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 agentmods add skills/danikf/tik4net/mikrotik-cli-probenpx skills add danikf/tik4net --skill mikrotik-cli-probegit 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-cli-probe)<a href="https://agentmods.dev/skills/danikf/tik4net/mikrotik-cli-probe"><img src="https://agentmods.dev/badge/skills/danikf/tik4net/mikrotik-cli-probe.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00166 | $0.02055 |
| Opus 5 | $0.00083 | $0.01027 |
| Sonnet 5 | $0.00033 | $0.00411 |
| Haiku 4.5 | $0.00017 | $0.00205 |
Grade A, and why
mikrotik-cli-probe 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 6d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MikroTik CLI probe (Telnet / PTY)
The binary API (mikrotik skill / mikrotik_call) is the right tool for normal queries. Use THIS
skill when the question is specifically about the terminal/CLI layer: what RouterOS emits over a
PTY, why a CLI command returns nothing, how to shape a command so its output is parseable, etc.
This is the layer tik4net's CLI-based transports (tik4net/Cli/, tik4net/Telnet/) sit on.
Two ways to get terminal ground truth. The probe script below is the router-only view (no tik4net at all). To see the same raw bytes as tik4net itself sees them — through the actual transport, with the mepty pull cadence, VT100 answers and prompt/settle decisions the library makes — use
mikrotik_callwithtraceLevel:'bytes'(channelstelnet.sock,wbxcli.mepty,mactelnet.udp) and optionallyincludeRouterLog:truefor the device-side log. That is the in-library equivalent of this probe and the faster first stop when the question is "what did our client do", not "what can the router do at all". See themikrotikskill's Wire tracing & router-log debugging section. Reach for the standalone probe script when you need a reference implementation independent of tik4net.Check which server answered. The MCP route runs a staged copy of the build output, so a trace can silently come from the server you had before your last build. Every answer names the assembly that produced it —
mikrotik_callon a trailing--- MCP SERVER --- … built <timestamp> …line,mikrotik_cli_completein itsserverBuildproperty. If that timestamp predates your build, the trace is evidence about the OLD code; reconnecttik4net-mcpand take it again. The probe script has no such trap: it does not use the library at all, which is exactly why it stays the tie-breaker.
The probe script
Tools/probes/telnet-cli-probe.ps1 is a minimal, self-contained Telnet client that reproduces
exactly what a correct PTY transport must do — Telnet IAC negotiation, VT100 cursor-probe answers, and
login with change-password-nag dismissal — then prints the RAW bytes the router returns (ESC shown as
\e, CR/LF as \r/\n). It deliberately does NOT use the tik4net library, so it gives you ground
truth to compare the library against.
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.
- 6d ago First seen · 110 lines · 166 tokens per session scan A 48c804f691be
mikrotik-cli-probe is a skill published in the GitHub repository danikf/tik4net (197 stars, last pushed yesterday), licensed Apache-2.0. It adds 166 tokens to every session and 2,055 once invoked, about $0.0008 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
dpg-migration
Migration logic for Azure SDK for .NET data-plane libraries migrating from AutoRest/Swagger to TypeSpec-based generation. Uses MCP tools from the generator-agent server for automated deterministic fixes.
csharp-azure-spector-coverage-gaps
Discovers and implements gaps in Spector test coverage for the Azure C# HTTP client emitter. Use when asked to find missing Spector scenarios, add Spector test coverage, or implement a specific Spector spec for the Azure C# emitter. Can also compare coverage between the Azure dashboard and the Standard (TypeSpec core)…
auto-build-repair
Headless, bounded repair of custom-code build failures in an already-generated Azure SDK PR. Thin wrapper over the shared azure-sdk-mcp:azsdkcustomizedcodeupdate engine in custom-code-only scope (editScope: CustomCode); the skill owns the iterate-until-green loop, capped by a per-language maxIterations read from…
azure-sdk-mgmt-pr-review
Review Azure SDK management-plane pull requests, check naming conventions, API compatibility, and code quality.
mgmt-review-comment-resolution
Resolve review comments on Azure management-plane .NET SDK PRs. Handles renaming types/properties, changing property types, and other API surface adjustments by updating TypeSpec client.tsp and regenerating.
mitigate-breaking-changes
Patterns and techniques for mitigating breaking changes in Azure management-plane SDKs. Covers SDK-side customizations (partial classes, CodeGenType, CodeGenSuppress) and TypeSpec decorator customizations (clientName, access, markAsPageable, alternateType, hierarchyBuilding).