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/tyunta/prefab-sentinel/guidenpx skills add tyunta/prefab-sentinel --skill guidegit clone --depth 1 https://github.com/tyunta/prefab-sentinelWhat 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 | $0.00227 | $0.04654 |
| Opus 5 | $0.00113 | $0.02327 |
| Sonnet 5 | $0.00045 | $0.00931 |
| Haiku 4.5 | $0.00023 | $0.00465 |
Grade A, and why
guide 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unity プロジェクトで Prefab / Scene / Asset の検査・編集・参照修復を行う MCP ツールリファレンス。
MCP ツールとして呼び出す（CLI は v0.4.0 で廃止済み）。Plugin 導入時はホスト（Claude Code / Codex CLI）が MCP サーバーを自動起動するため、このスキルが使える時点でツールは接続済み。
書き込みの実適用・実行検証・editor_* ツールを使うには Editor Bridge のセットアップが必要 → Unity Bridge セットアップ。read-only 検査・dry-run だけならセットアップ不要。
30 秒で動く 3 つの例
最短経路。UNITYTOOL_BRIDGE_WATCH_DIR 等の Editor Bridge 環境変数は read-only 経路では不要（broken-reference 検出と Variant 差分は YAML 直読みで完結する）。activate_project はセッションで最初に 1 回呼び、scope（必須）と Unity プロジェクトルート（project_root、任意）を宣言する。
(1) 壊れた参照を検出する — validate_refs で broken GUID / fileID を構造化応答で取り出す。
activate_project(scope="Assets/<feature>", project_root="/path/to/unity/project")
validate_refs(scope="Assets/<feature>")
返ってきた envelope の data.unique_missing_asset_guids が空配列なら OK、要素があれば未解決 GUID の集合（重複排除済み）。data.broken_occurrences に発生回数。
(2) Variant の override を可視化する — inspect_variant で base からの差分のみを取り出す。
inspect_variant(asset_path="Assets/<feature>/Variants/Foo.prefab", show_origin=True)
各 override に origin_path / origin_depth が付き、どの prefab（Base / Mid / Leaf）が値を確定したかを追える。
(3) 編集を dry-run でプレビューする — set_property の confirm=False で差分だけ取り出す（書き込まない）。
set_property(
asset_path="Assets/<feature>/Foo.prefab",
symbol_path="CharacterBody/MeshRenderer",
property_path="m_StaticBatchInfo.firstSubMesh",
value=2,
confirm=False,
)
symbol_path は GameObject パス + 末尾コンポーネント名でコンポーネント自体を指す（asset_path と symbol_path は常に別引数）。severity と data.diff を読んで意図通りなら confirm=True + 非空 change_reason で再呼び出し。change_reason を欠くと CHANGE_REASON_REQUIRED で拒否される。
最初に困ったらこの 3 ツール
どこから手をつけるか迷ったらここから。各ツールは read-only で副作用なし。
validate_refs— broken GUID / fileID を全件検出する起点。scope引数でスコープを宣言する。<scope>/config/ignore_guids.txtがあれば auto-load される。inspect_wiring— MonoBehaviour フィールドの配線（null / fileID 不整合 / 重複参照）を分析する。script_filterで特定の script class に絞れる。inspect_hierarchy— GameObject の階層ツリーをコンポーネント注釈付きで読む。expand_monobehaviour=trueでスクリプトクラス名を展開する。
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 · 179 lines · 227 tokens per session scan A 24e5b4604bd4
guide is a skill published in the GitHub repository tyunta/prefab-sentinel (11 stars, last pushed 17d ago), licensed MIT. It adds 227 tokens to every session and 4,654 once invoked, about $0.0011 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
particles
Use this skill when creating particle effects in Phaser 4. Covers ParticleEmitter, emission zones, death zones, particle properties, textures, gravity wells, and particle movement. Triggers on: particles, emitter, particle effect, explosion, fire, smoke.
web-games
Web browser game development principles. Framework selection, WebGPU, optimization, PWA.
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
ship-web-games
Package, deploy, and verify a playable Three.js or web game. Use for release builds, asset delivery, private/public deployment, production smoke tests, browser proof, release notes, rollback readiness, and cleanup of temporary QA resources.
unity
Compile, test, and drive Unity for this repo's C# packages (unity/core, jint, quickjs, clearscript) and the two Unity projects (tests/, kitchen-sink/). Use when a change touches C# under unity/, when Unity test results are needed, when a rendering snapshot has to be checked or regenerated, or when the app has to be…