Borrowing it
Nothing to install: this file belongs to skanehira/chatbook. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/skanehira/chatbook/main/CLAUDE.mdgit clone --depth 1 https://github.com/skanehira/chatbookWrote 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/skanehira/chatbook/claude-md)<a href="https://agentmods.dev/instructions/skanehira/chatbook/claude-md"><img src="https://agentmods.dev/badge/instructions/skanehira/chatbook/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 5.1 | $0.41673 | $0.41673 |
| Opus 5 | $0.20837 | $0.20837 |
| Sonnet 5 | $0.08335 | $0.08335 |
| Haiku 4.5 | $0.04167 | $0.04167 |
Grade C, and why
chatbook CLAUDE.md scanned grade C with 2 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 7d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
下記の E2E 専用ストアを `rm -rf` してから、`wrangler d1 migrations apply`（`--persist-to` で Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -o /dev/null -w "%{http_code}\n" https://<worker 名>.<アカウント>.workers.dev/api/pdfs # 401 How it starts
The opening of the file, as written. The whole thing — 1,574 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
技術書を読みながら、気になった箇所を選択して AI に質問できる PDF リーダー。利用者は 1 人。
React 19 (SPA) + Hono (Worker) + D1 + R2 を単一の Cloudflare Workers プロジェクトにまとめ、
@cloudflare/vite-plugin で SPA と Worker を同一の vp dev で動かす。
公開先は https://<worker 名>.<アカウント>.workers.dev（wrangler.jsonc の name と
Cloudflare アカウントのサブドメインで決まる）で、API はログインの内側にある
（下記「ログインとセッション」）。ローカルだけで動かしていた頃の前提（ログイン不要）は
もう成り立たない。
コマンド
vp（Vite+）に統一。生の vite / vitest は直接叩かない。
vp dev # SPA + Worker を同時起動 (http://localhost:5173)
pnpm run db:migrate:local # D1 マイグレーション適用（初回 / migrations 追加時のみ、自動適用はしない）
pnpm test # フロント単体 (jsdom)
pnpm run test:worker # Worker 単体 (@cloudflare/vitest-pool-workers)
pnpm run test:e2e # E2E (Playwright)。サーバーは自動起動するので vp dev は不要
vp check # フォーマット + lint + 型チェック（--fix で自動修正）
vp exec wrangler types # wrangler.jsonc の bindings/main 変更後に Env 型を再生成
単体テストを1ファイルだけ走らせる: vp exec vitest run src/front/lib/sseParser.test.ts
1 つの project だけ走らせる: pnpm run test:e2e --project=mobile（desktop / tablet / mobile）
E2E を1件だけ走らせる: pnpm run test:e2e -g "テスト名の一部"（-- を挟むと pnpm が
それをそのまま playwright へ渡し、-g が効かないまま全件走る）
git push 時に lefthook の pre-push が vp check + vp build を実行し、失敗すると push はブロックされる。
worktree を作ったら最初に .dev.vars を用意する
.dev.vars は gitignore 済み（.gitignore:4）で worktree には複製されない。無いまま
vp dev（pnpm run test:e2e の自動起動を含む）を動かすと、@cloudflare/vite-plugin が
commit 済みの worker-configuration.d.ts を再生成し、LLM_* の宣言が消えた差分が
毎回出る。worktree を切ったら実装を始める前に用意する:
cp .dev.vars.example .dev.vars
.dev.vars.example が実際に読む鍵をそのまま並べてあるので、コピーすればそのまま動く
（LLM_API_KEY はダミー、ログインは demo / demo）。
型の差分は値ではなく鍵の存在と並び順で決まるので、ダミー値でも空値でも消える——
LLM_BASE_URL / LLM_MODEL / LLM_WEB_SEARCH_SUPPORTED を値の空いた行で並べてあるのは
そのためで、使わないときも行を消さず、並べ替えもしないこと（どちらも型が変わる。
commit 済みの worker-configuration.d.ts は .dev.vars.example の並びで生成してある）。
現在の E2E は LLM へ
問い合わせないので、実キーが要るのは手で回答の生成を確かめるときだけ。そのときはメインクローンの
.dev.vars からコピーする。チャット送信を E2E に足すなら実キーが要る——ダミー値では認証が
通らず、トークンが 1 つも届かないまま 60 秒のタイムアウトまで粘って落ちる。
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.
- 7d ago First seen · 1,574 lines · 41,673 tokens per session scan C 5189b539ce37
chatbook CLAUDE.md is an instructions file published in the GitHub repository skanehira/chatbook (103 stars, last pushed 17d ago), licensed MIT. It adds 41,673 tokens to every session, about $0.2084 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).
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.