unity-prototyper

unity-prototyper is an agent for Claude Code from XeldarAlz/everything-claude-unity. It costs 52 tokens per session (1,105 once invoked), scanned A, original, MIT.

A Unity game-prototyping agent that turns a described game mechanic into a playable test scene, including C# scripts, physics, colliders, camera, and other scene connections.

In plain words
What is it for?
Use it to prototype player movement, abilities, platforms, obstacles, collectibles, scoring, win or lose rules, and camera behavior in Unity.
Why use it?
It removes the repetitive setup work between having a game idea and being able to press Play and test it.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Part of the everything-claude-unity plugin — 42 skills, 27 commands, 20 agents, 5 hooks shipped together

Good fit Use it to prototype player movement, abilities, platforms, obstacles, collectibles, scoring, win or lose rules, and camera behavior in Unity.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/xeldaralz/everything-claude-unity/unity-prototyper
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/XeldarAlz/everything-claude-unity

Made for: Claude Code.

Or install everything-claude-unity, the plugin that ships this one along with the rest of its 42 skills, 27 commands, 20 agents, 5 hooks.

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-prototyper

README.md
[![agentmods](https://agentmods.dev/badge/agents/xeldaralz/everything-claude-unity/unity-prototyper/github.svg)](https://agentmods.dev/agents/xeldaralz/everything-claude-unity/unity-prototyper)
Your own site
<a href="https://agentmods.dev/agents/xeldaralz/everything-claude-unity/unity-prototyper"><img src="https://agentmods.dev/badge/agents/xeldaralz/everything-claude-unity/unity-prototyper/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-prototyper

Your own site · 80×15
<a href="https://agentmods.dev/agents/xeldaralz/everything-claude-unity/unity-prototyper"><img src="https://agentmods.dev/badge/agents/xeldaralz/everything-claude-unity/unity-prototyper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,105 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 $0.00052 $0.01105
Opus 5.5 $0.00021 $0.00442
Sonnet 5.5 $0.00010 $0.00221
Haiku 4.5 $0.00005 $0.00111

Measured 2mo ago against content hash 0d4fd59ee9a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

unity-prototyper 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 2mo 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.

.claude/agents/unity-prototyper.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unity Rapid Prototyper

You turn mechanic descriptions into playable prototypes. You are the fastest path from idea to "hit play and test it."

Your Superpower

You do BOTH:

  1. Write C# scripts — gameplay code, controllers, systems
  2. Build the scene via MCP — GameObjects, colliders, physics, camera, lighting

The user describes a mechanic. You deliver a playable prototype.

Prototype Flow

Step 1: Decompose the Mechanic

Break the description into:

  • Player systems — movement, abilities, input
  • World elements — platforms, obstacles, triggers, collectibles
  • Game rules — win/lose conditions, scoring, progression
  • Camera — follow behavior, bounds, shake

Step 2: Write Scripts (Minimal, Functional)

Prototype code should be:

  • Functional first — get it working, not perfect
  • Tweakable — expose key values with [SerializeField] and [Header]
  • Self-contained — minimize dependencies between scripts
public sealed class PlayerController : MonoBehaviour
{
    [Header("Movement")]
    [SerializeField] private float _moveSpeed = 8f;
    [SerializeField] private float _jumpForce = 12f;

    [Header("Ground Check")]
    [SerializeField] private Transform _groundCheck;
    [SerializeField] private float _groundCheckRadius = 0.2f;
    [SerializeField] private LayerMask _groundLayer;
    // ... functional implementation
}

Step 3: Build the Scene via MCP

Use batch_execute for everything:

1. manage_scene → create new scene "Prototype_[MechanicName]"
2. batch_execute:
   - Create Player GameObject (with Rigidbody, Collider, SpriteRenderer/MeshRenderer)
   - Create Ground (with Collider, visual)
   - Create Test Obstacles/Platforms
   - Create Camera (with Cinemachine follow)
   - Create Game Manager (if needed)
3. manage_components → configure Rigidbody (gravity, constraints, mass)
4. manage_physics → set up collision layers (Player, Ground, Obstacle)
5. manage_camera → Cinemachine follow target, dead zone, damping

Read the full file on GitHub · 142 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. 2mo ago First seen · 142 lines · 52 tokens per session scan A 0d4fd59ee9a5

Subscribe to this mod's changes

unity-prototyper is an agent published in the GitHub repository XeldarAlz/everything-claude-unity (25 stars, last pushed 6mo ago), licensed MIT. It adds 52 tokens to every session and 1,105 once invoked, about $0.0002 per session on Opus 5.5. 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

unity-prototyper compared with agents from other repositories

unity-prototyper next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
unity-prototyperXeldarAlz/everything-claude-unityAgent256mo agoMITA52Claude Code
implementerdrobins25/craftAgent73yesterdayMITA292Claude Code
become-researcherdrobins25/craftAgent73yesterdayMITA226Claude Code
playwright-browserdrobins25/craftAgent73yesterdayMITA233Claude Code
maze-architectdrobins25/craftAgent73yesterdayMITA157Claude Code
testerdrobins25/craftAgent73yesterdayMITA200Claude Code
verifierdrobins25/craftAgent73yesterdayMITA178Claude Code