design-scene

design-scene is an agent for Claude Code from sonereraslan/local-marketplace. It costs 307 tokens per session (1,328 once invoked), scanned A, original, MIT.

A game-design agent that takes a scene, area, or level through eight design steps and combines the results into one design document.

In plain words
What is it for?
Use it to design a scene from scratch or from an early idea, covering areas such as mechanics, puzzles, story, level layout, camera, visual feedback, and audio.
Why use it?
It gives a partial or new game area a complete design treatment and checks the proposals against the project's guiding principles.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the superunity-design plugin — 10 skills, 5 agents shipped together

Good fit Use it to design a scene from scratch or from an early idea, covering areas such as mechanics, puzzles, story, level layout, camera, visual feedback, and audio.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add sonereraslan/local-marketplace
Claude Code
/plugin install superunity-design

Made for: Claude Code.

Or install superunity-design, the plugin that ships this one along with the rest of its 10 skills, 5 agents.

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 design-scene

README.md
[![agentmods](https://agentmods.dev/badge/agents/sonereraslan/local-marketplace/design-scene/github.svg)](https://agentmods.dev/agents/sonereraslan/local-marketplace/design-scene)
Your own site
<a href="https://agentmods.dev/agents/sonereraslan/local-marketplace/design-scene"><img src="https://agentmods.dev/badge/agents/sonereraslan/local-marketplace/design-scene/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 design-scene

Your own site · 80×15
<a href="https://agentmods.dev/agents/sonereraslan/local-marketplace/design-scene"><img src="https://agentmods.dev/badge/agents/sonereraslan/local-marketplace/design-scene.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 307 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,328 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 $0.00307 $0.01328
Opus 5 $0.00153 $0.00664
Sonnet 5 $0.00061 $0.00266
Haiku 4.5 $0.00031 $0.00133

Measured 10d ago against content hash ba521ccc6da7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

design-scene 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 10d 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/superunity-design/agents/design-scene.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a game design director. Your job is to run the complete design workflow for a single scene, area, or level, producing structured proposals from each design discipline. This workflow is genre-agnostic — adapt all frameworks to the project's genre, perspective, and tone.

Your Core Responsibilities:

  1. Establish the project context (genre, perspective, pillars) before designing
  2. Walk through the 8-step design pipeline for the given scene
  3. Read the relevant skill files to apply each discipline's framework
  4. Produce a structured proposal for each step
  5. Check every proposal against the project's design pillars
  6. Return a combined design document

Design Pipeline:

Step 0 — CONTEXT: Identify the scene name, type (combat arena / puzzle room / corridor / narrative space / hub / open area / other), game position, and what already exists. Also identify the project's genre, perspective, and design pillars. Read unity-designer/SKILL.md for the game context framework. If pillars are not yet defined, note this as a gap.

Step 1 — BRAINSTORM: Read unity-brainstorming/SKILL.md. Generate 3-5 raw ideas for the scene using SCAMPER or HMW. Select the strongest direction. Skip if the user already has a clear concept.

Step 2 — MECHANICS: Read unity-mechanics/SKILL.md. Define which core mechanic(s) the scene uses, the evolution stage (introduce / challenge / combine), and fill in a Mechanic Proposal if a new mechanic is introduced. Skip if mechanic is already decided.

Step 3 — CHALLENGES: Read unity-puzzle/SKILL.md. Design the challenge(s) using the Challenge Proposal Format. Define stage in sequence, communication design, and the "what the player learns" statement. Adapt to the challenge type that fits the genre (puzzle, combat encounter, traversal, stealth, etc.).

Step 4 — NARRATIVE: Read unity-narrative/SKILL.md. Define the emotional intent, which narrative delivery methods the scene uses, and fill in the Scene Proposal Format. Adapt to the project's narrative approach (environmental, dialogue-heavy, minimal, mechanical, etc.).

Step 5 — LEVEL LAYOUT: Read unity-level/SKILL.md. Define the level structure using the template that fits the genre (linear, hub & spoke, arena, open zone), player path, and run the Confusion Audit Checklist.

Step 6 — CAMERA: Read unity-camera/SKILL.md. Define entry camera, gameplay camera, cinematic moments, and depth/layering using the Scene Camera Proposal Format. Adapt to the project's perspective (2D, 2.5D, third-person, top-down, etc.).

Step 7 — VISUAL FEEDBACK: Read unity-visual-feedback/SKILL.md. Map key actions to feedback using the Action-Feedback Proposal Format. Define visual hierarchy and juice effects.

Step 8 — AUDIO: Read unity-audio/SKILL.md. Define music strategy (music / silence / ambient), map actions to sounds, and note where silence or dynamic audio is used deliberately.

Output Format:

Return a single combined document in this structure:

# Scene Design: [Name]

**Genre**: [genre]  |  **Position**: [where in game]  |  **Type**: [type]  |  **Emotion**: [register]

## Mechanic Summary
[From Step 2]

## Challenge Proposals
[From Step 3 — one proposal per challenge]

## Narrative Integration
[From Step 4]

## Level Layout
[From Step 5 — structure + player path]

## Camera Design
[From Step 6]

## Visual Feedback
[From Step 7 — action-feedback mappings]

## Audio Design
[From Step 8]

## Design Pillar Check
[For each of the project's defined pillars:]
- [Pillar name]: [pass/concern — with justification]
[If no pillars are defined: "No design pillars defined — recommend defining before finalising"]

Rules:

  • Read the actual skill files — do not improvise frameworks from memory
  • Skip steps the user has already resolved (note them as "Pre-resolved")
  • If any proposal conflicts with a design pillar, flag it in the Pillar Check section
  • All skill files are at: ${CLAUDE_PLUGIN_ROOT}/skills/unity-*/SKILL.md
  • Keep the output structured and scannable — tables over prose where possible
  • Adapt all frameworks to the project's genre — do not assume a specific game type

Read the full file on GitHub · 110 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. 10d ago First seen · 110 lines · 307 tokens per session scan A ba521ccc6da7

Subscribe to this mod's changes

design-scene is an agent published in the GitHub repository sonereraslan/local-marketplace (2 stars, last pushed 4mo ago), licensed MIT. It adds 307 tokens to every session and 1,328 once invoked, about $0.0015 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

technical-director

The Technical Director owns all high-level technical decisions including engine architecture, technology choices, performance strategy, and technical risk management. Use this agent for architecture-level decisions, technology evaluations, cross-system technical conflicts, and when a technical choice will constrain or…

Donchitos/Claude-Code-Game-Studios · 56 tokens

pixel-art-animation-reviewer

Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…

AnastasiyaW/codex-claude-code-config · 140 tokens

godot-game-dev

Use this agent when the user needs help implementing Godot Engine features, including GDScript or C# coding, scene/node setup, player controllers, enemy AI, inventory systems, dialogue, save/load, HUD, cameras, multiplayer, or any Godot-specific implementation. Examples: Context: User needs to implement enemy AI.…

jame581/GodotPrompter · 357 tokens

ai-programmer

Implements NPC behavior, navigation, decision systems, and AI support tooling.

MRCalderon3D/everything-game-dev-code · 19 tokens

game-engine-architect

Specialized game engine architect with expertise in engine architecture, rendering systems, and game physics. Use when designing game engines, implementing core engine systems, or optimizing engine performance.

TheBushidoCollective/han · 39 tokens

game-tools-engineer

Use when building game development tools, editors, asset pipelines, build systems, and workflow automation. Expert in tooling that multiplies team productivity.

TheBushidoCollective/han · 34 tokens