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 skills add alivirgo/Major-AI-Skills --skill unitygit clone --depth 1 https://github.com/alivirgo/Major-AI-SkillsWrote 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.
[](https://agentmods.dev/skills/alivirgo/major-ai-skills/unity)<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/unity"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/unity/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.
<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/unity"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/unity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00022 | $0.01174 |
| Opus 5.5 | $0.00009 | $0.00470 |
| Sonnet 5.5 | $0.00004 | $0.00235 |
| Haiku 4.5 | $0.00002 | $0.00117 |
Grade A, and why
unity 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.
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unity Engine C# Editor & Runtime AI Skill Guide (Claude)
Overview & Engine Architecture
Unity 6000.x / 2022 LTS+ combines Scenes, Prefabs, ScriptableObjects, URP/HDRP/Built-in RP, and Editor-only automation via -batchmode -quit -executeMethod. Claude acts as a Principal Unity Engineer: CI builds, Addressables, deterministic player settings, and Editor/runtime assembly separation.
┌─────────────────────────────────────────────────────────────┐
│ Editor (UnityEditor) → -executeMethod / BuildPipeline │
│ Player (runtime) → Mono / IL2CPP │
│ CI: one process per buildTarget; -activeBuildProfile │
└─────────────────────────────────────────────────────────────┘
Version pin: Unity Editor version in ProjectSettings/ProjectVersion.txt — CI must use the same Hub editor (e.g. 6000.0.xf1). Command-line reference.
When to use / when not to
Use when: automated builds, asset validation, playmode tests, Addressables content builds, batch import settings.
Do not use when: Unreal-specific Nanite workflows; server-side Unity without licensing review for headless batch (Unity licensing applies to build machines).
Operational Capabilities & Agent Directives
- Editor isolation:
#if UNITY_EDITOR,Assets/**/Editor/, Editor asmdefs — never referenceUnityEditorin runtime. - CI entry points:
public static void X()only;EditorApplication.Exit(code)on failure; no modal dialogs in batchmode. - One target per invocation: pass
-buildTarget StandaloneWindows64or-activeBuildProfile "Assets/.../Windows.asset"— multi-target requires separate processes. - Deterministic builds: pin graphics tiers, disable random
Application.targetFrameRateside effects in build scripts; useBuildOptions.StrictModewhere available; logApplication.unityVersion. - Color/URP: document active RP asset; linear color space + URP asset must match CI player settings or lighting differs from Editor.
- Logs: always
-logFilepath; parse forScripts have compiler errorsbefore blaming runtime.
What ships with it
2 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.
- 1mo ago Changed · -26 lines 562e17d6d4d8
- 1mo ago Changed · -12 tokens per session 8addf5e22450
- 2mo ago First seen · 146 lines · 34 tokens per session scan A 8d8e337fe631
unity is a skill published in the GitHub repository alivirgo/Major-AI-Skills (2 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 1,174 once invoked, about $0.0001 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 2026-08-31.
unity compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| unityalivirgo/Major-AI-Skills | Skill | 2 | yesterday | MIT | A | 22 | Claude Code |
| aspid-visual-element-fluentVPDPersonal/Aspid.FastTools | Skill | 24 | yesterday | MIT | A | 109 | Claude Code, Codex |
| aspid-serializable-typeVPDPersonal/Aspid.FastTools | Skill | 24 | yesterday | MIT | A | 136 | Claude Code, Codex |
| aspid-enum-valuesVPDPersonal/Aspid.FastTools | Skill | 24 | yesterday | MIT | A | 87 | Claude Code, Codex |
| aspid-profiler-markerVPDPersonal/Aspid.FastTools | Skill | 24 | yesterday | MIT | A | 82 | Claude Code, Codex |
| asp-ft-player-buildsVPDPersonal/Aspid.FastTools | Skill | 24 | yesterday | MIT | A | 99 | Claude Code |
| test-designing-guidenowsprinting/unity-coding-skills | Skill | 20 | 8d ago | Unlicense | A | 52 | Claude Code |