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 instructions/danikf/tik4net/agents-mdgit clone --depth 1 https://github.com/danikf/tik4netWhat 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 | $0.03026 | $0.03026 |
| Opus 5 | $0.01513 | $0.01513 |
| Sonnet 5 | $0.00605 | $0.00605 |
| Haiku 4.5 | $0.00303 | $0.00303 |
Grade A, and why
tik4net AGENTS.md 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 2d 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.
directly (curl for REST, the `mikrotik-cli-probe` skill for CLI/PTY) and confirm what it actually How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Entry point for AI coding agents working in this repository. Everything here is either non-obvious (you would get it wrong by default) or a pointer to the document that holds the detail. Nothing is duplicated from the documents it links to — follow the link rather than assuming.
Language: this is a public open-source project, so all documentation in this repository is English, including agent-facing files.
What this is
tik4net is a .NET library for talking to MikroTik RouterOS devices. It is not an API-only library:
as of 4.0 it ships 11 transports (binary API, REST, and a family of CLI/WinBox/MAC-layer channels)
behind one connection contract, plus an attribute-driven O/R mapper on top. The five shipping projects
multi-target netstandard2.0;net8.0 — netstandard2.0 is kept deliberately (Unity/Xamarin/.NET Framework
reach), and the net8.0 leg is where the modern surface lives, e.g. the IAsyncEnumerable streaming reads.
The test and tool projects are net8.0 / net48.
Reference map — read the right file, don't guess
| Question | Read |
|---|---|
| How the code is laid out; layers, transports, capability model, O/R mapper internals, where the risk is | ARCHITECTURE.md |
| What the router actually does on the wire (per-transport protocol ground truth) | Docs/README.md — index of the Docs/ findings |
| What the project is, for humans; packages, features, install | README.md |
| Why something is the way it is today; superseded diagnoses; dated incidents | Docs/HISTORY.md |
| What a shipping or non-shipping project does | that project's own README.md |
| End-user usage documentation | the wiki (cloned next to this repo — ask the maintainer for its local path) |
Read ARCHITECTURE.md before any non-trivial change. It maps the transport family and tells you which code is reverse-engineered and must not be refactored opportunistically.
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.
- 2d ago First seen · 215 lines · 3,026 tokens per session scan A 7f8581fc60ed
tik4net AGENTS.md is an instructions file published in the GitHub repository danikf/tik4net (197 stars, last pushed 2d ago), licensed Apache-2.0. It adds 3,026 tokens to every session, about $0.0151 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.
Other instructions, from other repositories
azure-sdk-for-net AGENTS.md
AGENTS.md instructions for Azure/azure-sdk-for-net, covering azure sdk for .net - ai agent guidelines, repository overview, purpose and scope, repository structure and agent interaction guidelines.
azure-sdk-for-net copilot-instructions.md
Copilot instructions for Azure/azure-sdk-for-net, covering project overview, prerequisites, folder structure, azure generator and azure management generator.
Fluence.Wpf AGENTS.md
AGENTS.md instructions for sintaxasn/Fluence.Wpf, covering fluence.wpf - developer handbook, 1. project overview, solution layout, clr namespaces and 2. coding standards.
Fluence.Wpf copilot-instructions.md
Copilot instructions for sintaxasn/Fluence.Wpf, covering fluence.wpf -- copilot instructions, project at a glance, non-negotiable rules, theme architecture (3-slot layout -- do not break) and reference priority.
OpenTouryo AGENTS.md
AGENTS.md instructions for OpenTouryoProject/OpenTouryo, covering プロジェクト ポリシー, git 操作は行わない（状態を変える操作をしない）, github 操作は gh で行う, github actions を書き足すとき and コーディング規約は coding.md、領域ごとの事情は analysis.md に従う.
OpenTouryo CLAUDE.md
Claude Code instructions for OpenTouryoProject/OpenTouryo, a project described as: ”Open棟梁”は、長年の.NETアプリケーション開発実績にて蓄積したノウハウに基づき開発した.NET用アプリケーション フレームワークです。 (”OpenTouryo” , is an application framework for .NET which was developed using the accumulated know-how with a long track record in .NET application development.).