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/uniclaude/unity-architectnpx skills add TheArcForge/UniClaude --skill unity-architectgit clone --depth 1 https://github.com/TheArcForge/UniClaudeWhat 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 | $0.00037 | $0.02165 |
| Opus 5 | $0.00018 | $0.01082 |
| Sonnet 5 | $0.00007 | $0.00433 |
| Haiku 4.5 | $0.00004 | $0.00216 |
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.
How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unity Architecture Decisions
Load this skill when designing a Unity feature or system. It contains condensed decision frameworks for the most common architectural choices. For deeper detail on any domain, reference files are available in references/.
Before You Design
Ask these questions for every non-trivial feature:
- Scale: How many instances? (1, tens, hundreds, thousands?)
- Lifetime: Persistent across scenes? Created/destroyed at runtime? Pooled?
- Variance: How do instances differ? (data only? behavior? visuals?)
- Ownership: Who spawns it? Who configures it? Who destroys it?
- Dependencies: What other systems does it talk to? (input, networking, UI, save system, audio?)
- Performance budget: Is this in a hot path? Per-frame? Event-driven?
DECISION: Object Representation
When this applies: You need reusable objects in the game (enemies, weapons, pickups, UI panels, level pieces).
Options:
- Prefab — self-contained GameObject template with components and children.
- Use when: objects share identical structure but may have different runtime state.
- Tradeoff: each variant is a full copy; changes to shared structure require updating all.
- Prefab Variant — inherits from a base prefab, overrides specific properties.
- Use when: objects share structure but differ in specific property values or child additions.
- Tradeoff: override tracking adds complexity; deep nesting (variant of variant) is fragile.
- ScriptableObject config + single prefab — one prefab reads data from a SO asset.
- Use when: objects are structurally identical but differ only in data (stats, costs, names, sprites).
- Tradeoff: requires a script to apply config at runtime; less visual preview in editor.
Questions to ask:
- Do variants differ in structure (different components/children) or only data?
- How many variants will exist? (3-5 → prefab variants. 50+ → SO config.)
- Do designers need to preview each variant visually in the editor?
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 183 lines · 37 tokens per session scan A 7626cd91b088
unity-architect is a skill published in the GitHub repository TheArcForge/UniClaude (51 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 2,165 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-ai-behavior
Use when implementing AI and NPC behavior — state machines, behavior trees, GOAP, NavMesh navigation, decision-making patterns, and when to use each approach.
unity-addressables
Use when managing asset loading — Addressables vs Resources vs direct references, async loading patterns, memory management, group strategies, and content update workflows.
unity-audio
Use when implementing audio systems — audio manager architecture, AudioMixer setup, spatial audio, event-driven audio, music systems, and sound effect management patterns.
unity-ecs
Use when considering ECS/DOTS architecture — when to use ECS vs MonoBehaviour, Burst compiler, Job System, hybrid approaches, and migration strategies from MonoBehaviour to ECS.
unity-input
Use when implementing input handling — new Input System setup, action maps, multi-device support, input rebinding, local multiplayer input, and input abstraction patterns.