unity-scene-assets

unity-scene-assets is a skill for Claude Code from Nice-Wolf-Studio/unity-claude-skills. It costs 59 tokens per session (2,882 once invoked), scanned A, original, MIT.

A guide for organizing Unity scenes and game assets, including how levels, shared systems, and loading are structured. It explains when to use separate scenes, additive loading, or Unity Addressables, which manage assets loaded when needed.

In plain words
What is it for?
Planning level and persistent scenes, loading assets and scenes asynchronously, choosing between Resources and Addressables, coordinating asset lifetimes, and creating loading screens.
Why use it?
It helps avoid hard-coded asset loading, unnecessary memory use, and scene setups that become difficult to maintain as a game grows. It also accounts for asynchronous loading and cleanup.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the unity plugin — 35 skills shipped together

Good fit Planning level and persistent scenes, loading assets and scenes asynchronously, choosing between Resources and Addressables, coordinating asset lifetimes, and creating loading screens.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nice-wolf-studio/unity-claude-skills/unity-scene-assets
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 Nice-Wolf-Studio/unity-claude-skills --skill unity-scene-assets
Clone the repo
git clone --depth 1 https://github.com/Nice-Wolf-Studio/unity-claude-skills

Made for: Claude Code.

Or install unity, the plugin that ships this one along with the rest of its 35 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.

agentmods badge for unity-scene-assets

README.md
[![agentmods](https://agentmods.dev/badge/skills/nice-wolf-studio/unity-claude-skills/unity-scene-assets/github.svg)](https://agentmods.dev/skills/nice-wolf-studio/unity-claude-skills/unity-scene-assets)
Your own site
<a href="https://agentmods.dev/skills/nice-wolf-studio/unity-claude-skills/unity-scene-assets"><img src="https://agentmods.dev/badge/skills/nice-wolf-studio/unity-claude-skills/unity-scene-assets/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-scene-assets

Your own site · 80×15
<a href="https://agentmods.dev/skills/nice-wolf-studio/unity-claude-skills/unity-scene-assets"><img src="https://agentmods.dev/badge/skills/nice-wolf-studio/unity-claude-skills/unity-scene-assets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,882 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
  • NVIDIA SkillSpector pass 7 Sept 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 $0.00059 $0.02882
Opus 5 $0.00030 $0.01441
Sonnet 5 $0.00012 $0.00576
Haiku 4.5 $0.00006 $0.00288

Measured 9d ago against content hash 502f35833277, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

unity-scene-assets 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 9d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/unity-scene-assets/SKILL.md · 328 lines

How it starts

The opening of the file, as written. The whole thing — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scene & Asset Management -- Decision Patterns

Prerequisite skills: unity-foundations/references/prefabs-and-scenes.md (SceneManager API, additive loading), unity-async-patterns (Addressables handle lifecycle, async loading), unity-game-architecture (bootstrap patterns)

These patterns address the most common asset management failures: Claude hardcodes Resources.Load, ignores async loading, and does not account for memory lifecycle.


PATTERN: Scene Architecture Strategy

WHEN: Structuring a project's scenes for a real game (not a prototype)

DECISION:

  • Single scene -- Game jam, prototype, tiny game. Everything in one scene. No loading, no complexity. Outgrow it quickly.
  • Scene-per-level -- Linear progression (platformers, puzzle games). LoadScene(name, LoadSceneMode.Single) between levels. Clean separation but no shared state without DontDestroyOnLoad.
  • Additive scene composition -- Open worlds, persistent HUD, shared systems. A "Boot" or "Persistent" scene stays loaded, gameplay/UI scenes load additively. Most flexible, most complex.

SCAFFOLD (Additive scene coordinator):

using UnityEngine;
using UnityEngine.SceneManagement;

public class SceneCoordinator : MonoBehaviour
{
    [SerializeField] private string persistentSceneName = "Persistent";
    private string _currentContentScene;

    public static SceneCoordinator Instance { get; private set; }

    void Awake()
    {
        if (Instance != null) { Destroy(gameObject); return; }
        Instance = this;
        DontDestroyOnLoad(gameObject);
    }

    [RuntimeInitializeOnLoadMethod(RuntimeInitializeLoadType.SubsystemRegistration)]
    static void ResetStatic() => Instance = null;

    /// <summary>
    /// Load a content scene additively, unloading the previous one.
    /// The persistent scene stays loaded.
    /// </summary>
    public async Awaitable LoadContentScene(string sceneName)
    {
        // Unload previous content scene
        if (!string.IsNullOrEmpty(_currentContentScene))
        {
            await SceneManager.UnloadSceneAsync(_currentContentScene);
        }

        // Load new content scene
        await SceneManager.LoadSceneAsync(sceneName, LoadSceneMode.Additive);
        _currentContentScene = sceneName;

        // Set active scene for lighting and new object spawning
        SceneManager.SetActiveScene(SceneManager.GetSceneByName(sceneName));
    }
}

Read the full file on GitHub · 328 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. 9d ago First seen · 328 lines · 59 tokens per session scan A 502f35833277

Subscribe to this mod's changes

unity-scene-assets is a skill published in the GitHub repository Nice-Wolf-Studio/unity-claude-skills (30 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 2,882 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.