Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add kazukinagata/shinkoku --skill setupgit 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/skills/kazukinagata/shinkoku/setup)<a href="https://agentmods.dev/skills/kazukinagata/shinkoku/setup"><img src="https://agentmods.dev/badge/skills/kazukinagata/shinkoku/setup/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/skills/kazukinagata/shinkoku/setup"><img src="https://agentmods.dev/badge/skills/kazukinagata/shinkoku/setup.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 | $0.00089 | $0.05707 |
| Opus 5.5 | $0.00036 | $0.02283 |
| Sonnet 5.5 | $0.00018 | $0.01141 |
| Haiku 4.5 | $0.00009 | $0.00571 |
Grade A, and why
setup 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 1mo 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 — 481 lines — stays where its author put it; the contents beside it link to each section on GitHub.
セットアップウィザード（Setup Wizard）
shinkoku の初回セットアップを対話的に行うスキル。
設定ファイル（shinkoku.config.yaml）の生成とデータベースの初期化を実施する。
ステップ0: CLI のインストール確認
shinkoku コマンドが利用可能か確認する。
shinkoku --versionを実行する- コマンドが存在しない場合:
uv tool install git+https://github.com/kazukinagata/shinkokuを実行してインストールする - コマンドが存在する場合:
uv tool upgrade shinkokuを実行して最新版に更新する
ステップ1: 既存設定の確認
CWD の shinkoku.config.yaml を Read ツールで読み込む。
- ファイルが存在する場合: 内容を表示し、更新するか確認する。更新しない場合はスキルを終了する。
- ファイルが存在しない場合: セットアップウィザードを開始する。
ステップ2: 基本設定のヒアリング
以下の項目を AskUserQuestion で確認する:
2-1. 対象年度
tax_year: 確定申告の対象年度（デフォルト: 2025）
2-1b. 事業所得の有無
has_business_income: 事業所得（副業含む）の有無（true / false）
事業所得がない場合、以下のステップをスキップする:
- 2-2（インボイス登録番号）
- 2.6-3（事業所住所）
- 2.7（事業情報）
- 2.8 の申告の種類（blue/white）・記帳方法の質問（給与所得のみなら不要）
2-2. 適格請求書発行事業者の登録番号（事業所得がある場合のみ）
invoice_registration_number: T + 13桁の番号（任意、スキップ可）
ステップ2.5: 納税者情報のヒアリング
以下の項目を AskUserQuestion で段階的に確認する。すべて任意（スキップ可能）だが、確定申告書等作成コーナーへの入力や人的控除の判定に使用される。
2.5-1. 氏名
taxpayer.last_name: 姓taxpayer.first_name: 名taxpayer.last_name_kana: 姓（カタカナ）taxpayer.first_name_kana: 名（カタカナ）
2.5-2. 基本情報
taxpayer.gender: 性別（male / female）taxpayer.date_of_birth: 生年月日（YYYY-MM-DD）taxpayer.phone: 電話番号taxpayer.relationship_to_head: 世帯主との続柄（本人/妻/夫/子等）
2.5-3. マイナンバー
taxpayer.my_number: マイナンバー12桁（取扱注意 — config に保存するが、ツール出力やログには一切表示しない）
2.5-4. 人的控除に関する状態（任意）
taxpayer.widow_status: 寡婦/ひとり親の区分（none / widow / single_parent）taxpayer.disability_status: 障害者の区分（none / general / special）taxpayer.working_student: 勤労学生に該当するか（true / false）
ステップ2.6: 住所情報のヒアリング
2.6-1. 自宅住所
address.postal_code: 郵便番号address.prefecture: 都道府県address.city: 市区町村address.street: 番地address.building: 建物名・部屋番号（任意）
2.6-2. 1月1日時点の住所（異なる場合のみ）
address.jan1_address: 1/1 時点の住所（住民税の課税自治体判定に使用）
2.6-3. 事業所住所（事業所得がある場合のみ。自宅と異なる場合のみ）
business_address.postal_code〜business_address.building
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 481 lines · 89 tokens per session scan A 84fb25eb222a
setup is a skill published in the GitHub repository kazukinagata/shinkoku (366 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 5,707 once invoked, about $0.0004 per session on Opus 5.5. 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 skills, from other repositories
capitoltrades-cli
Queries US congressional stock trades (STOCK Act disclosures) on capitoltrades.com via the cli-web-capitoltrades command-line tool — trades with rich filters, politician profiles and leaderboards, issuer lookup with price history, plus insight articles, buzz, and press. Use when the user asks about congress trades…
product-economics
Does this product make money at a price someone will pay? Forces contribution margin, a price with a stated basis, and a bottom-up market size — each number labelled measured / assumed / unknown, so a guess can never be read as a calculation.
quant-validation
The methods a financial-ML result has to survive before it is evidence — purged cross-validation with an embargo, triple-barrier labelling, sample uniqueness under overlapping labels, fractional differentiation, meta-labelling, and multiple-testing correction. Written because the invariants were required of…
litestar-testing
Auto-activate for test.py, conftest.py, litestar.testing, TestClient, AsyncTestClient, createtestclient, createasynctestclient, anyio, Guard mocks, or DI overrides. Not for generic pytest.
litestar
Auto-activate for Litestar, Controller, Router, @get/@post, FromPath, MsgspecDTO, OpenAPIConfig, Provide, FromDishka, Guard, ASGIMiddleware, HTTPException, ChannelsPlugin, or WebSocket. Not for standalone libs.
msgspec
Auto-activate for msgspec, Struct, Meta, msgspec.json, msgspec.msgpack, tagged unions, enchook, dechook, convert(), or Litestar DTO shapes. Not for Pydantic or ORM models — use their stack-specific skill.