agentmods.dev

unity-experience-builder

unity-experience-builder is a skill for Claude Code from qfoldit/Protein-Design-MCP. It costs 94 tokens per session (825 once invoked), scanned A, original, Apache-2.0.

A workflow for turning a validated Universal Assembly Graph—a structured description of objects and their relationships—into a live Unity scene. Unity is a game and real-time 3D engine, and this workflow uses a community bridge that is not made by Unity Technologies.

In plain words
What is it for?
Use it to build Unity scenes from descriptions of meshes, lights, parent-child relationships, physics, and grab interactions.
Why use it?
It provides a documented way to create Unity objects from the graph while making the bridge's unofficial status clear.

Skill for Claude Code

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

Part of the qfoldit-skills plugin — 20 skills shipped together

not rated 1repo 2mo ago A scan 94 tokens original Apache-2.0

Good fit Use it to build Unity scenes from descriptions of meshes, lights, parent-child relationships, physics, and grab interactions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/qfoldit/protein-design-mcp/unity-experience-builder
View source ↗ qfoldit/Protein-Design-MCP
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 qfoldit/Protein-Design-MCP --skill unity-experience-builder
Clone the repo
git clone --depth 1 https://github.com/qfoldit/Protein-Design-MCP

Made for: Claude Code.

Or install qfoldit-skills, the plugin that ships this one along with the rest of its 20 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-experience-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/qfoldit/protein-design-mcp/unity-experience-builder/github.svg)](https://agentmods.dev/skills/qfoldit/protein-design-mcp/unity-experience-builder)
Your own site
<a href="https://agentmods.dev/skills/qfoldit/protein-design-mcp/unity-experience-builder"><img src="https://agentmods.dev/badge/skills/qfoldit/protein-design-mcp/unity-experience-builder/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-experience-builder

Your own site · 80×15
<a href="https://agentmods.dev/skills/qfoldit/protein-design-mcp/unity-experience-builder"><img src="https://agentmods.dev/badge/skills/qfoldit/protein-design-mcp/unity-experience-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 825 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 $0.00094 $0.00825
Opus 5.5 $0.00038 $0.00330
Sonnet 5.5 $0.00019 $0.00165
Haiku 4.5 $0.00009 $0.00082

Measured 2mo ago against content hash 56bb7fb2379d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

unity-experience-builder 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-skills/skills/unity-experience-builder/SKILL.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

unity-experience-builder

Status: community, NOT official Unity Technologies. Built on CoplayDev/unity-mcp, which explicitly states it is "not affiliated with Unity Technologies." It is the de-facto standard today (MIT, 5800+ stars) but must never be described as an official Unity product in any qFoldIT material. If Unity Technologies ships a first-party MCP integration, prefer it over this one per the plugin's "prefer official" principle.

Prerequisites

  1. Unity 2021.3 LTS -> 6.x, Python 3.10+ (via uv).
  2. Package install: Window -> Package Manager -> + -> Add package from git URL: https://github.com/CoplayDev/unity-mcp.git?path=/MCPForUnity#main
  3. Window -> MCP for Unity -> Configure All Detected Clients to wire up Claude Code/Desktop automatically.
  4. Verify: ask for something trivial ("create a cube at the origin with a Rigidbody") and confirm it appears in the scene.

UAG -> Unity mapping

Baseline from game-designer/references/uag_schema.md (mesh -> GameObject+MeshRenderer, light -> GameObject+Light, parent_child -> Transform.SetParent, physics_collision -> Collider+Rigidbody, on_grab -> XR Interaction Toolkit Grabbable).

Key tools (by domain)

manage_gameobject (create/modify GameObjects+components), manage_material, manage_script (create/edit via apply_text_edits), manage_physics (collision layers, joints, raycasts, forces), manage_animation, manage_profiler, batch_execute (multiple calls in one round-trip). Activate only the tool groups you need (vfx/animation/ui/testing/probuilder) rather than all of them at once, for cleaner routing.

Workflow

  1. Confirm the UAG passed game-designer/scripts/uag_validate.py.
  2. Walk nodes in hierarchy order (parents before children where possible), calling manage_gameobject per node per the mapping table; unmapped type/trigger values (validator warnings) get flagged to the user, not silently skipped.
  3. Apply constraints/interactions via manage_physics/scripted components as appropriate.
  4. Prefer batch_execute for sets of related calls (e.g. all children of one parent) over many sequential single calls.

Read the full file on GitHub · 42 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 · 42 lines · 94 tokens per session scan A 56bb7fb2379d

Subscribe to this mod's changes

unity-experience-builder is a skill published in the GitHub repository qfoldit/Protein-Design-MCP (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 94 tokens to every session and 825 once invoked, about $0.0004 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 2026-08-31.

Game development
Related

unity-experience-builder compared with skills from other repositories

unity-experience-builder next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
unity-experience-builderqfoldit/Protein-Design-MCPSkill12mo agoApache-2.0A94Claude Code
playtest-reportDonchitos/Claude-Code-Game-StudiosSkill36k19d agoMITA20Claude Code
godot-signals-groupsgamedev-skills/awesome-gamedev-agent-skillsSkill6.9k10d agoApache-2.0A95Claude Code
scenario-unreal-gameplayscenario-labs/skillsSkill3.2kyesterdayMITA121Claude Code
motionOpenDCAI/GameFactory-3ASkill1.0k9d agoApache-2.0A0Claude Code, Codex
unity-addressablesBesty0728/Unity-SkillsSkill1.9kyesterdayMITA25Claude Code, Codex
unity-manual-componentBesty0728/Unity-SkillsSkill1.9kyesterdayMITA36Claude Code, Codex