scene-architecture

scene-architecture is a skill for Claude Code from TheArcForge/UniClaude. It costs 27 tokens per session (892 once invoked), scanned A, original, MIT.

A Unity game-development guide for organizing scenes, which are the saved environments and game states that contain objects and settings.

In plain words
What is it for?
Use it to plan menus, levels, results screens, persistent managers, loading transitions, and large worlds divided into streamed sections.
Why use it?
It helps choose a scene structure that fits the project, from a small single scene to multiple scenes loaded together or by distance.

Skill for Claude Code

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

Part of the uniclaude plugin — 11 skills shipped together

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.

agentmods
npx agentmods add skills/thearcforge/uniclaude/scene-architecture
Any agent
npx skills add TheArcForge/UniClaude --skill scene-architecture
Clone the repo
git clone --depth 1 https://github.com/TheArcForge/UniClaude

Made for: Claude Code.

Or install uniclaude, the plugin that ships this one along with the rest of its 11 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 scene-architecture

README.md
[![agentmods](https://agentmods.dev/badge/skills/thearcforge/uniclaude/scene-architecture.svg)](https://agentmods.dev/skills/thearcforge/uniclaude/scene-architecture)
Your own site
<a href="https://agentmods.dev/skills/thearcforge/uniclaude/scene-architecture"><img src="https://agentmods.dev/badge/skills/thearcforge/uniclaude/scene-architecture.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 892 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00027 $0.00892
Opus 5 $0.00014 $0.00446
Sonnet 5 $0.00005 $0.00178
Haiku 4.5 $0.00003 $0.00089

Measured 6d ago against content hash f91527be8959, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

scene-architecture 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 6d 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.

Sidecar~/skills/scene-architecture/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scene Architecture — Full Decision Framework

Use this when unity-architect's condensed scene section needs more depth.

DECISION: Scene Organization Pattern

When this applies: Deciding how to split a game into scenes.

Options:

  1. Monolithic (single scene) — entire game in one scene.

    • Use when: game jam, prototype, very small game (< 50 GameObjects total).
    • Tradeoff: cannot stream content, large file, merge conflicts in teams.
  2. Scene-per-state — Menu scene, Game scene, Results scene, etc.

    • Use when: distinct game states with clean boundaries.
    • Tradeoff: need persistent managers (audio, network) that survive loads.
    • Transition: LoadScene (replaces) or LoadSceneAsync for loading screens.
  3. Bootstrap + additive — one persistent scene + content scenes loaded/unloaded.

    • Use when: persistent UI, managers, or audio across multiple levels.
    • Tradeoff: more complex loading logic, must manage active scene.
    • Pattern: Bootstrap loads first (scene 0 in build), then loads content additively.
  4. Streaming (additive + distance) — world divided into chunks loaded by proximity.

    • Use when: open world, large levels, seamless transitions.
    • Tradeoff: complex trigger system, memory management, cross-scene references impossible.

Decision tree:

Is the game small enough for one scene?
├── YES → Monolithic
└── NO → Are there persistent systems across states?
    ├── NO → Scene-per-state (simple LoadScene)
    └── YES → Bootstrap + additive
              └── Is the world large/seamless? → Streaming chunks

DECISION: Persistent Managers

When this applies: Systems that must survive scene transitions (audio, networking, input, game state).

Options:

  1. Bootstrap scene (recommended) — managers live in a scene that is never unloaded.
    • Setup: Create a minimal scene with manager GameObjects. Set as scene 0 in build.
    • On start: bootstrap loads, then loads first content scene additively.
    • Benefit: managers are inspectable, debuggable, follow normal lifecycle.

Read the full file on GitHub · 92 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. 6d ago First seen · 92 lines · 27 tokens per session scan A f91527be8959

Subscribe to this mod's changes

scene-architecture is a skill published in the GitHub repository TheArcForge/UniClaude (51 stars, last pushed 3mo ago), licensed MIT. It adds 27 tokens to every session and 892 once invoked, about $0.0001 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.