ue-world-level-streaming

ue-world-level-streaming is a skill for Claude Code, Codex from quodsoler/unreal-engine-skills. It costs 64 tokens per session (4,650 once invoked), scanned A, original, MIT.

An Unreal Engine guide for managing which parts of a game world are loaded, unloaded, or switched during play. World Partition is Unreal Engine 5's system for dividing large worlds, while level streaming loads separate level sections as needed.

In plain words
What is it for?
Use it for World Partition, level streaming, level travel, data layers, level instances, persistent player data, and HLOD, which combines distant objects to reduce rendering work.
Why use it?
It helps choose a world-management approach that fits the game's size, multiplayer setup, server needs, and level-travel flow.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for World Partition, level streaming, level travel, data layers, level instances, persistent player data, and HLOD, which combines distant objects to reduce rendering work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/quodsoler/unreal-engine-skills/ue-world-level-streaming
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 quodsoler/unreal-engine-skills --skill ue-world-level-streaming
Clone the repo
git clone --depth 1 https://github.com/quodsoler/unreal-engine-skills

Made for: Claude Code, Codex.

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 ue-world-level-streaming

README.md
[![agentmods](https://agentmods.dev/badge/skills/quodsoler/unreal-engine-skills/ue-world-level-streaming/github.svg)](https://agentmods.dev/skills/quodsoler/unreal-engine-skills/ue-world-level-streaming)
Your own site
<a href="https://agentmods.dev/skills/quodsoler/unreal-engine-skills/ue-world-level-streaming"><img src="https://agentmods.dev/badge/skills/quodsoler/unreal-engine-skills/ue-world-level-streaming/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 ue-world-level-streaming

Your own site · 80×15
<a href="https://agentmods.dev/skills/quodsoler/unreal-engine-skills/ue-world-level-streaming"><img src="https://agentmods.dev/badge/skills/quodsoler/unreal-engine-skills/ue-world-level-streaming.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,650 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. Third-party audits
  • Socket pass 18 Mar 2026
  • Snyk pass 9 Mar 2026
How audits are shown
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 $0.00064 $0.04650
Opus 5 $0.00032 $0.02325
Sonnet 5 $0.00013 $0.00930
Haiku 4.5 $0.00006 $0.00465

Measured 11d ago against content hash 3c9c2c41dea0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ue-world-level-streaming 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 11d 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.

skills/ue-world-level-streaming/SKILL.md · 490 lines

How it starts

The opening of the file, as written. The whole thing — 490 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UE World & Level Streaming

You are an expert in Unreal Engine's world management and level streaming systems.


Context

Read .agents/ue-project-context.md before advising. Pay attention to:

  • Engine version — World Partition is UE5 only; sub-level streaming works in both UE4 and UE5.
  • Build targets — Dedicated server has no rendering-driven streaming; streaming must be server-safe.
  • World size — Determines whether World Partition or manual sub-level streaming is appropriate.
  • Multiplayer — Seamless travel requirements and per-player streaming radius.

Information to Gather

Before recommending a streaming approach, confirm:

  1. World size and type: Is this an open world (World Partition), a set of discrete levels, or a hub-and-spoke map?
  2. Multiplayer: Are you running a dedicated server? Are per-player streaming radii needed?
  3. Streaming control: Does gameplay code need to control load/unload explicitly, or should proximity drive it?
  4. Level travel: Non-seamless (lobby flows), seamless (multiplayer round transitions), or no travel?
  5. Persistent data: What must survive a level transition — player state, inventory, session state?

World Partition (UE5)

Enabling World Partition

Enable via the Level menu: World -> World Partition -> Convert Level. Once enabled, all actors in the level are managed by World Partition's grid. The level can no longer have traditional sub-levels. Use One File Per Actor (OFPA) for collaborative editing: each actor is saved as its own .uasset under __ExternalActors__.

Runtime Data Layers

Data layers replace the old sub-level toggle pattern. A runtime data layer can be loaded/unloaded at runtime without traveling to a new map.

// MyGameMode.cpp
#include "WorldPartition/DataLayer/DataLayerManager.h"

void AMyGameMode::ActivateDungeonDataLayer()
{
    UDataLayerManager* DLMgr = UDataLayerManager::GetDataLayerManager(GetWorld());
    if (!DLMgr) return;

    // Get by asset reference (set up in editor as a UDataLayerAsset)
    UDataLayerAsset* DungeonLayer = DungeonDataLayerAsset.LoadSynchronous();
    DLMgr->SetDataLayerRuntimeState(DungeonLayer, EDataLayerRuntimeState::Activated);
}

void AMyGameMode::DeactivateDungeonDataLayer()
{
    UDataLayerManager* DLMgr = UDataLayerManager::GetDataLayerManager(GetWorld());
    if (!DLMgr) return;

    UDataLayerAsset* DungeonLayer = DungeonDataLayerAsset.LoadSynchronous();
    DLMgr->SetDataLayerRuntimeState(DungeonLayer, EDataLayerRuntimeState::Unloaded);
}

Read the full file on GitHub · 490 lines

Files

What ships with it

1 file 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.

  1. 11d ago First seen · 490 lines · 64 tokens per session scan A 3c9c2c41dea0

Subscribe to this mod's changes

ue-world-level-streaming is a skill published in the GitHub repository quodsoler/unreal-engine-skills (335 stars, last pushed 6mo ago), licensed MIT. It adds 64 tokens to every session and 4,650 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

gameobject-component-destroy

Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.

IvanMurzak/Unity-MCP · 49 tokens

unity-version-split

Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).

IvanMurzak/Unity-MCP · 59 tokens

godot-signals-groups

Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…

gamedev-skills/awesome-gamedev-agent-skills · 95 tokens

unity-addressables

Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).

Besty0728/Unity-Skills · 25 tokens

motion

How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.

OpenDCAI/GameFactory-3A · 0 tokens

threejs-exposure-color-grading

Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.

scottstts/Threejs-Awesome-Graphics-Agent-Skills · 60 tokens