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/st-valve/mcp-unity/agents-mdgit clone --depth 1 https://github.com/st-VALVe/mcp-unityWrote 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/st-valve/mcp-unity/agents-md)<a href="https://agentmods.dev/instructions/st-valve/mcp-unity/agents-md"><img src="https://agentmods.dev/badge/instructions/st-valve/mcp-unity/agents-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 | $0.03162 | $0.03162 |
| Opus 5 | $0.01581 | $0.01581 |
| Sonnet 5 | $0.00632 | $0.00632 |
| Haiku 4.5 | $0.00316 | $0.00316 |
Grade A, and why
mcp-unity 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 3d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
Real UIAutomation interaction with native dialogs cannot run in standard headless CI (session 0). Unit tests mock `child_process.spawn` via DI; the live PowerShell path requires a manual run on an interactive Windows run How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Unity — AI Agent Guide (MCP Package)
Purpose (what this repo is)
MCP Unity exposes Unity Editor capabilities to MCP-enabled clients by running:
- Unity-side “client” (C# Editor scripts): a WebSocket server inside the Unity Editor that executes tools/resources.
- Node-side “server” (TypeScript): an MCP stdio server that registers MCP tools/resources and forwards requests to Unity over WebSocket.
How it works (high-level data flow)
- MCP client ⇄ (stdio / MCP SDK) ⇄ Node server (
Server~/src/index.ts) - Node server ⇄ (WebSocket JSON-RPC-ish) ⇄ Unity Editor (
Editor/UnityBridge/McpUnityServer.cs+McpUnitySocketHandler.cs) - Tool/Resource names must match exactly across Node and Unity (typically
lower_snake_case).
Key defaults & invariants
- Unity WebSocket endpoint:
ws://localhost:8090/McpUnityby default. - Config file:
ProjectSettings/McpUnitySettings.json(written/read by Unity; read opportunistically by Node). - Execution thread: Tool/resource execution is dispatched via
EditorCoroutineUtilityand runs on the Unity main thread. Keep synchronous work short; use async patterns for long work.
Repo layout (where to change what)
/
├── Editor/ # Unity Editor package code (C#)
│ ├── Tools/ # Tools (inherit McpToolBase)
│ ├── Resources/ # Resources (inherit McpResourceBase)
│ ├── UnityBridge/ # WebSocket server + message routing
│ ├── Services/ # Test/log services used by tools/resources
│ └── Utils/ # Shared helpers (config, logging, workspace integration)
├── Server~/ # Node MCP server (TypeScript, ESM)
│ ├── src/index.ts # Registers tools/resources/prompts with MCP SDK
│ ├── src/tools/ # MCP tool definitions (zod schema + handler)
│ ├── src/resources/ # MCP resource definitions
│ └── src/unity/mcpUnity.ts # WebSocket client that talks to Unity
└── server.json # MCP registry metadata (name/version/package)
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.
- 3d ago First seen · 193 lines · 3,162 tokens per session scan A 8e44780c54e2
mcp-unity AGENTS.md is an instructions file published in the GitHub repository st-VALVe/mcp-unity (10 stars, last pushed 3mo ago), licensed MIT. It adds 3,162 tokens to every session, about $0.0158 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
GameDesignOS AGENTS.md
Instructions for DY-2026/GameDesignOS, covering gamedesignos agent 入口, 默认接法, agent 执行规则, 什么时候用整个项目 and 每个 skill 单独怎么用.
claudemon CLAUDE.md
Instructions for zamarrowski/claudemon, covering ai agent guidelines, project shape, general guidelines, general rules and guards & defensive code.
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.
nes-php-glfw copilot-instructions.md
Instructions for oliverearl/nes-php-glfw, covering github copilot development guidelines for nes emulator, agent document source of truth, project overview, code style & standards and documentation.
game-and-watch-retro-go-sd CLAUDE.md
Claude Code instructions for sylverb/game-and-watch-retro-go-sd, covering claude.md, what this project is, build / flash workflow, architecture and three storage tiers, one elf.
Cities2-MCP AGENTS.md
Instructions for mayor-modder/Cities2-MCP, covering agent rules, workspace safety, commit and pr safety, public-facing writing and merge and release gates.