Borrowing it
Nothing to install: this file belongs to kazukinagata/shinkoku. 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/kazukinagata/shinkoku/main/CLAUDE.mdgit clone --depth 1 https://github.com/kazukinagata/shinkokuWrote 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/kazukinagata/shinkoku/claude-md)<a href="https://agentmods.dev/instructions/kazukinagata/shinkoku/claude-md"><img src="https://agentmods.dev/badge/instructions/kazukinagata/shinkoku/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/kazukinagata/shinkoku/claude-md"><img src="https://agentmods.dev/badge/instructions/kazukinagata/shinkoku/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 | $0.04110 | $0.04110 |
| Opus 5 | $0.02055 | $0.02055 |
| Sonnet 5 | $0.00822 | $0.00822 |
| Haiku 4.5 | $0.00411 | $0.00411 |
Grade A, and why
shinkoku 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
shinkoku
確定申告自動化 Claude Code Plugin。Python 3.11+、SQLite WAL モードで動作する。 会社員＋副業（事業所得・青色申告）の所得税・消費税確定申告をエンドツーエンドで支援する。 帳簿管理・税額計算は CLI で実行し、確定申告書等作成コーナーへの入力は Claude in Chrome が代行する。
対象ペルソナ
Full = 計算＋確定申告書等作成コーナーへの入力代行、Out = 対象外
| ペルソナ | 対応レベル | 備考 |
|---|---|---|
| 個人事業主（青色申告・一般用） | Full | メインターゲット。帳簿→決算書→税額計算→作成コーナー入力 |
| 会社員＋副業（事業所得） | Full | 源泉徴収票＋事業所得の税額計算→作成コーナー入力 |
| 給与所得のみ（会社員） | Full | 還付申告・医療費控除等→作成コーナー入力 |
| 消費税課税事業者 | Full | 2割特例・簡易課税・本則課税すべて対応 |
| ふるさと納税利用者 | Full | CRUD + 控除計算 + 限度額推定 |
| 住宅ローン控除（初年度） | Full | 控除額計算。初年度は添付書類が別途必要 |
| 医療費控除 | Full | 明細集計＋控除額計算 |
| 仮想通貨トレーダー | Full | 雑所得（総合課税）として税額計算に自動反映 |
| 株式投資家（分離課税） | Out | 株式譲渡所得・配当の分離課税には対応していません |
| FXトレーダー | Out | 先物取引に係る雑所得等には対応していません |
| 不動産所得 | Out | 不動産所得用の決算書・申告に対応していません |
| 退職所得 | Out | 退職所得控除の計算に対応していません |
| 譲渡所得（不動産売却） | Out | 長期/短期税率、3,000万円特別控除なし |
| 外国税額控除 | Out | 外国税支払額の追跡・控除計算なし |
| 農業所得・山林所得 | Out | 専用所得区分なし |
| 非居住者 | Out | 日本居住者専用 |
対象外の機能
| 機能 | 理由 |
|---|---|
| マイナポータル連携 | freee 等の SaaS 固有機能（API 連携が前提） |
アーキテクチャ
skills/ (SKILL.md) ← 対話フロー定義（オープン標準 Agent Skills 仕様）
skills/reading-*/SKILL.md ← OCR 画像読取スキル（旧 agents/ の後継）
src/shinkoku/cli/ ← CLI エントリーポイント（shinkoku コマンド）
↓
src/shinkoku/tools/ ← ビジネスロジック（純粋関数）
↓
src/shinkoku/ ← コア（models, db, master_accounts）
- ツール呼び出し:
shinkoku <command> <subcommand>で実行（argparse サブコマンド + JSON 入出力） - ビジネスロジック:
src/shinkoku/tools/*.pyに純粋関数として定義（CLI から呼び出し）
コマンド
make dev # Claude Code をプラグインモードで起動
make test # 全テスト実行
make lint # Ruff lint チェック
uv run pytest tests/unit/ -v # ユニットテストのみ
uv run pytest tests/scripts/ -v # CLI スクリプトテスト
uv run pytest tests/integration/ -v # 統合テスト
uv run mypy src/shinkoku/ --ignore-missing-imports # 型チェック
uv run ruff format --check src/ tests/ # フォーマットチェック
CLI 呼び出し例
# 帳簿 CRUD
uv run shinkoku ledger init --db-path shinkoku.db --fiscal-year 2025
uv run shinkoku ledger journal-add --db-path shinkoku.db --input journal.json
uv run shinkoku ledger trial-balance --db-path shinkoku.db --fiscal-year 2025
# 税額計算
uv run shinkoku tax calc-income --input income_params.json
# データ取込
uv run shinkoku import csv --file-path transactions.csv
# ふるさと納税
uv run shinkoku furusato summary --db-path shinkoku.db --fiscal-year 2025
# PDF ユーティリティ
uv run shinkoku pdf extract-text --file-path document.pdf
uv run shinkoku pdf to-image --file-path document.pdf --output-dir output/images
# プロファイル
uv run shinkoku profile --config shinkoku.config.yaml
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 · +32 tokens per session cac757cafa80
- 11d ago First seen · 272 lines · 4,078 tokens per session scan A a3745d253513
shinkoku CLAUDE.md is an instructions file published in the GitHub repository kazukinagata/shinkoku (359 stars, last pushed yesterday), licensed MIT. It adds 4,110 tokens to every session, about $0.0205 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
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.