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/moonolgerd/game-mcp/copilot-instructionsgit clone --depth 1 https://github.com/moonolgerd/game-mcpWrote 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/moonolgerd/game-mcp/copilot-instructions)<a href="https://agentmods.dev/instructions/moonolgerd/game-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/moonolgerd/game-mcp/copilot-instructions.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 | $0.00989 | $0.00989 |
| Opus 5 | $0.00495 | $0.00495 |
| Sonnet 5 | $0.00198 | $0.00198 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
game-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 4d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Game Discovery MCP Server - AI Agent Instructions
Architecture Overview
This is a Model Context Protocol (MCP) server built as a single C# script (game-mcp.cs) that discovers installed games across multiple Windows platforms. The project uses:
- Single-file architecture: Everything in
game-mcp.cs(683 lines) - no traditional project structure - Top-level program: Uses C# 9+ top-level statements with inline package references
- MCP framework: Uses
[email protected]with .NET hosting - JSON source generation: Uses
GameJsonContextfor AOT-compatible serialization
Key Patterns & Conventions
MCP Tool Registration Pattern
[McpServerToolType]
public static class GameDiscoveryTools
{
[McpServerTool(Name = "discover_games")]
[Description("...")]
public static async Task<string> DiscoverGames() { ... }
}
Platform Discovery Pattern
Each platform (Steam, Epic, GOG, Xbox, Registry) follows this structure:
- Private
DiscoverXxxGames()method returningList<Game> - Registry/file system scanning with error isolation
- Graceful degradation when platforms unavailable
- Consistent
Gameobject mapping
Error Handling Convention
- Continue on platform errors: Individual platform failures don't break discovery
- Stderr logging: Uses
Console.Error.WriteLine()for debugging without breaking MCP protocol - JSON error responses: All tools return JSON with
ErrorResponsetype for failures
JSON Serialization Approach
- Source generation required: Uses
GameJsonContext.Default.XxxTypepattern - Response classes: Separate DTOs (
GameInfo,GameDiscoveryResult,LaunchResponse,ErrorResponse) - No reflection: AOT-compatible with
[JsonSerializable]attributes
Critical Development Workflows
Running the MCP Server
dotnet run game-mcp.cs # Starts stdio MCP server
VS Code Integration
Configure in .vscode/mcp.json:
{
"servers": {
"game-discovery": {
"type": "stdio",
"command": "dotnet",
"args": ["run", "D:\\Repos\\game-mcp\\game-mcp.cs"]
}
}
}
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.
- 4d ago First seen · 102 lines · 989 tokens per session scan A 2cc461aa153c
game-mcp copilot-instructions.md is an instructions file published in the GitHub repository moonolgerd/game-mcp (0 stars, last pushed 6mo ago), licensed MIT. It adds 989 tokens to every session, about $0.0049 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.
Other instructions, from other repositories
Unreal_mcp AGENTS.md
Instructions for ChiR24/Unreal_mcp, covering project knowledge base, structure, where to look, code map and conventions.
ue-mcp CLAUDE.md
Instructions for db-lyon/ue-mcp, covering claude.md, repo at a glance, development workflow, git and commits and versioning.
Unreal_mcp copilot-instructions.md
Instructions for ChiR24/Unreal_mcp, covering copilot instructions for unreal mcp, architecture, critical constraints, ue 5.7 safety and build and test.
STS2MCP AGENTS.md
Instructions for Gennadiyev/STS2MCP, covering sts2 mcp — ai gameplay guide, mcp tool calling tips, state polling, card index shifting and event & reward flow.
better-godot-mcp CLAUDE.md
Instructions for n24q02m/better-godot-mcp, covering claude.md - better-godot-mcp, commands, setup, lint & type check and fix.
Unreal-MCP CLAUDE.md
Instructions for IvanMurzak/Unreal-MCP, covering claude.md — unreal-mcp, architecture in one screen, layout, editor vs runtime (in-game) and build / test (per leg).