unity-ai-bridge: Skill for Claude Code

.claude/skills/unity-bridge/SKILL.md

unity-bridge is a skill for Claude Code from butterlatte-zhang/unity-ai-bridge. It costs 52 tokens per session (1,188 once invoked), scanned A, original, Apache-2.0.

A skill for controlling the Unity Editor through file-based communication. Unity is a game-development editor for scenes, objects, assets, scripts, and related project data.

In plain words
What is it for?
Use it to manage scenes and game objects, edit assets and prefabs, run scripts, inspect runtime behavior, profile projects, and take screenshots.
Why use it?
It lets an agent inspect and change Unity projects through defined operations instead of relying only on manual editor work.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

This is butterlatte-zhang/unity-ai-bridge's own configuration. It tells Claude Code how to work on unity-ai-bridge itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything unity-ai-bridge configures →

Reuse

Borrowing it

Nothing to install: this file belongs to butterlatte-zhang/unity-ai-bridge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/butterlatte-zhang/unity-ai-bridge/main/.claude/skills/unity-bridge/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/butterlatte-zhang/unity-ai-bridge

Made for: Claude Code.

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-bridge

README.md
[![agentmods](https://agentmods.dev/badge/skills/butterlatte-zhang/unity-ai-bridge/unity-bridge/github.svg)](https://agentmods.dev/skills/butterlatte-zhang/unity-ai-bridge/unity-bridge)
Your own site
<a href="https://agentmods.dev/skills/butterlatte-zhang/unity-ai-bridge/unity-bridge"><img src="https://agentmods.dev/badge/skills/butterlatte-zhang/unity-ai-bridge/unity-bridge/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-bridge

Your own site · 80×15
<a href="https://agentmods.dev/skills/butterlatte-zhang/unity-ai-bridge/unity-bridge"><img src="https://agentmods.dev/badge/skills/butterlatte-zhang/unity-ai-bridge/unity-bridge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,188 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 $0.01188
Opus 5 $0.00026 $0.00594
Sonnet 5 $0.00010 $0.00238
Haiku 4.5 $0.00005 $0.00119

Measured 10d ago against content hash ed56dbc3bdd0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

unity-bridge 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.

The scan reads SKILL.md. This mod also ships 2 executable files (bridge.py, mcp_server.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/unity-bridge/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unity Bridge

Interact with Unity Editor via file-based IPC. Always read params/{tool}.json before calling a tool to get accurate parameters.

Invocation

bridge.py is located in the same directory as this SKILL.md. Run from the Unity project root:

python3 <skill-dir>/bridge.py <tool-name> '<json-params>'

where <skill-dir> is the directory containing this file. Omit JSON when no parameters are needed.

Critical Rules

  1. Pre-check: Unity Editor must be running. Verify via Temp/UnityBridge/heartbeat
  2. Read params first: Always read params/{tool-name}.json before calling — do not guess parameters from memory
  3. camelCase: JSON parameter keys must be camelCase. PascalCase keys are ignored
  4. Serial execution: Only one tool call at a time. Concurrent calls are queued
  5. Param source: JSON files under params/ are auto-generated from C# tool method signatures

Tool Index (65 tools)

Scene (7): scene-list-opened list opened scenes · scene-get-data get scene data · scene-open open scene · scene-create create scene · scene-save save scene · scene-set-active set active scene · scene-unload unload scene

GameObject (11): gameobject-find find · gameobject-create create · gameobject-destroy destroy · gameobject-modify modify properties · gameobject-duplicate duplicate · gameobject-set-parent set parent · gameobject-component-add add component · gameobject-component-destroy remove component · gameobject-component-get get component data · gameobject-component-list-all list components · gameobject-component-modify modify component

Assets (11): assets-find search assets · assets-find-built-in search built-in assets · assets-get-data get asset data · assets-modify modify asset · assets-copy copy · assets-move move · assets-delete delete · assets-refresh refresh AssetDatabase · assets-create-folder create folder · assets-material-create create material · assets-shader-list-all list shaders

Read the full file on GitHub · 84 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 84 lines · 52 tokens per session scan A ed56dbc3bdd0

Subscribe to this mod's changes

unity-bridge is a skill published in the GitHub repository butterlatte-zhang/unity-ai-bridge (20 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,188 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 2026-08-30.

Related

Other skills, from other repositories

unreal-actor-editing

Manage actors in UE levels via UCP. Use when the user asks to spawn, delete, move, duplicate, select, or otherwise manipulate actors in the Unreal Engine editor.

Italink/UnrealClientProtocol · 42 tokens

unreal-niagara-editing

Edit Niagara systems, emitters, and scripts via UCP. Use when the user asks to create/modify particle effects, manage emitters, configure modules, set module inputs, edit Niagara script graphs, or any Niagara VFX operation.

Italink/UnrealClientProtocol · 55 tokens

unreal-modeling-meshops

A reference skill for editing and repairing 3D meshes in Unreal Engine, a game-development tool. It covers operations such as simplification, remeshing, Boolean changes, voxel processing, subdivision, and basic editing.

Italink/UnrealClientProtocol · 48 tokens

unreal-modeling-primitives

A set of Unreal Engine GeometryScript operations for creating basic 3D mesh shapes and applying common modeling operations. These shapes include boxes, spheres, cylinders, capsules, cones, toruses, and discs.

Italink/UnrealClientProtocol · 49 tokens

unreal-modeling-asset

A guide for editing Unreal Engine StaticMesh assets, which are reusable 3D models, and creating or changing their collision shapes.

Italink/UnrealClientProtocol · 44 tokens

unreal-modeling-attributes

A GeometryScript guide for reading and changing attributes on Unreal Engine mesh geometry. These attributes include vertex colours, polygroups, and material IDs.

Italink/UnrealClientProtocol · 32 tokens