Borrowing it
Nothing to install: this file belongs to shuji-bonji/rfcxml-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/rfcxml-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/shuji-bonji/rfcxml-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/rfcxml-mcp/claude-md)<a href="https://agentmods.dev/instructions/shuji-bonji/rfcxml-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/shuji-bonji/rfcxml-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/rfcxml-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/shuji-bonji/rfcxml-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 | $0.32442 | $0.32442 |
| Opus 5 | $0.16221 | $0.16221 |
| Sonnet 5 | $0.06488 | $0.06488 |
| Haiku 4.5 | $0.03244 | $0.03244 |
Grade A, and why
rfcxml-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 5d 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 — 1,599 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RFCXML MCP Server - 開発ガイド
プロジェクト概要
RFC文書を構造的に理解するためのMCPサーバー。RFCXMLの意味構造を活用し、BCP 14 要件抽出、依存関係分析、実装チェックリスト生成などを提供する。
ツール一覧
| ツール | 説明 |
|---|---|
get_rfc_structure |
セクション階層とメタデータ取得 |
get_requirements |
規範性要件（MUST/SHOULD/MAY）抽出 |
get_definitions |
用語定義とスコープ |
get_rfc_dependencies |
参照RFC（normative/informative）+ referencedBy（Datatracker API） |
get_related_sections |
関連セクション（<xref> + テキスト両対応） |
generate_checklist |
実装チェックリスト生成 |
validate_statement |
主張の仕様準拠検証（重み付きマッチング + 意味的否定検出） |
古い RFC (< 8650) は XML がないためテキストフォールバックで対応。8650 以降でも XML が
404 以外の理由（5xx・タイムアウト）で取れなければテキストに落ちる。レスポンスに
_source / _sourceNote を付与。
テキストフォールバック時の機能制約
XMLXPath / 構造化情報に依存する一部機能は、テキストフォールバックでは精度が落ちる。下記マトリクスは known limitation として明文化しておく。
| ツール | XML 形式 | text 形式 | API 補完 | 備考 |
|---|---|---|---|---|
get_rfc_structure |
✅ 完全 | ⚠️ 階層精度低下 | ✅ メタデータ補完 | API で abstract / authors を補完。category / stream は API から取れたときだけ付く（不達なら _sourceNote に書く）。公開日は本文から取る |
get_requirements |
✅ 完全 | ⚠️ 抽出精度低下 | ❌ なし | 段落ベースの推測になる |
get_definitions |
✅ 完全 | ⚠️ 抽出精度低下 | ❌ なし | <dl> がなく、X: Y とぶら下げの形で推測 |
get_rfc_dependencies |
✅ 完全 | ✅ 良 | ✅ Datatracker relateddocument |
参考文献の欄があれば text パーサで取得、無ければ API |
get_related_sections |
✅ 完全 | ⚠️ 本文の Section N の記述から |
❌ なし | 節レベルの相互参照は本文にしか無く、API に存在しない |
generate_checklist |
✅ 完全 | ⚠️ 抽出精度低下 | ❌ なし | get_requirements 経由のため同じ制約 |
validate_statement |
✅ 完全 | ⚠️ 抽出精度低下 | ❌ なし | 同上 |
凡例: ✅ 完全 / ⚠️ 制限あり（精度低下） / ❌ 取得不能。
_referencesSource の値の意味（get_rfc_dependencies のみ）:
'xml'— RFCXML の<references>から抽出。完全な anchor / title 付き'text'— テキスト本文の参考文献の欄から抽出。題名は欄から取るので仮置きではない。欄が 1 つしかない RFC（RFC 2616）ではすべてinformativeに入り、そのときだけ_sourceNoteが付く'api'— DatatrackerrelateddocumentAPI から取得。title / anchor はプレースホルダ（title: "RFC N",anchor: "RFCN"）。本文に参考文献の欄が無いときに使う
開発コマンド
npm run build # ビルド
npm test # テスト（単発実行）
npm run test:watch # テスト（ウォッチモード）
npm run test:coverage # テスト + カバレッジ
npm run test:e2e # E2E テスト（MCP クライアント統合）
npm run audit # 実物の RFC に不変条件を当てる（本数と種類は tests/audit/corpus.mjs と invariants.mjs が正）
npm run crosscheck # 7 つのツールの出力が互いに矛盾しないかを見る（条件は tests/crosscheck/run.mjs）
npm run snapshot # 代表的な出力を固定し、差分を見る（見本は tests/snapshot/cases.mjs）
npm run lint # リント
npm run format # フォーマット
npm start # MCP サーバー起動
npm run prefetch # RFC 本文をディスクキャッシュに事前充填
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.
- 5d ago Changed · +1,140 lines · +23,335 tokens per session 968bfa2f6215
- 6d ago Changed · +341 lines · +7,430 tokens per session 1996e42f4f62
- 10d ago First seen · 118 lines · 1,677 tokens per session scan A edba1a5e84cf
rfcxml-mcp CLAUDE.md is an instructions file published in the GitHub repository shuji-bonji/rfcxml-mcp (4 stars, last pushed 4d ago), licensed MIT. It adds 32,442 tokens to every session, about $0.1622 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).
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.
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.