Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/bigdra50/unity-clinpx agentmods add skills/bigdra50/unity-cli/unity-uiWrote 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-ui)<a href="https://agentmods.dev/skills/bigdra50/unity-cli/unity-ui"><img src="https://agentmods.dev/badge/skills/bigdra50/unity-cli/unity-ui/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-ui"><img src="https://agentmods.dev/badge/skills/bigdra50/unity-cli/unity-ui.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 | $0.00081 | $0.04307 |
| Opus 5.5 | $0.00032 | $0.01723 |
| Sonnet 5.5 | $0.00016 | $0.00861 |
| Haiku 4.5 | $0.00008 | $0.00431 |
Grade A, and why
unity-ui 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 — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.
unity-ui
PREREQUISITE:
../unity-shared/SKILL.md（Relay Server 経由で Unity Editor が起動/アクティブであること）skill 経由のコマンドは必ず
-i <instance>を付ける (unity-shared #インスタンス指定)。uitree コマンドは Play Mode 中のみ動作する。必ず
u -i <instance> playしてから実行すること。
UI テストの種別
| 種別 | 検証内容 | 手法 | スクショ |
|---|---|---|---|
| Functional | 操作→状態が正しいか | click → text で値検証 | 不要 |
| Visual Regression | 外観が変わっていないか | screenshot → 画像比較 | 必要 |
| Structural Snapshot | ツリー構造が変わっていないか | dump --json → diff | 不要 |
| Smoke | 最低限動くか | click → console にエラーなし | 任意 |
| Monkey | ランダム操作でクラッシュしないか | monkey → errors 確認 | 不要 |
UI システム判定
| 手がかり | UI Toolkit | uGUI |
|---|---|---|
| ファイル | .uxml, .uss |
.prefab に Canvas |
| コンポーネント | UIDocument | Canvas, RectTransform |
コマンドリファレンス
要素の指定方法は2通り: ref ID (ref_3) または -p <panel> -n <name>。
構造把握
u -i <instance> uitree dump # 全パネル一覧 (contextType: Player がゲーム側)
u -i <instance> uitree dump -p "PanelSettings" # パネルのツリー (各要素の ref/name/type/classes が見える)
u -i <instance> uitree dump -p "PanelSettings" --json # JSON 出力 (snapshot用)
u -i <instance> uitree query -p "PanelSettings" -t Button # type で検索 (VisualElement ベースのボタンはヒットしない → -c で検索)
u -i <instance> uitree query -p "PanelSettings" -n "BtnStart" # name で検索
u -i <instance> uitree query -p "PanelSettings" -c "action-btn" # USS class で検索
u -i <instance> uitree query -p "PanelSettings" -t Button -c "primary" # AND 条件
u -i <instance> uitree inspect -p "PanelSettings" -n "BtnStart" # 要素詳細
u -i <instance> uitree inspect ref_5_48 # ref ID で指定
u -i <instance> uitree inspect ref_5_48 --style # resolvedStyle 含む
u -i <instance> uitree inspect ref_5_48 --children # 子要素情報含む
テキスト取得
u -i <instance> uitree text -p "PanelSettings" -n "ToastMessage" # name で指定
u -i <instance> uitree text ref_5_12 # ref ID で指定
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 · 428 lines · 81 tokens per session scan A 90ee34401ce1
unity-ui is a skill published in the GitHub repository bigdra50/unity-cli (39 stars, last pushed 4mo ago), licensed MIT. It adds 81 tokens to every session and 4,307 once invoked, about $0.0003 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.
test-designing-guide
Provides test design methodology for Unity projects. Use this skill whenever designing test cases from requirements or specifications, including selecting test techniques, deriving test cases, and formatting them. Even for small features, load this skill to ensure test design rigor.
test-writing-guide
Provides guidelines for writing test code for Unity projects. Make sure to use this skill whenever writing, creating, editing, or modifying test code files (files under Tests/). This includes implementing new tests, fixing test failures, adding test cases, or any task that results in test code changes. Even for small…
swallowtail-qa
Playtest Godot games and exported builds, capture frame spikes, compare QA baselines, and produce Swallowtail branded reports. Use for release QA and reusable game-specific test scenarios, not routine implementation-only unit tests.
run-tests
Provides guidelines for running Unity tests using the rununitytests tool. Make sure to use this skill whenever running, executing, or re-running tests in the Unity Editor. This includes verifying implementations, debugging test failures, running specific test assemblies, or any task that involves the rununitytests…
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…