RoselineMCP: Instructions file for Claude Code

CLAUDE.md

RoselineMCP CLAUDE.md is an instructions file for Claude Code from Atypical-Consulting/RoselineMCP. It costs 10,398 tokens per session, scanned A, original, MIT.

A set of project instructions for RoselineMCP, a .NET server that analyzes and automatically fixes C# code using Microsoft’s Roslyn tools.

In plain words
What is it for?
Use it when changing RoselineMCP code, its MCP tools, API documentation, README, or public tool-reference website.
Why use it?
It keeps code changes and the project’s documentation synchronized, including descriptions of available tools and their interfaces.

Instructions file for Claude Code

Written for Claude Code: PostToolUse hook event. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is Atypical-Consulting/RoselineMCP's own configuration. It tells Claude Code how to work on RoselineMCP 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 RoselineMCP configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Atypical-Consulting/RoselineMCP. 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/Atypical-Consulting/RoselineMCP/dev/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Atypical-Consulting/RoselineMCP

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 RoselineMCP CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/atypical-consulting/roselinemcp/claude-md/github.svg)](https://agentmods.dev/instructions/atypical-consulting/roselinemcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/atypical-consulting/roselinemcp/claude-md"><img src="https://agentmods.dev/badge/instructions/atypical-consulting/roselinemcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for RoselineMCP CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/atypical-consulting/roselinemcp/claude-md"><img src="https://agentmods.dev/badge/instructions/atypical-consulting/roselinemcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10,398 This file is loaded in full into every session.
When invoked 10,398 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.10398 $0.10398
Opus 5 $0.05199 $0.05199
Sonnet 5 $0.02080 $0.02080
Haiku 4.5 $0.01040 $0.01040

Measured 8d ago against content hash 3d29cc62d8b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

RoselineMCP 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 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.

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.

CLAUDE.md · 617 lines

How it starts

The opening of the file, as written. The whole thing — 617 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

RoselineMCP is a .NET 10.0 MCP (Model Context Protocol) server that provides comprehensive code analysis and automated fixing capabilities for C# solutions using Roslyn analyzers and code fix providers.

Documentation Alignment (required)

Whenever you change code, you MUST check that the documentation is still aligned — and update whatever drifted in the same change. A code change is not done until its docs match. This is a hard rule; treat stale docs as a bug in the change.

When you add/remove a tool, or change a tool's parameters, response shape, annotations, or behavior, review and update every surface that mirrors it:

  • docs/API.md — per-tool request/response contract and the response-envelope section
  • CLAUDE.md — the "MCP Tools Available" list and the "Adding New MCP Tools" example/pattern
  • README.md — the tool list and any usage snippets
  • website/src/data/tools.ts and website/src/pages/tools.astro — the public tools reference (name, title, kind, params, data payload, capability pills). Both pages derive their counts from that array — toolCountPhrase (the two headings) and codeIntelligenceToolPhrase (index.astro's blurb), plus toolCount in tools.astro's meta description — so a tool added to an existing group needs no page edit and the copy cannot go stale. A tool in a new group, or with a new ToolKind, still does: groupBlurb is kept in index.astro and tools.astro, and kindLabel in tools.astro; a missing key renders as nothing rather than failing. Never restate a count in a page's prose — that is how tools.astro came to announce "Thirteen tools" above fourteen cards (#197). Forgetting tools.ts itself is now machine-checked, not just swept for: RoselineMCP.Tests/Release/WebsiteToolsDataContractTests.cs pins the array's wire names against the reflected [McpServerTool] set (the same reflection ToolDescriptionContractTests uses), so adding, removing or renaming a tool without updating tools.ts is a red test naming the file, not a page that quietly drifts (#208)
  • mcpb/manifest.json — the tools[] array (names + descriptions)
  • CHANGELOG.mdnothing to edit by hand. release-please generates each release's entries from Conventional Commits, so a user-facing change is described by your PR title; write it to read well as a changelog line. Expand it, if the one-liner is not enough, in the open release PR

Read the full file on GitHub · 617 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 · 617 lines · 10,398 tokens per session scan A 3d29cc62d8b4

Subscribe to this mod's changes

RoselineMCP CLAUDE.md is an instructions file published in the GitHub repository Atypical-Consulting/RoselineMCP (5 stars, last pushed yesterday), licensed MIT. It adds 10,398 tokens to every session, about $0.0520 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 2026-08-31.