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/noricha-vr/webscreen/claude-mdgit clone --depth 1 https://github.com/noricha-vr/WebScreenWrote 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/instructions/noricha-vr/webscreen/claude-md)<a href="https://agentmods.dev/instructions/noricha-vr/webscreen/claude-md"><img src="https://agentmods.dev/badge/instructions/noricha-vr/webscreen/claude-md.svg" alt="Measured on agentmods" 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 | $0.01706 | $0.01706 |
| Opus 5 | $0.00853 | $0.00853 |
| Sonnet 5 | $0.00341 | $0.00341 |
| Haiku 4.5 | $0.00171 | $0.00171 |
Grade A, and why
WebScreen CLAUDE.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 today.
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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Claude Code がこのリポジトリで作業するときの地図。詳細は各リンク先を正本とし、ここには判断に効く情報だけ置く。
このリポジトリは 2 系統が同居している
| 系統 | 実体 | 状態 |
|---|---|---|
| 現行(ここを触る) | web/ — Astro + Cloudflare Workers + D1 + R2 |
本番 https://web-screen.net |
| 旧(触らない) | リポジトリ直下の router/ movie_maker/ templates/ static/ api/ 等 — FastAPI + Selenium + GCS |
廃止予定。Cloud Run で古いリビジョンが稼働したままだが新規開発しない |
<critical_rule>
新しい機能・修正は web/ に入れる。 旧系統のファイルは、明示的に「旧版を直して」と指示された時以外は編集しない。
Dockerfile / docker-compose.yaml / cloudbuild.yaml / requirements.txt も旧系統専用(Cloud Build のトリガーは無効化済み)。
</critical_rule>
関連サービスは別リポにある: web-capture(Cloud Run。URL のスクリーンショットを撮って R2 へ置く)。
何をするプロダクトか
Web ページ・画像・PDF を、VRChat のビデオプレイヤーで再生できる MP4 に変換して配る。 変換した動画は公開 URL を持ち、VRChat に貼るだけで再生できる。
web/ の構成
| パス | 役割 |
|---|---|
web/src/pages/ |
エントリポイント(api/ は Worker の API、[shortId]/ はプレビューとダウンロード) |
web/src/lib/contracts/ |
API の契約の正本。api.ts が producer(Worker)と consumer(ブラウザ・web-capture)の共通定義 |
web/src/lib/services/ |
ドメインロジック(D1 / R2 の操作、認証、保持期間) |
web/src/lib/convert/ |
ブラウザ内変換(PDF.js / FFmpeg.wasm) |
web/src/lib/ui/ |
画面の配線(DOM 操作と状態遷移) |
web/src/i18n/ |
表示文言の正本(ja / en)。テンプレートや JS に文言を直書きしない |
web/cron/ |
保持期間バッチ(別 Worker。同じ D1 / R2 を共有する) |
web/migrations/ |
D1 のマイグレーション |
開発
make install # 初回のみ(web/ の依存を lockfile 固定で入れる)
make help
make check
make e2e
make stream-probe ID=AbCdEf123456
web/.dev.vars にローカル用の環境変数が要る(.dev.vars.example を参照)。
- ローカル環境・E2E の落とし穴(dev サーバー復旧・ポート分離・Claude Code サンドボックス)は docs/local-dev.md
デプロイ
main への push で GitHub Actions が本番へ反映する(.github/workflows/deploy.yml)。
型チェック → ユニットテスト → ビルド → D1 マイグレーション → Worker 2 つ → 疎通確認、の順で、失敗したら自動でロールバックする。
<critical_rule>
wrangler rollback は Worker のコードしか戻さない。 D1 / R2 のデータも cron スケジュールも戻らない。
そのため D1 の変更は必ず後方互換にする(破壊的変更は「追加 → 切替 → 削除」の 3 段階に分ける)。
</critical_rule>
判断材料の詳細は playbook ノート playbook-cloudflare-workers-deploy にある(note use で読む)。
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.
- today Changed · +12 lines · +358 tokens per session 35d57c373c8e
- 4d ago First seen · 80 lines · 1,348 tokens per session scan A 3480effffb62
WebScreen CLAUDE.md is an instructions file published in the GitHub repository noricha-vr/WebScreen (20 stars, last pushed today), licensed MIT. It adds 1,706 tokens to every session, about $0.0085 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.