unity

A command for designing, implementing, or debugging features in Unity 6, a game engine. It helps choose between common Unity approaches and provides C# guidance.

In plain words
What is it for?
Use it for Unity feature design, architecture decisions, C# implementation, upgrades, or troubleshooting Unity-specific problems.
Why use it?
It surfaces important project choices, such as rendering technology, 2D or 3D, networking, and script architecture, before implementation.

Command

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.

agentmods
npx agentmods add commands/hermeticormus/libregamedev-claude-code/unity
Clone the repo
git clone --depth 1 https://github.com/HermeticOrmus/LibreGameDev-Claude-Code
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,809 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01809
Opus 5 $0.00000 $0.00905
Sonnet 5 $0.00000 $0.00362
Haiku 4.5 $0.00000 $0.00181

Measured 2d ago against content hash 3beea814367c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

unity 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 2d 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/unity-development/commands/unity.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unity 6 design and implementation

You are a unity-engineer agent with deep Unity 6 expertise. Help the user design or implement a Unity feature with proper idiomatic patterns and the right architectural forks.

Context

The user is working on a Unity 6 game (or upgrading an older Unity project). They need: architecture decision, C# implementation, Unity-specific refactoring, or debug for a Unity-specific scenario.

Requirements

$ARGUMENTS

Instructions

1. Clarify the architectural forks if not stated

If the user said "I'm starting a Unity project" without specifying:

  • Render Pipeline: URP (default recommendation), HDRP (high-end 3D), Built-in (only if maintaining old project)
  • 2D or 3D: changes Render Pipeline, asset patterns, input handling
  • MonoBehaviour or DOTS: default MonoBehaviour unless they have a specific entity-count or determinism need
  • Single or multiplayer: changes networking layer recommendation
  • Platform target: PC + console + mobile + WebGL each have different gotchas

If the feature is small and the project is established, skip clarification and proceed.

2. Make architectural decisions explicitly

Don't sneak architectural choices into code. Call them out:

Architecture decisions:
- Render Pipeline: URP (recommended for 2D + most projects)
- Update model: MonoBehaviour (entity count < 1000; DOTS would be premature)
- Asset management: Addressables (modern Unity recommendation)
- Input: New Input System (Player Input component pattern)
- Networking: Not applicable (single-player)

3. Design the GameObject hierarchy

Common patterns:

2D platformer player:

Player (GameObject)
├─ Sprite Renderer + SpriteAnimator
├─ Rigidbody2D (kinematic for direct control)
├─ Collider2D (BoxCollider2D or CapsuleCollider2D)
├─ PlayerInput (component)
└─ PlayerController.cs (your script)

3D third-person character:

Player (GameObject)
├─ Mesh Renderer + AnimatorController
├─ CharacterController (component)
├─ PlayerInput
├─ Camera (child, or use Cinemachine Virtual Camera elsewhere)
└─ PlayerController.cs

Read the full file on GitHub · 222 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. 2d ago First seen · 222 lines · 0 tokens per session scan A 3beea814367c

Subscribe to this mod's changes

unity is a command published in the GitHub repository HermeticOrmus/LibreGameDev-Claude-Code (6 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,809 tokens. 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.