component-design

Guidance for organizing Unity MonoBehaviours, the scripts that control game objects. It covers splitting responsibilities, communication between components, and predictable startup and shutdown order.

In plain words
What is it for?
Use it when designing or reviewing component-based Unity code, choosing communication patterns, ordering initialization, or organizing components on a prefab.
Why use it?
It helps prevent one oversized script from becoming hard to understand and reduces confusion about how components connect and initialize.

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/component-design
Any agent
npx skills add TheArcForge/Hades --skill component-design
Clone the repo
git clone --depth 1 https://github.com/TheArcForge/Hades

Made for: Claude Code, Codex.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,960 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 $0.00025 $0.03960
Opus 5 $0.00013 $0.01980
Sonnet 5 $0.00005 $0.00792
Haiku 4.5 $0.00003 $0.00396

Measured 2d ago against content hash 388ffbe02b48, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

component-design 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/component-design/SKILL.md · 505 lines

How it starts

The opening of the file, as written. The whole thing — 505 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Component Design

Guidance for structuring Unity MonoBehaviours: when to split responsibilities, how to wire communication between components, and how to enforce predictable lifecycle ordering.

When to Apply

Activate when the conversation involves:

  • Deciding whether to split one MonoBehaviour into multiple components
  • Choosing how components should communicate (events, interfaces, direct references)
  • Establishing component lifecycle order or initialization sequencing
  • Reviewing a MonoBehaviour that has grown large or hard to maintain
  • Naming or organizing components on a prefab
  • Setting up inter-system communication on a multi-component prefab

Do NOT activate for questions about scene structure, data modeling, or prefab hierarchy — those go to hades:unity-architect, hades:data-modeling, or hades:prefab-architecture.

Project Context Check

Before making recommendations:

  1. Check existing patterns in the graph:

    • Call graph_query(edgeKind: "references", edgeTargetNamePattern: "MonoBehaviour", edgeTargetKind: "Class") to understand component density and naming conventions already in the project
    • Call search_by_name("*Manager*") to detect existing manager patterns and whether the project uses service-locator style aggregators
    • Call graph_query(edgeKind: "references", edgeTargetPath: "<path/to/Component.cs>") on the focal component to find how it is already used across prefabs
  2. Check team decisions in memory:

    • Call recall_memory("component design patterns communication") to find documented communication conventions
    • Check validation status — if a recalled decision shows warning, surface the conflict to the user before proceeding
  3. Adapt recommendations based on findings:

    • If the project already uses event channels consistently → recommend SO event channel for new communication
    • If the project uses direct serialized references throughout → align unless there is a decoupling reason
    • After the user agrees on a pattern not yet documented, call propose_memory_update to record it

Read the full file on GitHub · 505 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 · 505 lines · 25 tokens per session scan A 388ffbe02b48

Subscribe to this mod's changes

component-design is a skill published in the GitHub repository TheArcForge/Hades (27 stars, last pushed 6d ago), licensed MIT. It adds 25 tokens to every session and 3,960 once invoked, about $0.0001 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