values.
TestBase.LabAddress picks which of them a run uses, and the choice is not cosmetic: the MAC-layer
transports run with no host at all, addressed by routerMac alone. That is the case those transports
exist for (a router with no IP address), so a mac* run that passed the host as well would leave it
untested — and routerMac is therefore mandatory in App.config for those three runsettings, not an
optimization that skips MNDP.
Transports
One *.runsettings file per transport sets tik.connectionType; the suite is run once per transport.
| Runsettings | Protocol | Port |
|---|---|---|
api / apissl |
binary API, plain / TLS | 8728 / 8729 |
rest / restssl |
REST HTTP / HTTPS | 80 / 443 |
telnet |
CLI | 23 |
ssh |
CLI over SSH | 22 |
mactelnet |
CLI over MAC layer | 20561 |
winboxcli / winboxclimac |
CLI in the WinBox terminal, IP / MAC | 8291 / 20561 |
winboxnative / winboxnativemac |
structured M2, IP / MAC | 8291 / 20561 |
The authoritative capability matrix is in README.md — it is kept
in sync with TikConnectionCapability. Do not maintain a second copy here.
Most of a run's skips are not capability skips. About 76 of them are [Ignore]d manual probes and RE
harnesses that skip on every transport — measured 2026-08-29 on RouterOS 7.24, a 541-test run skips 92
on api and 108 on winboxnative, so what actually separates the two transports is around a dozen tests,
not the raw count. Read the reasons (parse-trx.ps1 -ShowSkips) rather than the number; a count that
looks plausible is how a bogus skip survives. The per-transport figures for that run are pinned in
Docs/HISTORY.md.
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.
- 4d ago Changed · +21 lines e341bdae02ba
- 9d ago First seen · 390 lines · 110 tokens per session scan A e7ee9acdc2f7
mikrotik-tests is a skill published in the GitHub repository danikf/tik4net (197 stars, last pushed 2d ago), licensed Apache-2.0. It adds 110 tokens to every session and 5,876 once invoked, about $0.0006 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
author-test
Generate a test given sample. Parameters: C# SDK repository root; Package name: one of Azure.AI.Projects, Azure.AI.Projects.Agents or Azure.AI.Extensions.OpenAI; the sample to use as a starting point for the test.
compiler-commit
Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits with the [compiler] or [rust-compiler] prefix.
compiler-port
Port a compiler pass from TypeScript to Rust. Gathers context, plans the port, implements in a subagent with test-fix loop, then reviews.
generate-code-cs
Generate the code from typespec for C#. Parameter: C# SDK repository root location .
build-sample-matrix
Build the matrix of all the samples throughout different frameworks.
update-changelog
Update the CHANGELOG.md files of C# projects. Parameters: csroot C# SDK repository root.