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.
npx agentmods add skills/thearcforge/hades/unity-ecsnpx skills add TheArcForge/Hades --skill unity-ecsgit clone --depth 1 https://github.com/TheArcForge/HadesWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00034 | $0.05930 |
| Opus 5 | $0.00017 | $0.02965 |
| Sonnet 5 | $0.00007 | $0.01186 |
| Haiku 4.5 | $0.00003 | $0.00593 |
Grade A, and why
unity-ecs 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.
How it starts
The opening of the file, as written. The whole thing — 694 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unity ECS / DOTS
Decision framework for adopting Unity's Data-Oriented Technology Stack. Covers when ECS, Jobs, and Burst deliver meaningful value vs. when they add cost without benefit, how to apply each layer independently, and a proven incremental migration path from MonoBehaviour to full ECS.
When to Apply
Activate when the conversation involves:
- Evaluating whether to use ECS, Jobs, or Burst for a new system
- A MonoBehaviour simulation that is hitting CPU performance limits
- Questions about
IComponentData,SystemBase,ISystem,IJobParallelFor, orBurstCompile - Deciding on a hybrid approach (MonoBehaviour logic driving entity data via Baking)
- Migrating an existing MonoBehaviour-based system toward DOTS
- Any mention of entity counts in the thousands or tens of thousands
- NativeContainer allocation or disposal questions
Do NOT activate for general performance questions not involving entities — those go to hades:unity-performance. Do NOT activate for architecture questions about scene or prefab structure — those go to hades:unity-architect.
Project Context Check
Before making ECS recommendations, gather context so advice matches the actual project state.
-
Check for existing ECS usage:
- Call
graph_query(edgeKind: "references", edgeTargetNamePattern: "IComponentData", edgeTargetKind: "Class")— reveals whether ECS components already exist. If they do, advice must be consistent with those patterns. - Call
graph_query(edgeKind: "references", edgeTargetNamePattern: "SystemBase", edgeTargetKind: "Class")and the same withedgeTargetNamePattern: "ISystem"— identifies existing ECS systems. Presence ofISystem(unmanaged) suggests a performance-first stance;SystemBasesuggests an earlier adoption or more managed-style code.
- Call
-
Understand project scale and targets:
- Call
get_project_summary()— reveals platform targets (mobile vs. PC/console), project age, and team size. ECS has a steep learning curve; on a solo mobile project with a 6-month timeline, it is rarely appropriate.
- Call
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.
- 2d ago First seen · 694 lines · 34 tokens per session scan A d77a537cec8f
unity-ecs is a skill published in the GitHub repository TheArcForge/Hades (27 stars, last pushed 6d ago), licensed MIT. It adds 34 tokens to every session and 5,930 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.
Other skills, from other repositories
octocode-mannequin
Use when posing, animating, or explaining a 3D human skeleton/manikin: anatomical joints, ROM clamps, walk/run/dance/backflip sequences, Three.js viewer, or agent-driven WebMCP figure control (reach/lookat). Phrases like pose the manikin, skeleton scheme, animate a walk cycle. Not for general 3D scenes…
unity-reviewer
Use after implementation to review code changes for Unity anti-patterns, performance issues, and correctness problems. Also use when superpowers:requesting-code-review is active to provide Unity-specific review criteria.
component-design
Use when you need detailed decision frameworks for MonoBehaviour composition, inter-component communication, single responsibility, and execution order.
data-modeling
Use when you need detailed decision frameworks for ScriptableObject patterns, runtime data management, serialization strategies, and data-driven architecture.
prefab-architecture
Use when you need detailed decision frameworks for prefab vs variant vs ScriptableObject, nested prefab design, override strategies, and prefab editing workflows.
scene-architecture
Use when you need detailed decision frameworks for scene structure, additive loading, scene management, transitions, and persistent managers.