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/signal-loop/unitycodemcpserver/agents-mdgit clone --depth 1 https://github.com/Signal-Loop/UnityCodeMCPServerWhat 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 | $0.00729 | $0.00729 |
| Opus 5 | $0.00365 | $0.00365 |
| Sonnet 5 | $0.00146 | $0.00146 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
UnityCodeMCPServer AGENTS.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 2d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Agent guidance for contributors working in this repository.
Scope
- This file is for work inside this repo, not for downstream Unity projects using the package.
- Follow the closest AGENTS.md if a nested file is added later.
- Explicit user instructions override this file.
Project Shape
- Unity package and test project live under
Assets/Plugins/UnityCodeMcpServer. - Unity tests live under
Assets/Testsand related test assemblies in the repo root. - Python STDIO bridge code lives under
Assets/Plugins/UnityCodeMcpServer/Editor/STDIO~/src.
Editing Rules
- Make the smallest change that satisfies the request.
- Implement only the changes needed for the task, and finish the requested work before stopping.
- Do not change unrelated code, scenes, assets, or settings.
- Add tests for logic changes unless the change is trivial documentation or rename-only work.
- Keep existing style and naming conventions. In Unity C# code, use snake_case for private fields.
- Prefer latest supported Unity APIs already used by the repo.
Available Unity Tools
execute_csharp_script_in_unity_editorto run C# scripts in the editor.run_unity_teststo run Unity tests. Use this tools instead of command-line test runs for Unity-related work.read_unity_console_logsto read Unity console logs for compile errors.
Additional Unity Tools
play_unity_gameto start Play mode in the Unity editor for testing runtime behavior. You must useenter_play_modebefore this andexit_play_modeafter to return to edit mode.
Unity Workflow
- Before relying on Unity editor tooling, check for compilation problems in Unity logs and fix them first.
- If you edit C# source, validate with relevant Unity tests and re-check logs for compile errors.
- Use
run_unity_testsfor Unity test verification andread_unity_console_logsto inspect compile/runtime issues. - When using
execute_csharp_script_in_unity_editor, read the bundledexecuting-csharp-scripts-in-unity-editorskill first and treat script execution, console-log checks, and test runs as one workflow. - Do not use editor-executed C# scripts to edit source files or plain text files; use normal file editing tools for that.
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.
- 2d ago First seen · 62 lines · 729 tokens per session scan A 7e6ceee6faac
UnityCodeMCPServer AGENTS.md is an instructions file published in the GitHub repository Signal-Loop/UnityCodeMCPServer (19 stars, last pushed 1mo ago), licensed MIT. It adds 729 tokens to every session, about $0.0036 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 copilot-instructions.md
Instructions for IvanMurzak/Unity-MCP, covering project guidelines, critical rules, no c# reflection for private access, code review and code style.
mcp-unity AGENTS.md
Instructions for CoderGamester/mcp-unity, covering mcp unity — ai agent guide (mcp package), purpose (what this repo is), how it works (high-level data flow), key defaults & invariants and repo layout (where to change what).
godot-ai CLAUDE.md
Instructions for hi-godot/godot-ai, covering claude.md - godot ai and claude-specific notes.
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.
turn-based-game-mcp shared-library.instructions.md
Shared library development patterns for the turn-based games platform.
turn-based-game-mcp copilot-instructions.md
Copilot instructions for chrisreddington/turn-based-game-mcp, covering turn-based games platform, purpose, repository structure, code standards and required before each commit.