unity-rql

unity-rql is a skill for Claude Code from IvanMurzak/Unity-MCP. It costs 82 tokens per session (2,158 once invoked), scanned A, original, Apache-2.0.

A guide to using RQL across the Unity Editor to read and change scene objects, assets, prefabs, scenes, logs, tests, and editor state. Unity is a game development editor, and RQL is the query language used to work with its data.

In plain words
What is it for?
Use it to find and inspect Unity data, learn available component members, change objects or assets, manage scenes and prefabs, inspect logs, and work with tests or profiling.
Why use it?
It brings querying, schema inspection, and editing into one workflow, reducing the need for repeated manual Editor operations. It also separates read-only queries from changes and supports previews and undoable edits.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to find and inspect Unity data, learn available component members, change objects or assets, manage scenes and prefabs, inspect logs, and work with tests or profiling.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ivanmurzak/unity-mcp/unity-rql
About the project

Unity-MCP connects AI coding agents to the Unity game engine through MCP, letting them work with the Unity Editor and running games. It is used by game developers to generate code, automate development and testing, debug projects, and add AI-driven behavior to games. The catalogue entries provide skills, instructions, an MCP integration, and settings for operating this workflow.

IvanMurzak/Unity-MCP · 4,475 stars · on GitHub · ai-game.dev

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.

Any agent
npx skills add IvanMurzak/Unity-MCP --skill unity-rql
Clone the repo
git clone --depth 1 https://github.com/IvanMurzak/Unity-MCP

Made for: Claude Code.

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 unity-rql

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/ivanmurzak/unity-mcp/unity-rql"><img src="https://agentmods.dev/badge/skills/ivanmurzak/unity-mcp/unity-rql.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,158 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00082 $0.02158
Opus 5.5 $0.00033 $0.00863
Sonnet 5.5 $0.00016 $0.00432
Haiku 4.5 $0.00008 $0.00216

Measured today against content hash da5b81e7176a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

unity-rql 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 today.

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.

Unity-MCP-Plugin/.claude/skills/unity-rql/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RQL — query and change the Unity Editor

RQL is one pipeline language for the whole Editor: find objects, read members, filter, aggregate, and change them in one call. Prefer one precise query over many exploratory calls.

  • rql-query — read-only queries, compact table results.
  • rql-mutate — queries ending with set / call; all-or-nothing, undoable (Ctrl+Z), dry_run: true previews.
  • rql-schema — sources and component types in the scene; rql-schema(type) lists one type's members and methods.
unity-mcp-cli run-tool rql-query --input '{"query": "objects | where name contains \"Enemy\" | select $ref name"}'
unity-mcp-cli run-tool rql-mutate --input '{"query": "objects | where name == \"Player\" | set active = false"}'

Language

RQL: source | stage | stage ...
Sources: objects (every GameObject in the loaded scenes, inactive included), roots, scenes, selection, prefab (the prefab open in prefab editing mode), console (Editor log entries), shaders, componentTypes, profiler (memory / rendering / frame snapshots; call Start / Stop / Save), tests (test methods; run a selection with tests-run query), testResults (last run), editor (Editor state and operations). Assets: unity.assets("t:Material") or unity.assets("t:Prefab", "Assets/Enemies"), unity.asset("Assets/Mats/Red.mat"). ref("Light#1234") resolves a $ref; unity.find("Player") or unity.find("Level/Pillar_1") a GameObject by unique name or path.
Stages:
  where <predicate>                  filter
  select a b.c alias=(expr)          project columns (wrap computed expressions in parentheses)
  sort <expr> [desc], ...            stable sort
  first N | skip N | count
  get <path>                         replace each item by a member (lists are flattened)
  recurse children [max-depth=N] [include-self=false]   walk the hierarchy (input items included by default)
  distinct [expr] | group-by expr | sum expr | min expr | max expr | avg expr
Expressions: == != < <= > >= and or not + - * / %; contains, starts-with, ends-with (case-insensitive); matches "regex"; x in [a, b]; x is null; x is not null; $ is Light (includes subclasses); has(member). Literals: numbers, "strings", true/false/null, lists [a, b], objects {x: 1, y: 2}.
Paths: a.b.c, list[0], map["key"]; .member on a list maps over its elements. List methods: .any(pred) .all(pred) .count([pred]) .sum(e) .min(e) .max(e) .first([pred]); inside them bare names refer to the element, falling back to the outer item.
Meta: $ (current item), $ref (stable id such as Light#1234), $type, $path, $index, $depth. Enums compare to strings (type == "Spot"); == on strings is case-sensitive.
Unity: GameObject has components (list), children (list), active, name, tag, layer, transform (position, localPosition, eulerAngles, localScale, parent). Component members are the C# members (public + [SerializeField]); find them via objects | get components | where $ is Light. Vectors/colors print as (x, y, z); write "(1, 2, 3)", [1, 2, 3] or {x: 1, y: 2, z: 3}; colors also "#ff8800". Material shader properties: properties["_Color"]. Destroyed objects read as null (missing references: where target == null). Navigate with paths or get; select only projects output columns.
Results come back as compact rows (header line, then col|col). Long results are truncated — refine with where/first or use count. Unknown members produce warnings with suggestions; rql-schema(type) lists a type's members.

Read the full file on GitHub · 99 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. today First seen · 99 lines · 82 tokens per session scan A da5b81e7176a

Subscribe to this mod's changes

unity-rql is a skill published in the GitHub repository IvanMurzak/Unity-MCP (4,475 stars, last pushed today), licensed Apache-2.0. It adds 82 tokens to every session and 2,158 once invoked, about $0.0003 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 2026-10-16.