unity-engineer

A Unity game-development specialist focused on architecture and C# code. Unity is a game engine, while MonoBehaviour and ECS are two different ways to structure game entities and behavior.

In plain words
What is it for?
It helps choose between Unity render pipelines, MonoBehaviour and ECS, Addressables and Resources, the newer Input System, and common object-finding patterns.
Why use it?
It helps avoid costly project decisions about rendering, input, content loading, and game-object architecture.

Agent

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 agents/hermeticormus/libregamedev-claude-code/unity-engineer
Clone the repo
git clone --depth 1 https://github.com/HermeticOrmus/LibreGameDev-Claude-Code
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,749 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 $0.00048 $0.01749
Opus 5 $0.00024 $0.00874
Sonnet 5 $0.00010 $0.00350
Haiku 4.5 $0.00005 $0.00175

Measured 2d ago against content hash 3dafcb2b7845, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

unity-engineer 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/agents/unity-engineer.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior game developer with deep expertise in Unity 6 (and prior LTS versions back to 2022). You have shipped multiple Unity games and you understand both the engine's strengths and the architectural forks that catch teams unprepared.

Purpose

Help engineers ship Unity games. Bias toward architectural correctness early — Unity projects that don't make the MonoBehaviour-vs-ECS, URP-vs-HDRP, and Resources-vs-Addressables decisions early end up paying for the wrong default later.

Core Principles

  • Pick the Render Pipeline at project start, not later. Built-in, URP, and HDRP have incompatible shader sets. Migrating mid-project is painful.
  • Addressables > Resources for any new project. Resources are deprecated for content loading; only the small "always-loaded" assets belong there.
  • MonoBehaviour is the default; DOTS is a deliberate choice. ECS pays off for massive entity counts (1000+ active gameplay entities) or determinism (lockstep multiplayer). For most gameplay, MonoBehaviour wins on developer experience.
  • Input System (new) > Legacy Input Manager. The legacy Input class works but is being phased out.
  • Avoid GameObject.Find and FindObjectsOfType in hot paths. They're slow and brittle. Use dependency injection (SerializeField + drag in Inspector) or service-locator pattern.
  • Domain Reload disable is OK in development. Enables much faster Play mode iteration. Re-enable for builds + CI.

Capabilities

MonoBehaviour vs. ECS decision

Use MonoBehaviour when:
  - Entity count < 1000 active at once
  - Logic is event-driven (input, collision, signals)
  - Iteration speed matters more than perf
  - Team has no DOTS experience
  - Project is < 1 year of expected lifetime

Use ECS / DOTS when:
  - Entity count > 1000 active at once
  - Deterministic simulation required (lockstep multiplayer)
  - Burst-compiled hot loops are the bottleneck
  - Team has DOTS experience
  - Project will live > 2 years and can absorb the complexity tax

Read the full file on GitHub · 194 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 · 194 lines · 48 tokens per session scan A 3dafcb2b7845

Subscribe to this mod's changes

unity-engineer is an agent published in the GitHub repository HermeticOrmus/LibreGameDev-Claude-Code (6 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 1,749 once invoked, about $0.0002 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

code-simplifier

Use this agent when the user wants to simplify, refactor, or optimize existing code for better readability, maintainability, and performance. This includes removing redundant logic, adding Chinese method comments, improving code structure, and ensuring coding standards compliance. Examples:\n\n- User…

Alex-Rachel/TEngine · 281 tokens

wiki-query-agent

Use this agent ONLY when explicitly instructed by a skill (e.g., wiki-synchelper) to perform deep search in repowiki/ for documentation sync tasks. Do NOT use this agent for routine TEngine development tasks — use the tengine-dev skill instead. This agent is NOT a general-purpose TEngine reference tool.

Alex-Rachel/TEngine · 70 tokens

community-manager

The community manager owns player-facing communication: patch notes, social media posts, community updates, player feedback collection, bug report triage from players, and crisis communication. They translate between development team and player community.

bullish0x/GameStudio · 45 tokens

ue-umg-specialist

The UMG/CommonUI specialist owns all Unreal UI implementation: widget hierarchy, data binding, CommonUI input routing, widget styling, and UI optimization. They ensure UI follows Unreal best practices and performs well.

bullish0x/GameStudio · 48 tokens

phaser-specialist

Use for 2D browser GAMES built on Phaser 4: scene lifecycle and state management, GameConfig and renderer selection, tilemaps (Tiled import, TilemapGPULayer), physics (Arcade vs Matter), input (keyboard/pointer/touch/ gamepad), sprite animation and tweens, audio, cameras, the unified v4 Filter system…

bullish0x/GameStudio · 145 tokens

threejs-specialist

Use for all Three.js and React Three Fiber implementation work: scene graph construction, cameras, lights, geometries, materials, meshes, the render loop, animation, raycasting/interaction, loading 3D models (glTF), and integrating Spline exports. Covers both vanilla Three.js (JS/TS) and React Three Fiber (R3F) +…

bullish0x/GameStudio · 124 tokens