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.
git clone --depth 1 https://github.com/nurture-tech/unity-mcp-serverWrote 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/rules/nurture-tech/unity-mcp-server/unity)<a href="https://agentmods.dev/rules/nurture-tech/unity-mcp-server/unity"><img src="https://agentmods.dev/badge/rules/nurture-tech/unity-mcp-server/unity/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/nurture-tech/unity-mcp-server/unity"><img src="https://agentmods.dev/badge/rules/nurture-tech/unity-mcp-server/unity.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00224 | $0.00224 |
| Opus 5.5 | $0.00090 | $0.00090 |
| Sonnet 5.5 | $0.00045 | $0.00045 |
| Haiku 4.5 | $0.00022 | $0.00022 |
Grade A, and why
unity 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 2mo 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
-
When editing an existing scene or prefab, open it first.
-
After creating a new scene, open it.
-
After creating or changing objects in a scene or prefab, focus on the objects that were created or changed.
-
After making a change to a scene or prefab that you want to keep, save it.
-
After editing a prefab, exit isolation mode before continuing to work on the scene.
-
Don't use generic file tools (edit_file, apply, copy, move, etc) when working with anything in the
Assetsfolder. -
Call the appropriate
Undoclass methods when running Unity Editor scripts to allow undoing any modifications. -
Take a screenshot after every change you make to a loaded Unity scene or prefab that affects visuals.
-
Use
PhysicsMasterialinstead ofPhysicMaterial. -
When creating a prefab, use
PrefabUtility.SaveAsPrefabAssetAndConnectinstead ofPrefabUtility.SaveAsPrefabso that the gameobject in the current scene/prefab is connected to the new prefab.
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.
- 2mo ago First seen · 24 lines · 224 tokens per session scan A ff67642a2985
unity is a cursor rule published in the GitHub repository nurture-tech/unity-mcp-server (32 stars, last pushed 6mo ago), licensed MIT. It adds 224 tokens to every session, about $0.0009 per session on Opus 5.5. 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 cursor rules, from other repositories
cursor
Use hera-agent-unity CLI for any Unity Editor task — measure, do not guess, save tokens.
hera-agent-unity
Use hera-agent-unity CLI for any Unity Editor task — measure, do not guess, save tokens.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.