What is unreal-engine?

An Unreal Engine 5 support skill for automating game development, editor work, and packaging. Unreal Engine is a real-time engine for games and other interactive 3D experiences.

Use it for Python editor scripts, C++ modules, asset migration, Editor Utility Widgets, Unreal Automation Tool tasks, and BuildCookRun packaging.

It helps coordinate Blueprints, C++ code, editor tools, assets, and automated builds in larger Unreal projects.

unreal-engine — Skill for Claude Code by alivirgo/Major-AI-Skills

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 alivirgo/Major-AI-Skills --skill unreal-engine

Clone the repo

git clone --depth 1 https://github.com/alivirgo/Major-AI-Skills

Made for: Claude Code.

Or install mas-3d-games, the plugin that ships this one along with the rest of its 8 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/unreal-engine/github.svg)](https://agentmods.dev/skills/alivirgo/major-ai-skills/unreal-engine)

Your own site

<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/unreal-engine"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/unreal-engine/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/unreal-engine"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/unreal-engine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,105 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.

Model	Per session	Once invoked
Fable 5.1	$0.00026	$0.01105
Opus 5.5	$0.00010	$0.00442
Sonnet 5.5	$0.00005	$0.00221
Haiku 4.5	$0.00003	$0.00111

Measured 1mo ago against content hash c83f55bd0bea, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

unreal-engine 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 1mo 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.

plugins/mas-3d-games/skills/unreal-engine/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.

Unreal Engine 5 Editor & Pipeline AI Skill Guide (Claude)

Overview & Engine Architecture

Unreal Engine 5.x combines UObject/C++, Blueprints, Editor Python (import unreal), and UAT BuildCookRun packaging. Rendering: Nanite, Lumen, Niagara. Claude acts as Principal UE TD: editor automation only in Python, deterministic cooked builds, World Partition / Data Layers, no game-thread blocking in tools.

Version pin: Engine association in .uproject (e.g. 5.4, 5.5) — CI must build with matching EngineAssociation and -engine= path.

┌─────────────────────────────────────────────────────────────┐
│  Editor Python / UBT  →  Cook  →  Stage  →  Pak  →  Archive │
│  UnrealEditor-Cmd.exe -ExecutePythonScript=...              │
│  RunUAT.bat BuildCookRun -project=... -platform=Win64       │
└─────────────────────────────────────────────────────────────┘

When to use / when not to

Use when: batch asset fixes, validation, packaging, render queue via Movie Render Queue (MRQ), commandlet-style automation.

Do not use when: import unreal in shipped game modules — Python is Editor-only. Do not assume Python works in packaged game.

Operational Capabilities & Agent Directives

Python scope: Run via Editor, UnrealEditor-Cmd, or -ExecutePythonScript= — never in runtime game code.
UAT packaging: Explicit -platform, -clientconfig=Development|Shipping, -archivedirectory, -pak; log Saved/Logs.
Deterministic cooks: Pin -cookflavor, disable stray -iterate when you need clean QA; store Build.version artifact; for MRQ use fixed warm-up frames, seed in sequencer settings, fixed anti-aliasing samples.
Color: OCIO / OpenColorIO for MRQ; sRGB vs linear EXR outputs — tag output format in job preset; Lumen exposure can vary slightly GPU-to-GPU — document tolerance for pixel tests.
Maps list: Packaging fails if maps missing from Project Settings → Packaging — automate validation Python that reads ProjectSettings packaging maps.
Live Coding: Disable in CI — hot reload causes nondeterministic Blueprint compile state.

Read the full file on GitHub · 99 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago Changed · -28 lines c83f55bd0bea
1mo ago Changed · -9 tokens per session fa78e5bebc2f
2mo ago First seen · 127 lines · 35 tokens per session scan A 8864d796b113

Subscribe to this mod's changes

unreal-engine is a skill published in the GitHub repository alivirgo/Major-AI-Skills (2 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 1,105 once invoked, about $0.0001 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.

Deterministic Game development agent-skills agentic-skills ai-agent-skills ai-agents buildcookrun game-engines headless uat ue5 unreal-engine unreal-python

unreal-engine next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
unreal-enginealivirgo/Major-AI-Skills	Skill	2	yesterday	MIT	A	26	Claude Code
unreal-mcpNousResearch/hermes-agent	Skill	261k	yesterday	MIT	A	17	Claude Code, Codex
asset-managementkevinpbuckley/VibeUE	Skill	812	2d ago	MIT	A	130	Claude Code, Codex
level-actorskevinpbuckley/VibeUE	Skill	812	2d ago	MIT	A	64	Claude Code, Codex
vibeuekevinpbuckley/VibeUE	Skill	812	2d ago	MIT	A	82	Claude Code, Codex
materialskevinpbuckley/VibeUE	Skill	812	2d ago	MIT	A	95	Claude Code, Codex
project-settingskevinpbuckley/VibeUE	Skill	812	2d ago	MIT	A	61	Claude Code, Codex