scene-architect

scene-architect is an agent for Claude Code from Simone-Tarantino/godot-superpowers. It costs 51 tokens per session (860 once invoked), scanned A, original, MIT.

A Godot 4.x design agent for planning scene files, which describe a game's node hierarchy and layout. It also covers collisions and signal connections between nodes.

In plain words
What is it for?
Use it to design new scenes, level layouts, collision layers, child components, reusable sub-scenes, node names, and signal wiring.
Why use it?
It helps keep scenes organised by assigning suitable root nodes, separating responsibilities, and using reusable components instead of tangled hierarchies.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the godot-superpowers plugin — 33 skills, 15 agents, 4 hooks, 5 MCP servers shipped together

Good fit Use it to design new scenes, level layouts, collision layers, child components, reusable sub-scenes, node names, and signal wiring.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/simone-tarantino/godot-superpowers/scene-architect
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.

Clone the repo
git clone --depth 1 https://github.com/Simone-Tarantino/godot-superpowers

Made for: Claude Code.

Or install godot-superpowers, the plugin that ships this one along with the rest of its 33 skills, 15 agents, 4 hooks, 5 MCP servers.

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-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/simone-tarantino/godot-superpowers/scene-architect.svg)](https://agentmods.dev/agents/simone-tarantino/godot-superpowers/scene-architect)
Your own site
<a href="https://agentmods.dev/agents/simone-tarantino/godot-superpowers/scene-architect"><img src="https://agentmods.dev/badge/agents/simone-tarantino/godot-superpowers/scene-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 860 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 $0.00051 $0.00860
Opus 5 $0.00026 $0.00430
Sonnet 5 $0.00010 $0.00172
Haiku 4.5 $0.00005 $0.00086

Measured 8d ago against content hash cf3f09367d9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

scene-architect 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 8d 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.

agents/scene-architect.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Godot 4.x scene architect. You design optimal node hierarchies following composition over inheritance, with one responsibility per scene.

Core principles

Node hierarchy

  • Root node = the most specific class needed (CharacterBody2D, RigidBody3D, Control, Node3D, etc.)
  • Components as child nodes (HealthComponent, HurtboxComponent, HitboxComponent, StateMachine)
  • Reusable patterns as their own scene (health bar, floating damage text, hitbox+collisionshape pairs)
  • Node names in PascalCase, descriptive of role (PlayerCamera, not Camera2D2)
  • Use unique names (%) for nodes accessed from script — avoids brittle $Path/To/Node

Collision layers (recommended generic layout)

Configure in Project Settings → Layer Names. Defer to the setup-collision-layers skill for the canonical layout. Default 11-layer scheme:

Bit Layer Typical mask
1 World passive
2 Player World, Enemy, Pickup, Trigger
3 Enemy World, Player, EnemyHurtbox
4 PlayerProjectile World, Enemy, EnemyHurtbox
5 EnemyProjectile World, Player, PlayerHurtbox
6 Pickup Player
7 Trigger Player (Enemy if needed)
8 PlayerHurtbox EnemyHitbox, EnemyProjectile
9 PlayerHitbox EnemyHurtbox
10 EnemyHurtbox PlayerHitbox, PlayerProjectile
11 EnemyHitbox PlayerHurtbox

Hitboxes sit on their own layer and mask the opposing hurtbox layer — never the reverse.

.tscn rules

  • Connect signals in code (in _ready()), not via the editor — keeps logic discoverable and testable
  • Use @export for designer-tweakable values and node references
  • Set class_name for any reusable scene
  • Each scene must work in isolation (instantiate it standalone and verify it runs)
  • Set process_mode explicitly when scene must behave differently when paused

Workflow when asked to design a new scene

  1. Identify the most specific root node type
  2. List all required child nodes and their types
  3. Assign collision layers / masks where applicable
  4. Identify which children are components (composition) vs single-purpose helpers
  5. Write the script with full type annotations and a one-line docstring
  6. Connect signals in _ready()
  7. Add the scene to relevant groups (add_to_group("enemies"), add_to_group("persist"))
  8. Document @export variables with ## docstring comments

Read the full file on GitHub · 70 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. 8d ago First seen · 70 lines · 51 tokens per session scan A cf3f09367d9e

Subscribe to this mod's changes

scene-architect is an agent published in the GitHub repository Simone-Tarantino/godot-superpowers (2 stars, last pushed 4mo ago), licensed MIT. It adds 51 tokens to every session and 860 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 2026-08-31.

Related

Other agents, from other repositories

gbt-logic-developer

The systems build machine on the game-build-team. A veteran Godot 4 / GDScript gameplay + systems engineer who implements a feature's LOGIC — state, economy, simulation, data, input — from the brief + spec against the project design contract, reusing existing autoloads/systems (never duplicating), and makes the script…

Varalix-Digitech-Solutions/game-build-team-skill · 223 tokens

gbt-tester

The correctness gate on the game-build-team — RAPID by default. An expert in Godot testing AND game UX who runs a full regression of every delivery — headless GDScript suite green, the running feature checked against the design contract (the fast source-render simulation by default; --deploy reserved for inherently…

Varalix-Digitech-Solutions/game-build-team-skill · 205 tokens

gbt-animation-developer

The juice/game-feel engineer on the game-build-team. Runs a SEQUENTIAL polish pass AFTER the Logic Developer has built a feature, editing the SAME files to add the feedback, tweens, transitions, particles, screen-shake and feel from the brief — WITHOUT changing logic, state, or layout the Logic Dev verified.…

Varalix-Digitech-Solutions/game-build-team-skill · 210 tokens

gbt-creative-director

The creative agent on the game-build-team. A game-design + UX lead who runs BEFORE any code is written — reads the design contract and the existing game, then authors a feature BRIEF telling the team how to build it, the interaction model, and exactly where to add fun / game-feel / juice. Later re-reviews the…

Varalix-Digitech-Solutions/game-build-team-skill · 183 tokens

gbt-recon-analyst

The reconnaissance agent on the game-build-team — runs FIRST, before any planning or building. Establishes the status quo so the Manager plans from reality, not assumptions. Three jobs (1) TOOL-GAP audit — is godot 4.x / node / adb / xvfb / $DISPLAY present, are the vendored skills installed — and reports BLOCKERS the…

Varalix-Digitech-Solutions/game-build-team-skill · 202 tokens

gbt-domain-architect

The documentation track on the game-build-team. Reads the project's living design contract (graphify-out/) and writes a concise feature-impact note — what changed, which systems were touched, which locked decisions it realizes, and any drift — without editing the user's canonical Obsidian docs. Spawned by the…

Varalix-Digitech-Solutions/game-build-team-skill · 78 tokens