zk-utils: Instructions file for Claude Code

CLAUDE.md

zk-utils CLAUDE.md is an instructions file for Claude Code from koei-kaji/zk-utils. It costs 823 tokens per session, scanned A, original, MIT.

Repository instructions for zk-utils, a note-management tool that lets AI assistants search, create, and analyse links between notes. They describe its design, components, available MCP tools, and development commands.

In plain words
What is it for?
Use them when working on zk-utils, especially when changing note search, note creation, link analysis, MCP server code, or tests.
Why use it?
They give an AI coding assistant the project context it needs before changing code, reducing guesses about the architecture and how to test the work.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is koei-kaji/zk-utils's own configuration. It tells Claude Code how to work on zk-utils itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything zk-utils configures →

Reuse

Borrowing it

Nothing to install: this file belongs to koei-kaji/zk-utils. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/koei-kaji/zk-utils/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/koei-kaji/zk-utils

Made for: Claude Code.

Wrote 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.

agentmods badge for zk-utils CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/koei-kaji/zk-utils/claude-md/github.svg)](https://agentmods.dev/instructions/koei-kaji/zk-utils/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/koei-kaji/zk-utils/claude-md"><img src="https://agentmods.dev/badge/instructions/koei-kaji/zk-utils/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.

agentmods 80×15 button for zk-utils CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/koei-kaji/zk-utils/claude-md"><img src="https://agentmods.dev/badge/instructions/koei-kaji/zk-utils/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 823 This file is loaded in full into every session.
When invoked 823 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00823 $0.00823
Opus 5 $0.00411 $0.00411
Sonnet 5 $0.00165 $0.00165
Haiku 4.5 $0.00082 $0.00082

Measured 9d ago against content hash 33e167b1476b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

zk-utils 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.

CLAUDE.md · 104 lines

What it actually says

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

zk-utilsは、zkノート管理ツール用のMCP(Model Context Protocol)サーバーです。zkと連携してノート検索、作成、リンク解析などの機能を提供します。

Architecture

プロジェクトはDDD(ドメイン駆動設計)とクリーンアーキテクチャを採用しています:

src/zk_utils/
├── domain/          # ドメインモデル(Note, Tag等)
├── application/     # ユースケース・アプリケーションサービス
├── infrastructure/ # 外部システム(zkコマンド)との連携
└── presentation/   # MCPサーバー(FastMCP)とDI設定

Key Components

  • ZkClient: zkコマンドラインツールとの連携(subprocess経由)
  • FastMCP: MCPサーバーフレームワーク
  • Injector: 依存性注入コンテナ
  • Note Domain Model: title, path, tags, contentを持つノートエンティティ

MCP Tools

MCPサーバーは以下のツールを提供:

  • get_notes: ノート一覧取得(ページネーション、検索、タグフィルタ対応)
  • get_note_content: 指定ノートの内容取得
  • get_link_to_notes: 指定ノートからのリンク先取得
  • get_linked_by_notes: 指定ノートへのリンク元取得
  • get_related_notes: 関連ノート取得
  • get_tags: タグ一覧取得
  • create_note: 新規ノート作成

Development Commands

Setup

# 依存関係のインストール
uv sync

Testing

# 全テスト実行
make test
# または
uv run pytest

# 特定のテストファイル実行
uv run pytest tests/test_specific.py

# カバレッジ付きテスト実行(pytest.iniで設定済み)
uv run pytest --cov=. --cov-report=term-missing

Linting & Formatting

# lintチェック(ruff + mypy)
make lint
# または
uv run ruff check .
uv run mypy --show-error-codes .

# フォーマット実行
make format
# または
uv run ruff check . --select I --fix-only --exit-zero
uv run ruff format .

# 全体チェック(format + lint + test)
make pre-commit

MCP Server Development

# MCPサーバー起動(開発用)
make mcp-run
# または
ZK_DIR=. uv run mcp dev src/zk_utils/presentation/mcp/server.py

Environment Variables

  • ZK_DIR: zkノートディレクトリのパス(MCPサーバー実行時に必要)

Key Dependencies

  • mcp[cli]: MCPサーバーフレームワーク
  • pydantic-settings: 設定管理
  • injector: 依存性注入
  • ruff: リンター・フォーマッター
  • mypy: 型チェック
  • pytest: テストフレームワーク

Notes

  • zkコマンドラインツールが事前にインストールされている必要があります
  • すべてのzkコマンド実行はsubprocessを通じて行われます
  • MCPサーバーはstdio transportで動作します
Changes

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.

  1. 9d ago First seen · 104 lines · 823 tokens per session scan A 33e167b1476b

Subscribe to this mod's changes

zk-utils CLAUDE.md is an instructions file published in the GitHub repository koei-kaji/zk-utils (1 stars, last pushed 1mo ago), licensed MIT. It adds 823 tokens to every session, about $0.0041 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.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

deepseek-ai/deepseek-harness · 3,735 tokens