Roslyn-Backed-MCP: Instructions file for Claude Code

.github/copilot-instructions.md

Roslyn-Backed-MCP copilot-instructions.md is an instructions file for Claude Code, GitHub Copilot from darylmcd/Roslyn-Backed-MCP. It costs 1,365 tokens per session, scanned A, original, MIT.

A set of coding rules for the Roslyn-Backed-MCP C# repository. Roslyn is Microsoft’s technology for analyzing C# code.

In plain words
What is it for?
Use it when writing or reviewing C# code, especially code that connects the repository’s core, analysis, and command-line layers.
Why use it?
It gives coding agents consistent style, project boundaries, and safety rules to follow while changing the repository.

Instructions file for Claude CodeGitHub Copilot

Written for Claude Code and GitHub Copilot: Claude Code plugin machinery, but also a Copilot instructions file. Also seen: mentions subagents; mentions Claude Code; mentions AGENTS.md.

This is darylmcd/Roslyn-Backed-MCP's own configuration. It tells Claude Code and GitHub Copilot how to work on Roslyn-Backed-MCP 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 Roslyn-Backed-MCP configures →

Reuse

Borrowing it

Nothing to install: this file belongs to darylmcd/Roslyn-Backed-MCP. 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/darylmcd/Roslyn-Backed-MCP/main/.github/copilot-instructions.md
Clone the repo
git clone --depth 1 https://github.com/darylmcd/Roslyn-Backed-MCP

Made for: Claude Code, GitHub Copilot.

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 Roslyn-Backed-MCP copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/darylmcd/roslyn-backed-mcp/copilot-instructions.svg)](https://agentmods.dev/instructions/darylmcd/roslyn-backed-mcp/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/darylmcd/roslyn-backed-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/darylmcd/roslyn-backed-mcp/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,365 This file is loaded in full into every session.
When invoked 1,365 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 $0.01365 $0.01365
Opus 5 $0.00682 $0.00682
Sonnet 5 $0.00273 $0.00273
Haiku 4.5 $0.00136 $0.00136

Measured 8d ago against content hash a691baf7ff04, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

Roslyn-Backed-MCP copilot-instructions.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.

.github/copilot-instructions.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Instructions

Implementation quality and safety rules for this repository. For session bootstrap and workflow, follow AGENTS.md first.

Code Style (C#)

  • Namespaces: file-scoped (namespace Foo;), not block-scoped — enforced as warning in .editorconfig
  • var: use var only when type is apparent; use explicit types elsewhere
  • Braces: omit only for single-line; use braces when multiline
  • Expression bodies: prefer for single-line properties and accessors
  • Usings: System namespaces first; no blank line between using groups; remove unused usings before merge
  • Nullability: enable nullable reference types; use ?? and null-conditional operators; no unchecked ! except in tests
  • Async: all async methods suffixed Async; no async void except event handlers

Layering Rules

  • RoslynMcp.Host.Stdio may depend on RoslynMcp.Core and RoslynMcp.Roslyn
  • RoslynMcp.Roslyn may depend on RoslynMcp.Core
  • RoslynMcp.Core has no intra-project dependencies — DTOs and contracts only
  • Do NOT let raw Roslyn types (SyntaxNode, ISymbol, etc.) cross the RoslynMcp.Core boundary
  • Do NOT put transport-specific logic in RoslynMcp.Roslyn
  • stdout is reserved for MCP protocol traffic — use stderr for all operational logging

Roslyn MCP (AI sessions in this repo)

  • Enable the roslyn MCP server (roslynmcp via stdio; see repo .mcp.json).
  • Read-side tools are the default for every session — including bootstrap self-edit on this repo — and are 5–30× faster than Grep / Bash: dotnet build / Bash: dotnet test. Specifically: prefer compile_check over dotnet build, test_related_files + test_run --filter over dotnet test, find_references / symbol_search over Grep, document_symbols over eyeballing. See ai_docs/bootstrap-read-tool-primer.md for the full pattern→tool table.
  • Write-side on peer repos: prefer Roslyn MCP refactoring tools over ad hoc multi-file text edits when a tool covers the operation (rename, extract/move type, code fixes, bulk type replace, etc.) — preview first, then apply.
  • Write-side on THIS repo: depends on session shape.
    • Worktree session (default for backlog-sweep subagents; running against the installed global roslynmcp tool): *_apply is safe — use it when a Roslyn MCP refactor tool covers the operation. Load the worktree's own RoslynMcp.slnx; workspace_reload after apply if a downstream call needs fresh state.
    • Main-checkout self-edit (running dotnet run --project src/RoslynMcp.Host.Stdio against the checkout you're editing): *_apply is restricted because the binary servicing the call is the binary being edited; use Edit / Write. *_preview and all read-side tools remain fully supported.
  • Canonical three-part policy: ai_docs/runtime.md (Roslyn MCP client policy).

Read the full file on GitHub · 93 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 · 93 lines · 1,365 tokens per session scan A a691baf7ff04

Subscribe to this mod's changes

Roslyn-Backed-MCP copilot-instructions.md is an instructions file published in the GitHub repository darylmcd/Roslyn-Backed-MCP (1 stars, last pushed today), licensed MIT. It adds 1,365 tokens to every session, about $0.0068 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.

Related

Other instructions, from other repositories

graftcode graftcode-dotnet.instructions.md

Instructions for grft-dev/graftcode, covering graftcode — .net backend services, when this applies (always), authoritative docs (source of truth), golden rules and service = .net class library.

grft-dev/graftcode · 7,060 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens