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 bigdra50/unity-cli --skill unity-sharedgit clone --depth 1 https://github.com/bigdra50/unity-cliWrote 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/bigdra50/unity-cli/unity-shared)<a href="https://agentmods.dev/skills/bigdra50/unity-cli/unity-shared"><img src="https://agentmods.dev/badge/skills/bigdra50/unity-cli/unity-shared/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/bigdra50/unity-cli/unity-shared"><img src="https://agentmods.dev/badge/skills/bigdra50/unity-cli/unity-shared.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 | $0.00044 | $0.01062 |
| Opus 5.5 | $0.00018 | $0.00425 |
| Sonnet 5.5 | $0.00009 | $0.00212 |
| Haiku 4.5 | $0.00004 | $0.00106 |
Grade A, and why
unity-shared 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.
What it actually says
unity-shared
全 unity-* スキルが従う共通ルール。
インスタンス指定 (必須)
unity-* スキル経由で u コマンドを呼ぶ際は 必ず -i <instance> を付ける。default インスタンスに依存しない。
u -i <instance> refresh # OK
u refresh # NG (skill 経由では使わない)
<instance> はユーザーから渡される or 親セッションが指定する値で置き換える。u instances で接続中 Unity 一覧を確認できる。本ドキュメント以下のサンプルでは <instance> をそのまま使うが、実行時は具体名 (例: TestProject) に置換する。
理由: 複数 Unity 接続環境で誤ったインスタンスへコマンドを送るリスクと、subagent 間の挙動を default 依存にしないため。
接続確認
u instances # 接続中 Unity 一覧
u -i <instance> state # 特定エディタの状態
接続不可時: unity-relay --port 6500 で Relay 起動。
Quick Verify
コード変更後に毎回実行する検証シーケンス。順序厳守 (clear は refresh の前に置く。後にすると refresh の診断ログを消してしまう)。
# 1. 既存ログをクリア (refresh の診断を残すため refresh の前)
u -i <instance> console clear
# 2. AssetDatabase リフレッシュ (コンパイルトリガー)
u -i <instance> refresh
# 3. isCompiling が false になるまでポーリング (2秒間隔, 最大30秒)
for _ in $(seq 1 15); do
u -i <instance> state --json | jq -e '.isCompiling == false' >/dev/null && break
sleep 2
done
# 4. Error/Warning 取得 (--count は deprecated. head -N を使う)
u -i <instance> console get -l E,W | head -50
u state --json の出力例 (抜粋, キーはトップレベル):
{"isCompiling": false, "isPlaying": false, "isPaused": false}
- Error あり → 修正して再実行 (最大3回)
- Warning のみ → 報告して続行
注記: 空 (0 行) は「クリーン」だが「Warning が無い」とは限らない
Unity はインクリメンタルコンパイルのため、ソース未変更で refresh を呼んでも再コンパイルは走らず、過去の Warning は再出力されない。console clear 後に空が返っても以下のいずれかを意味する:
- ソース変更があり再コンパイルが走り、エラー/警告がない (本当のクリーン)
- ソース未変更で再コンパイルがスキップされ、過去の警告が出力されないだけ
直前にソース編集があった文脈なら「クリーン」扱いで OK。過去の警告を確実に確認したい場合は対象ファイルの touch (touch Assets/.../Foo.cs) で mtime を更新してから refresh するか、Library/ScriptAssemblies/ をクリアする。
フォールバック順
CLI 非対応の操作を行う場合:
1. u -i <instance> <既存コマンド> 最優先
2. u -i <instance> api call Type Method 5,243 メソッド対応
3. YAML 直接編集 最終手段 (.meta インポート設定等)
セキュリティ
u api callは UnityEngine / UnityEditor のみ許可- 破壊的操作の実行前にユーザー確認
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 First seen · 94 lines · 44 tokens per session scan A d93432e7d343
unity-shared is a skill published in the GitHub repository bigdra50/unity-cli (39 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 1,062 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
uloop-get-project-info
Get Unity project information via uloop CLI. Use when you need to check project settings, Unity version, platform, or other project metadata.
aibridge-prefab-patch
Unity Prefab asset patch workflow for AIBridge. Use when modifying complex prefab assets with prefab patch operations, child or component creation, SerializedProperty writes, array edits, internal GameObject/component references, dry-run validation, or when deciding between prefab patch, inspector setproperty, scene…
aibridge
Unity Editor and Player Runtime CLI integration for AIBridge. Use for harness snapshot reads, Unity compile/logs/assets/scenes/prefabs/Inspector, screenshots/GIFs, Play Mode input, Runtime Player targets, focus/menu/game view, or AIBridgeCLI syntax. Route batch/multi, complex prefab patching, and direct UnityYAML…
aibridge-code-index
Optional read-only AIBridge Code Index lightweight lookup for Unity C# declaration names. Use only when Root Rule declares Code Index enabled and this Skill is installed. Map declaration names to files or positions. Do not use for references, callers, implementations, derived types, diagnostics, comments, strings, or…
aibridge-development-workflow
A development workflow guide for projects built with Unity, a game and interactive-app engine. It routes coding, asset changes, debugging, reviews, and validation through project-specific rules and checks.
aibridge-workflow-orchestration
AIBridge workflow and multi-agent orchestration guidance. Use when Codex needs to design, review, or execute a multi-agent workflow plan, split Unity work into parallel or pipeline agent roles, define structured workflow artifacts, choose between batch/multi automation and agent orchestration, run adversarial…