unity-architect

A planning guide for designing the structure of Unity projects and features. Unity is a game-development platform, and the guide covers choices such as components, scenes, prefabs, data, and performance.

In plain words
What is it for?
Use it when planning a new Unity system, organizing scenes or prefabs, modeling data, deciding how components should work, or considering performance and testability.
Why use it?
It helps developers choose an appropriate structure before implementation and understand trade-offs between different Unity approaches.

Skill for Claude CodeCodex

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 skills/thearcforge/hades/unity-architect
Any agent
npx skills add TheArcForge/Hades --skill unity-architect
Clone the repo
git clone --depth 1 https://github.com/TheArcForge/Hades

Made for: Claude Code, Codex.

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,833 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 $0.00042 $0.04833
Opus 5 $0.00021 $0.02416
Sonnet 5 $0.00008 $0.00967
Haiku 4.5 $0.00004 $0.00483

Measured 2d ago against content hash c8f29fcf27d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

unity-architect 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.

ClaudeCodePlugin/skills/unity-architect/SKILL.md · 590 lines

How it starts

The opening of the file, as written. The whole thing — 590 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unity Architect

Top-level routing skill for Unity architecture decisions. Provides decision frameworks for component strategy, scene structure, data modeling, prefab architecture, and performance — then routes to specialized sub-skills for deeper implementation guidance.

When to Apply

Activate when the conversation involves:

  • Designing a new system or feature from scratch ("how should I structure X?")
  • Evaluating trade-offs between architectural approaches
  • Scoping a feature before implementation starts
  • Asking whether to use MonoBehaviour vs ScriptableObject vs ECS
  • Asking how to organize scenes, prefabs, or data
  • Performance planning before any profiling has been done
  • Cross-cutting concerns: networking, persistence, or testability

Do NOT activate for narrow implementation questions about a specific existing system — those go directly to the relevant sub-skill.

Project Context Check

Before making recommendations:

  1. Check existing patterns in the graph (always use Hades tools first, not grep/find):
    • Call get_project_summary() to understand project scale, render pipeline, assembly count, asset coverage, and asset volumes — a 200-prefab project warrants different advice than a 20-prefab one
    • Call search_by_name("<keyword>", kind="Class") to filter by declaration kind — search_by_name has no path-prefix or exact-match option anymore; use graph_query(namePattern: "<keyword>", pathPrefix: "Assets/Scripts") to scope a search to one directory
    • Call find_references_to("<script_path>") to discover all dependents — returns both asset references (prefabs, scenes) and C# code references (fields, parameters, inheritance, constructors)
    • Call graph_query(edgeKind: "references", edgeTargetNamePattern: "Pool", edgeTargetKind: "Class") or with edgeTargetNamePattern: "Factory" to discover whether spawn infrastructure already exists
    • Call graph_query(edgeKind: "references", edgeTargetNamePattern: "GameEvent", edgeTargetKind: "Class") or with edgeTargetNamePattern: "EventChannel" to detect event architecture
    • Call trace_dependencies("<CentralSystem>") on any system the new feature depends on to surface tight coupling early

Read the full file on GitHub · 590 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 · 590 lines · 42 tokens per session scan A c8f29fcf27d0

Subscribe to this mod's changes

unity-architect is a skill published in the GitHub repository TheArcForge/Hades (27 stars, last pushed 6d ago), licensed MIT. It adds 42 tokens to every session and 4,833 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 2026-08-30.

Related

Other skills, from other repositories