Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add kazukinagata/shinkoku/plugin install 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/consumption-tax)<a href="https://agentmods.dev/skills/kazukinagata/shinkoku/consumption-tax"><img src="https://agentmods.dev/badge/skills/kazukinagata/shinkoku/consumption-tax/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/consumption-tax"><img src="https://agentmods.dev/badge/skills/kazukinagata/shinkoku/consumption-tax.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 | $0.00122 | $0.04420 |
| Opus 5 | $0.00061 | $0.02210 |
| Sonnet 5 | $0.00024 | $0.00884 |
| Haiku 4.5 | $0.00012 | $0.00442 |
Grade A, and why
consumption-tax 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 2d 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 — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.
消費税計算(Consumption Tax Calculation)
課税売上・課税仕入から消費税額を計算するスキル。
assess スキルで消費税の課税事業者と判定され、settlement スキルで決算が完了していることを前提とする。
計算結果は /e-tax スキル(Claude in Chrome)で確定申告書等作成コーナーに入力する。
設定の読み込み(最初に実行)
shinkoku.config.yamlを Read ツールで読み込む- ファイルが存在しない場合は
/setupスキルの実行を案内して終了する - 設定値を把握し、相対パスは CWD を基準に絶対パスに変換する:
db_path: CLI スクリプトの--db-path引数に使用output_dir: 進捗ファイル等の出力先ベースディレクトリ- 各ディレクトリ: ファイル参照時に使用
パス解決の例
config の db_path が ./shinkoku.db で CWD が /home/user/tax-2025/ の場合:
shinkoku tax calc-consumption --input /home/user/tax-2025/output/consumption_input.json
進捗情報の読み込み
設定の読み込み後、引継書ファイルを読み込んで前ステップの結果を把握する。
.shinkoku/progress/progress-summary.mdを Read ツールで読み込む(存在する場合)- 以下の引継書を Read ツールで読み込む(存在する場合):
.shinkoku/progress/06-settlement.md.shinkoku/progress/02-assess.md
- 読み込んだ情報を以降のステップで活用する(ユーザーへの再質問を避ける)
- ファイルが存在しない場合はスキップし、ユーザーに必要情報を直接確認する
基本方針
- assess スキルの判定結果(課税事業者判定・申告方法)を確認してから開始する
- 免税事業者の場合は消費税申告不要であることを案内して終了する
- 申告方法(2割特例/簡易課税/本則課税)に応じた計算を行う
- 税率区分(標準税率10%/軽減税率8%)を正確に区分する
- references/tax-classification.md の区分ルールに従って判定する
前提条件の確認
消費税計算を開始する前に以下を確認する:
- 課税事業者であるか: assess スキルの判定結果を確認する
- 申告方法の確定: 以下のいずれかを確認する
- 2割特例(インボイス登録により課税事業者になった場合の経過措置)
- 簡易課税(届出済みで基準期間の課税売上が5,000万円以下)
- 本則課税(上記以外)
- 課税期間: 通常は1月1日〜12月31日(個人事業者)
- 帳簿データが揃っているか: settlement スキルの決算が完了していること
申告方法の判定フロー
Q1. インボイス登録により課税事業者になったか?
かつ基準期間の課税売上が1,000万円以下か?
├── Yes → 2割特例の適用が可能 → Q2へ
└── No → Q3へ
Q2. 2割特例を適用するか?
├── Yes → 2割特例で計算
└── No → Q3へ(簡易課税・本則課税と比較して有利な方を選択可能)
Q3. 簡易課税制度選択届出書を提出済みで、
基準期間の課税売上が5,000万円以下か?
├── Yes → 簡易課税で計算
└── No → 本則課税で計算
ステップ1: 課税売上の集計
帳簿から課税売上高を税率区分別に集計する。ledger.py trial-balance や ledger.py search の結果から以下を算出する:
集計項目
| 項目 | 説明 |
|---|---|
| 課税売上高(税込) | 税率10%と軽減税率8%を区分して集計 |
| 課税売上高(税抜) | 課税標準額(1,000円未満切り捨て) |
| 非課税売上高 | 受取利息等の非課税取引 |
| 免税売上高 | 輸出取引等(該当する場合) |
勘定科目との対応
- 売上(4001): 通常は課税売上(tax_category = taxable)
- 受取利息(4100): 非課税売上(tax_category = non_taxable)
- 雑収入(4110): 内容に応じて課税/非課税を判定
What ships with it
2 files 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.
- 2d ago Changed · +6 lines 41111867c5ab
- 13d ago First seen · 337 lines · 122 tokens per session scan A d39508dec1da
consumption-tax is a skill published in the GitHub repository kazukinagata/shinkoku (359 stars, last pushed 3d ago), licensed MIT. It adds 122 tokens to every session and 4,420 once invoked, about $0.0006 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 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…
vertical-fintech-mobile
Domain-knowledge pack for money on a phone — wallets, payments, custody and signing, transaction lifecycle, KYC/AML gates, and offline reconciliation. The rules that separate a payments app from a CRUD app with a currency symbol: a balance is a claim about a server, an idempotency key must outlive the process that…
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-granian
Auto-activate for litestargranian, GranianPlugin, litestar run Granian options, runtime threads, HTTP/2, TLS, access logs, metrics, static mounts, or worker lifecycle. Not for non-Granian servers.
litestar-testing
Auto-activate for test.py, conftest.py, litestar.testing, TestClient, AsyncTestClient, createtestclient, createasynctestclient, anyio, Guard mocks, DI overrides, or handler tests. Not for generic pytest.