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 instructions/tyunta/prefab-sentinel/agents-mdgit 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 | $0.04982 | $0.04982 |
| Opus 5 | $0.02491 | $0.02491 |
| Sonnet 5 | $0.00996 | $0.00996 |
| Haiku 4.5 | $0.00498 | $0.00498 |
Grade A, and why
prefab-sentinel AGENTS.md 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
プロジェクト運用ルール
- AI agent 初回参照: AGENT_GUIDE.md
本ファイルは prefab-sentinel リポジトリの運用ルール正本。仕様の正本は専門ドキュメント（docs/api-reference.md / docs/tool-conventions.md / docs/execution-reference.md / ARCHITECTURE.md / TESTING.md / CONFIGURATION.md）に分かれて置かれ、README.md はそれらへの入口（エントリポイント兼ルーター）として機能する。
仕様に関わる変更を行う場合は、実装変更と同時に対応する専門ドキュメントの該当箇所を更新する。
設計原則
- Easy より Simple: 目的達成に必要な最小実装を優先する。
- 根拠優先: 前提・不変条件・判断理由を明文化する。
- 検証可能性: 設定値と結果の対応を説明できる実装のみ採用する。
- 必須参照の欠落は補完せず
errorで停止する（fail-fast）。 - ファイルサイズ目安（200〜400 行）は partial 単位で評価する。1 ファイル合計ではなく
partial classごとの責務単位で行数を判定する。partial 構成は disk 上のファイル名（tools/unity/PrefabSentinel.Unity*Bridge.<Concern>.cs）が正本で、test が AGENTS.md inventory との drift を検出する（tests/test_editor_control_bridge_source.py::TestOperationalRulesPartialInventory/tests/test_unity_patch_bridge_source.py::TestPatchBridgeOperationalRulesInventory）。 - 現在の per-concern token inventory（test 用、追加・削除時に同期）:
UnityEditorControlBridge: AnimationClip / AssetDelete / AssetOps / AssetOps.Create / AssetOps.Move / BlendShape / CameraView / CompileBarrier / Components / ConsoleCapture / EditorState / Geometry / GeometryContributors / Helpers / Hierarchy / InspectorSurface / InspectorSurface.Payload / MaterialBatch / MaterialQuery / MaterialWrite / Menu / MenuScriptWatch / PrefabStage / Properties / PropertyObjectReference / PropertyWrite / RendererFramingBounds / RunScriptAsync / RunScriptCompile / SaveInstantiate / Screenshot / Screenshot.TargetCapture / Screenshot.TargetCapture.WorldSpaceUi / SerializedProperty / SerializedProperty.ObjectReference / SerializedProperty.Payload / SerializedProperty.Target / SerializedProperty.Traversal / SerializedProperty.Write / UdonSharpAddComponent / UdonSharpArrayWrite / UdonSharpFieldWrite / UdonSharpInvocation / UdonSharpListenerWiring / UiElementUnityPatchBridge: Payloads / Prefab / OpenComposition / OpenCompositionAudit / Asset / Scene / Resolve / Mutation / ManagedReference / Diagnostics
Mutationpartial は value-kind dispatcher と各SerializedPropertyType用 reader が 1 つの cohesive concern を構成するため、200〜400 行ガイドラインも issue #129 暫定の 1,000 行上限も意図的に超過する（issue #129 spec.md "further sub-split" / Non-Goals 参照）。
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 · 131 lines · 4,982 tokens per session scan A dcb46d8cbc60
prefab-sentinel AGENTS.md is an instructions file published in the GitHub repository tyunta/prefab-sentinel (11 stars, last pushed 17d ago), licensed MIT. It adds 4,982 tokens to every session, about $0.0249 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.