agentmods.dev

upilot-unity-mcp

upilot-unity-mcp is a cursor rule for Cursor from codingriver/upilot. It costs 7,479 tokens per session, scanned A, original, MIT.

Rules for using UPilot MCP to automate the Unity Editor, the development environment for Unity games and interactive applications. They also define project-specific setup and the standard Unity project for checking package changes.

In plain words
What is it for?
Use them to automate Unity Editor tasks and validate UPilot repository or package changes in the designated test project.
Why use it?
They help keep Unity automation aligned with the project's package, inherited rules, and validation project. This reduces confusion about which project and instructions should be used.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

not rated 0repo changed 12d ago A scan 7,479 tokens original MIT

Good fit Use them to automate Unity Editor tasks and validate UPilot repository or package changes in the designated test project.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/codingriver/upilot/upilot-unity-mcp
View source ↗ codingriver/upilot
Install

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.

Clone the repo
git clone --depth 1 https://github.com/codingriver/upilot

Made for: Cursor.

Wrote 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.

agentmods badge for upilot-unity-mcp

README.md
[![agentmods](https://agentmods.dev/badge/rules/codingriver/upilot/upilot-unity-mcp/github.svg)](https://agentmods.dev/rules/codingriver/upilot/upilot-unity-mcp)
Your own site
<a href="https://agentmods.dev/rules/codingriver/upilot/upilot-unity-mcp"><img src="https://agentmods.dev/badge/rules/codingriver/upilot/upilot-unity-mcp/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.

agentmods 80×15 button for upilot-unity-mcp

Your own site · 80×15
<a href="https://agentmods.dev/rules/codingriver/upilot/upilot-unity-mcp"><img src="https://agentmods.dev/badge/rules/codingriver/upilot/upilot-unity-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7,479 This file is loaded in full into every session.
When invoked 7,479 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.07479 $0.07479
Opus 5.5 $0.02992 $0.02992
Sonnet 5.5 $0.01496 $0.01496
Haiku 4.5 $0.00748 $0.00748

Measured 12d ago against content hash 9568120b920d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

upilot-unity-mcp 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 12d 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.

Tests~/UPilotTest/.cursor/rules/upilot-unity-mcp.mdc · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UPilot Unity MCP

rulesVersion: 60 upilotPackageVersion: 0.3.53 projectPath: D:\upilot\Tests~\UPilotTest generatedAt: 2026-10-17T08:07:14Z

This Unity project has the io.github.codingriver.upilot UPM package installed. Project-specific business rules outside this controlled UPilot block take precedence.

Parent Agent Rules

  • Parent Agent rules path: ../../AGENTS.md (relative to the project root AGENTS.md).
  • Before applying this UPilot block, automatically load the parent rules when the path is not (none).
  • Resolve every loaded AGENTS.md to a canonical absolute path and keep a visited set, including this file, so repeated or circular references are skipped.
  • Apply inherited parent rules first, then this project's local rules, then this UPilot block.

Template-First Maintenance

  • Resolve source templates through skills/upilot-unity-mcp/template-manifest.json in the UPilot package source. AGENTS.md.template generates the UPilot blocks in project AGENTS.md and .cursor/rules/upilot-unity-mcp.mdc, plus Documentation~/AgentRules/AGENTS.upilot.md; the installer maintains the CLAUDE.md block referencing @AGENTS.md.
  • Author package-wide UPilot rules only in AGENTS.md.template. Never append them to the unmanaged area of project or parent AGENTS.md, or directly edit Cursor rules. The generated UPilot managed blocks remain the standing rule entry points; they are outputs, not independent authoring sources.
  • Author UPilot Skill instructions in SKILL.md.template and metadata in agents/openai.yaml.template. Never hand-create or hand-update an installed UPilot Skill, modify installed template copies, or create a parallel test-project-specific UPilot Skill to bypass this workflow. Fix the authoritative package source instead of patching generated repository files or installed copies.
  • Maintain distributed references, scripts, and other non-generated resources directly in package source, then distribute them through the same synchronization workflow; do not add templates for these resources. These ownership rules do not replace genuine project business rules/Skills or repository release rules.
  • Increment manifest agentRulesVersion for Agent behavior changes, and skillPackVersion for any distributed Skill file or template change, including AGENTS.md.template. Keep the manifest as the version source of truth.
  • After every authorized batch of template or distributed-resource changes, automatically complete source generation, source validation, project synchronization, and installed validation within the same task, without waiting for a separate user reminder. Follow the existing UPilot Skill's references/installation.md maintenance procedure. Saving templates alone is not completion; there is no background file watcher.
  • Verify project identity before using unity_agent_integrations_check and unity_agent_integrations_sync(apply=true). These tools use that project's installed UPM templates, not Server-bundled templates. The legacy unity_agent_rules_check/install tools affect only AGENTS.md and cannot prove complete synchronization.
  • Claim completion only after all five targets match the expected versions, context, and hashes, both .agents/skills/upilot-unity-mcp and .claude/skills/upilot-unity-mcp pass installed validation, and a repeat complete check returns current.
  • Preserve bytes outside managed blocks and parent-rule inheritance. Keep verified backups for customized or unverifiable targets under .upilot/backups/agent-integrations/. If source is missing, markers are malformed, a path is unsafe, a lock is busy, or backup/verification fails, report the incomplete targets; never bypass the failure by directly editing outputs.

Read the full file on GitHub · 205 lines

Changes

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.

  1. 12d ago Changed · +7 lines · +320 tokens per session 9568120b920d
  2. 14d ago Changed 6045f58b830e
  3. 17d ago Changed · -9 tokens per session 4b5ae88df544
  4. 20d ago Changed · +5 lines · +700 tokens per session f13c0911ab79
  5. 1mo ago Changed · -10 lines · -418 tokens per session e0752b16f3b8
  6. 1mo ago Changed · +127 tokens per session e4e073702a27
  7. 1mo ago Changed · +24 lines · +1,495 tokens per session 8c8bbca7b7f8
  8. 1mo ago Changed · +21 lines · +1,126 tokens per session 7026d0039b69
  9. 1mo ago Changed · +148 tokens per session baffb1be9d71
  10. 1mo ago First seen · 158 lines · 3,990 tokens per session scan A ba83ec5b6fde

Subscribe to this mod's changes

upilot-unity-mcp is a cursor rule published in the GitHub repository codingriver/upilot (0 stars, last pushed 13d ago), licensed MIT. It adds 7,479 tokens to every session, about $0.0299 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 2026-08-31.

Game developmentai-agentclaudecodexcursoreditor-automationgamedev-tools
Related

Other cursor rules, from other repositories

ascii-simulation-game-cursorrules-prompt-file

Cursor rules for ASCII simulation game development.

PatrickJS/awesome-cursorrules · 1,002 tokens

gamemaker-gml

GameMaker Language (GML) rules for scripts, objects, events, rooms, data structures, and performance-minded game code.

PatrickJS/awesome-cursorrules · 0 tokens

drawscape-factorio-usage

A set of coding rules for using the drawscape_factorio Python module to turn exported entity data into SVG output. It specifies the required functions, configuration values, and JSON input.

holtwood/awesome-cursorrules-zh · 0 tokens

scoring-and-ranking-rules

A set of rules for scoring and ranking entries in a game or competition. Entries advance after a win, leave the pool after a loss, and receive individual rankings.

holtwood/awesome-cursorrules-zh · 86 tokens

weekly-scoring-process-pseudocode

Pseudocode for a weekly scoring process, written in Chinese, that takes game results and updates the status of entries.

holtwood/awesome-cursorrules-zh · 62 tokens

pn-godot

Godot 4.x coding conventions: GDScript typing, signal patterns, scene composition, shader style, naming, Resource patterns, multiplayer RPC safety, GDExtension registration. Use when editing .gd, .tscn, .tres, .gdshader, or project.godot files.

perniemann/pnCore · 1,156 tokens