Borrowing it
Nothing to install: this file belongs to shuji-bonji/pdf-reader-mcp. 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/shuji-bonji/pdf-reader-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/shuji-bonji/pdf-reader-mcpWrote 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/shuji-bonji/pdf-reader-mcp/claude-md)<a href="https://agentmods.dev/instructions/shuji-bonji/pdf-reader-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/shuji-bonji/pdf-reader-mcp/claude-md/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/instructions/shuji-bonji/pdf-reader-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/shuji-bonji/pdf-reader-mcp/claude-md.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 | $0.01518 | $0.01518 |
| Opus 5 | $0.00759 | $0.00759 |
| Sonnet 5 | $0.00304 | $0.00304 |
| Haiku 4.5 | $0.00152 | $0.00152 |
Grade A, and why
pdf-reader-mcp 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 9d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pdf-reader-mcp - 開発ガイド
プロジェクト概要
PDF の中身を読み取り・報告する MCP サーバ。PDF family における「実体」担当。
| 層 | サーバ | 一行定義 |
|---|---|---|
| 正典 | pdf-spec-mcp | 仕様は何を要求するか |
| 実体 | 本サーバ | 中身に何があるか（合否は言わない） |
| 判定 | pdf-verify-mcp | それは本物で、規格に適っているか |
| 生成 | pdf-writer-mcp | 仕様どおりに書けるか |
- 残タスク:
docs/TASKS.md - 責務分担の提案:
mcps/pdf-family-role-architecture.md - 上位仕様:
Document-Note/mcps/PDFfamily/foundation/pdf-reader-mcp.md
ツール一覧（19・3 tier）
| Tier | ツール |
|---|---|
| 1 基本 | read_text / read_url / read_images / render_page / search_text / get_metadata / get_page_count / summarize |
| 2 構造検査 | inspect_structure / inspect_fonts / inspect_annotations / inspect_signatures / inspect_tags / extract_tables / extract_structured_text / locate_objects |
| 3 検証・分析 | compare_structure / validate_metadata / validate_tagged |
境界ルール（ツール追加時の判断基準）
ISO 規格等に照らした compliant / valid / pass-fail を返すなら pdf-verify-mcp、 観測結果を返すだけなら本サーバ。
本サーバは「何があるか」を報告する。「それでいいのか」は判定せず、利用者（LLM）に委ねる。
inspect_signaturesは署名フィールドの存在を報告する（暗号検証は verify のverify_signatures）inspect_tagsは構造ツリーを報告する（PDF/UA 準拠の判定は verify のvalidate_conformance）
⚠️ Tier 3 の validate_tagged / validate_metadata はこの規則の例外（verify が存在しなかった
時代の実装）。pdf-verify-mcp v0.6.0 が PDF/UA 判定を実装したため、責務としては移管済み。
詳細は docs/TASKS.md の M-2。新しい validate_* をここに足さないこと。
アーキテクチャの要点
index.ts → tools/{tier1,tier2,tier3}/*.ts（zod スキーマ + ハンドラ）
services/pdfjs-service.ts : pdfjs 依存（構造ツリー・オペレータリスト）
services/pdflib-service.ts : pdf-lib 依存（辞書レベル）
utils/formatter.ts : markdown 化
- ツール追加は該当 tier に 1 ファイル + 登録
console.log禁止（MCP の stdio を汚染する）。ログは stderr へ
落とし穴
1. pdfjs 依存はこのサーバの固有資産
analyzeTagsFromDoc（構造ツリー）や countImagesFromDoc（getOperatorList +
OPS.paintImageXObject）は pdfjs に依存する。verify は意図的に pdfjs を持たない
（pdf-lib + pkijs のみ）ため、pdfjs が要る検査はここでしかできない。
これは弱点ではなく役割分担。
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.
- 9d ago First seen · 102 lines · 1,518 tokens per session scan A 9578621cf1c0
pdf-reader-mcp CLAUDE.md is an instructions file published in the GitHub repository shuji-bonji/pdf-reader-mcp (2 stars, last pushed 8d ago), licensed MIT. It adds 1,518 tokens to every session, about $0.0076 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 2026-08-31.
Other instructions, from other repositories
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.