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/ivanmurzak/unity-mcp/claude-mdgit clone --depth 1 https://github.com/IvanMurzak/Unity-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/ivanmurzak/unity-mcp/claude-md)<a href="https://agentmods.dev/instructions/ivanmurzak/unity-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ivanmurzak/unity-mcp/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 | $0.00503 | $0.00503 |
| Opus 5 | $0.00251 | $0.00251 |
| Sonnet 5 | $0.00101 | $0.00101 |
| Haiku 4.5 | $0.00050 | $0.00050 |
Grade A, and why
Unity-MCP 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 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.
What it actually says
CLAUDE.md
What This Is
Unity-MCP bridges LLMs (Claude, Cursor, Copilot, etc.) with Unity Editor and Runtime via the Model Context Protocol. Sub-projects: Unity-MCP-Plugin/ (Unity Editor/Runtime plugin), cli/, Installer/, Unity-Tests/.
The MCP server is NOT in this repo — the plugin consumes the shared GameDev-MCP-Server (binary gamedev-mcp-server, release assets gamedev-mcp-server-<rid>.zip, Docker aigamedeveloper/mcp-server) — one engine-agnostic server shared by Unity-MCP, Godot-MCP, and Unreal-MCP. The plugin downloads the release pinned by the ServerVersion constant in Unity-MCP-Plugin/Packages/com.ivanmurzak.unity.mcp/Editor/Scripts/McpServerManager.cs (decoupled from the plugin Version). Server version pin: bumping the consumed server = changing that constant; the pinned v<ServerVersion> release (with all 7 RID zips) must already exist on GameDev-MCP-Server BEFORE cutting a plugin release that pins it.
Build / Run
- Bump version:
.\commands\bump-version.ps1 <version> - CI/CD pipelines live in
.github/workflows/.
Project Constitution
Non-negotiable principles and architecture constraints: .specify/memory/constitution.md. You MUST read the constitution before performing any code review.
Find Detail In
- docs/claude/architecture.md — System architecture: SignalR bridge, main-thread execution, deterministic port hashing
- docs/claude/style.md — Coding conventions:
#nullable enable, no reflection for private access, namespace pattern, copyright headers - docs/claude/release.md — Release, versioning, CI/CD
- docs/claude/documentation-sync.md — README translation/copy sync requirements
Unity-MCP-Plugin/CLAUDE.md— sub-project specifics
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 · 25 lines · 503 tokens per session scan A 50f16c628cc7
Unity-MCP CLAUDE.md is an instructions file published in the GitHub repository IvanMurzak/Unity-MCP (4,079 stars, last pushed 10d ago), licensed Apache-2.0. It adds 503 tokens to every session, about $0.0025 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
unity-mcp CLAUDE.md
Claude Code instructions for CoplayDev/unity-mcp, covering claude.md, what this project is, architecture, three layers on the python side and transport modes.
evernote-mcp-server CLAUDE.md
Instructions for brentmid/evernote-mcp-server, covering claude.md, project overview, architecture, development commands and local development.
mcp-privilege-cloud CLAUDE.md
Claude Code instructions for aaearon/mcp-privilege-cloud, covering 🤖 llm development guidelines, 📚 mandatory: context7 documentation usage, required context7 usage patterns, context7 mcp tool usage for this project and use context7 mcp tools to get library documentation.
steam-games-mcp CLAUDE.md
Instructions for Grinv/steam-games-mcp, a project described as: MCP server for Steam: keyless store/catalog data (deals, tags, SteamOS/Deck/Frame compat) plus player profiles, libraries and achievements via the Steam Web API.
eco-mcp-app CLAUDE.md
Claude Code instructions for coilyco-flight-deck/eco-mcp-app, a project described as: Inline Claude Desktop widget for any public Eco game server — live player counts, meteor countdown, world stats. A hand-rolled MCP Apps reference implementation in Python (no bundler, no React).
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.