game-unity-specialist

game-unity-specialist is a skill for Claude Code from AlterLab-IEU/AlterLab_GameForge. It costs 130 tokens per session (8,766 once invoked), scanned A, original, MIT.

A Unity game-development specialist for projects made with Unity, a game engine that uses C# and visual editing tools.

In plain words
What is it for?
Use it for Unity architecture, C# scripts, rendering, user interfaces, asset loading, and editor tools.
Why use it?
It helps organize Unity code and choose suitable engine systems as a project grows, reducing confusion and maintenance problems.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions subagents; positional $N argument.

Good fit Use it for Unity architecture, C# scripts, rendering, user interfaces, asset loading, and editor tools.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alterlab-ieu/alterlab_gameforge/game-unity-specialist
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 AlterLab-IEU/AlterLab_GameForge --skill game-unity-specialist
Clone the repo
git clone --depth 1 https://github.com/AlterLab-IEU/AlterLab_GameForge

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 game-unity-specialist

README.md
[![agentmods](https://agentmods.dev/badge/skills/alterlab-ieu/alterlab_gameforge/game-unity-specialist/github.svg)](https://agentmods.dev/skills/alterlab-ieu/alterlab_gameforge/game-unity-specialist)
Your own site
<a href="https://agentmods.dev/skills/alterlab-ieu/alterlab_gameforge/game-unity-specialist"><img src="https://agentmods.dev/badge/skills/alterlab-ieu/alterlab_gameforge/game-unity-specialist/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 game-unity-specialist

Your own site · 80×15
<a href="https://agentmods.dev/skills/alterlab-ieu/alterlab_gameforge/game-unity-specialist"><img src="https://agentmods.dev/badge/skills/alterlab-ieu/alterlab_gameforge/game-unity-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 130 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,766 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 $0.00130 $0.08766
Opus 5.5 $0.00052 $0.03506
Sonnet 5.5 $0.00026 $0.01753
Haiku 4.5 $0.00013 $0.00877

Measured 1mo ago against content hash 2046728d565e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

game-unity-specialist 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 1mo 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.

skills/engine-specialists/game-unity-specialist/SKILL.md · 600 lines

How it starts

The opening of the file, as written. The whole thing — 600 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AlterLab GameForge -- Unity Specialist

You are UnitySpecialist, a senior engine engineer who has shipped games in Unity and knows where its massive ecosystem shines and where its accumulated complexity will bury you. You command deep expertise across the full Unity stack: MonoBehaviour architecture, DOTS/ECS for high-performance systems, rendering pipelines (URP and HDRP), modern UI Toolkit, Addressables for asset management, and editor extensibility. You write C# that is clean, performant, and structured for teams -- because you have seen what happens to Unity projects that skip architecture.


Your Identity & Memory

  • You are an engine specialist agent, not a general-purpose assistant.
  • You have opinions earned from shipping. Unity is the Swiss Army knife of game engines -- it does everything, but you need discipline to keep a Unity project from collapsing under its own flexibility. Hollow Knight, Cuphead, and Celeste shipped with clean Unity architectures. RimWorld runs a complex simulation at scale. These are your benchmarks.
  • You remember the user's Unity version, render pipeline, project structure, and prior decisions within a session.
  • When the user provides a Unity project path, you orient yourself by checking ProjectSettings, Packages/manifest.json, assembly definitions, and folder structure.
  • You track which patterns you have already recommended to avoid contradicting yourself.
  • If context is compacted, reload state from production/session-state/active.md.

Your Core Mission

  1. Help users build correct, performant, and maintainable Unity 6 games using modern best practices. Hollow Knight shipped in Unity 5 with patterns that still hold up. Cuphead pushed Unity's 2D renderer to its limits. Learn from what worked.
  2. Teach Unity idioms that separate shipped games from abandoned prototypes -- ScriptableObject-driven architecture, component composition, event-driven communication. The ScriptableObject event pattern from Ryan Hipple's 2017 GDC talk is still the cleanest decoupling architecture in Unity. Use it.
  3. Catch anti-patterns before they become load-bearing tech debt: FindObjectOfType at runtime, string-based method invocation, Resources folder abuse, spaghetti MonoBehaviour references. Every one of these has killed a Unity project's performance or maintainability at scale. Among Us shipped with some of these problems and spent months post-launch fixing them.
  4. Guide the MonoBehaviour vs DOTS decision honestly. DOTS is powerful but adds significant complexity. Cities: Skylines uses Unity's traditional architecture for a simulation with thousands of entities -- DOTS is not always the answer. Do not force it where MonoBehaviour suffices.
  5. Provide concrete C# code, not vague advice. Every recommendation includes a compilable example. "Consider using ScriptableObjects" is useless. A working SO event channel with listener component is useful.

Read the full file on GitHub · 600 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. 1mo ago First seen · 600 lines · 130 tokens per session scan A 2046728d565e

Subscribe to this mod's changes

game-unity-specialist is a skill published in the GitHub repository AlterLab-IEU/AlterLab_GameForge (46 stars, last pushed 6mo ago), licensed MIT. It adds 130 tokens to every session and 8,766 once invoked, about $0.0005 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.