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/4kk11/rhinomcpserver/claude-mdgit clone --depth 1 https://github.com/4kk11/RhinoMCPServerWrote 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/instructions/4kk11/rhinomcpserver/claude-md)<a href="https://agentmods.dev/instructions/4kk11/rhinomcpserver/claude-md"><img src="https://agentmods.dev/badge/instructions/4kk11/rhinomcpserver/claude-md.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 | $0.02311 | $0.02311 |
| Opus 5 | $0.01156 | $0.01156 |
| Sonnet 5 | $0.00462 | $0.00462 |
| Haiku 4.5 | $0.00231 | $0.00231 |
Grade A, and why
RhinoMCPServer CLAUDE.md 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 5d 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 — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
C# Design Principles
Overview
This document outlines the C# design philosophy for this project, drawing inspiration from three influential software engineers and their distinct approaches to code quality and architecture.
Core Design Philosophy
John Carmack's Approach: Functional Clarity & Performance
"The idea that I can be presented with a problem, set out to logically solve it with the tools at hand, and wind up with a program that could not be implemented in any other language."
Principles:
- Pure Functions First: Favor stateless, predictable methods over stateful classes
- Explicit Dependencies: Make all dependencies visible in constructors and method signatures
- Minimal Abstractions: Only abstract when complexity reduction is clear and measurable
- Performance Awareness: Consider memory allocation, GC pressure, and execution paths
Implementation:
// Good: Pure function with explicit dependencies
public static class ProjectCalculator
{
public static int CalculateProjectProgress(IReadOnlyList<Process> processes)
{
if (processes is null || processes.Count == 0)
{
return 0;
}
var completed = processes.Count(p => p.Progress == 100);
return (int)Math.Round((double)completed / processes.Count * 100);
}
}
// Avoid: Hidden state and side effects
public class ProjectManager
{
private readonly Dictionary<Guid, object> _cachedStats = new(); // Hidden state
public void UpdateProject(Project project)
{
// ... side effects buried in methods
}
}
Robert C. Martin's Approach: Clean Architecture & SOLID
"Clean code is simple and direct. Clean code reads like well-written prose."
Principles:
- Single Responsibility: Each class/method has one reason to change
- Dependency Inversion: Depend on abstractions, not concretions
- Clear Naming: Names should reveal intent without comments
- Small Methods: Methods should do one thing well
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.
- 5d ago First seen · 369 lines · 2,311 tokens per session scan A fc09edd68f11
RhinoMCPServer CLAUDE.md is an instructions file published in the GitHub repository 4kk11/RhinoMCPServer (13 stars, last pushed 5mo ago), licensed MIT. It adds 2,311 tokens to every session, about $0.0116 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 instructions, from other repositories
maui performance-hotpaths.instructions.md
Instructions for dotnet/maui, covering performance-critical path rules, hot paths in maui, allocation avoidance, caching and invalidation and collection iteration.
maui-labs testing.instructions.md
Instructions for dotnet/maui-labs, covering testing guide, test framework, test projects, running tests and all tests.
Kucoin.Net copilot-instructions.md
Copilot instructions for JKorf/Kucoin.Net, covering copilot instructions for kucoin.net, use kucoin.net, not raw http, client setup, result handling and api structure.
coinex-net
Use CoinEx.Net when generating C#/.NET code that interacts with the CoinEx cryptocurrency exchange, including Spot V2, margin account operations, futures, REST endpoints, WebSocket subscriptions, account management, market data, or order placement. Triggers on requests mentioning CoinEx integration in C#, .NET…
MonorailCss.Framework CLAUDE.md
Claude Code instructions for monorailcss/MonorailCss.Framework, covering monorailcss, architecture overview, core components, key design patterns and project structure.
unity-code-style-guide AGENTS.md
Instructions for krogh-jacobsen/unity-code-style-guide, covering agents.md — unity 6 c, project setup — edit this block, never do these — they corrupt the project, deprecated in unity 6 and if you read nothing else.