An interactive setup wizard for configuring a Japanese tax accountant's office. It asks about the firm, clients, accounting software, expense rules, overseas services, invoices, payroll, and report sharing.

Use it during initial setup to enter firm details, choose accounting and payroll systems, define expense and overseas-service handling, and set report-sharing preferences.

It gathers the office's working rules and software choices before the accounting assistant is used.

setup — Command for Claude Code by michielinksee: An interactive setup wizard for configuring a Japanese tax…

Install

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.

agentmods

npx agentmods add commands/michielinksee/bantou/setup

Clone the repo

git clone --depth 1 https://github.com/michielinksee/bantou

Made for: Claude Code.

Or install bantou, the plugin that ships this one along with the rest of its 5 skills, 6 commands, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/michielinksee/bantou/setup.svg)](https://agentmods.dev/commands/michielinksee/bantou/setup)

Your own site

<a href="https://agentmods.dev/commands/michielinksee/bantou/setup"><img src="https://agentmods.dev/badge/commands/michielinksee/bantou/setup.svg" alt="Measured on agentmods" height="20"></a>

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 605 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00016	$0.00605
Opus 5	$0.00008	$0.00302
Sonnet 5	$0.00003	$0.00121
Haiku 4.5	$0.00002	$0.00060

Measured 5d ago against content hash b18798ee6c41, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 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.

packages/claude-for-jp-accounting/commands/setup.md · 75 lines

What it actually says

/bantou:setup

Initial firm onboarding. Conducts a guided interview to configure the plugin for the tax accountant's office.

Usage

/jp-accounting:setup

No arguments required. The command starts an interactive interview.

Interview flow (approximately 10 minutes)

The setup agent asks the following 8 questions in sequence. Each question adapts based on previous answers.

Q1. Firm name (事務所名)

"事務所名を教えてください。"

Q2. Client count (顧問先数)

"顧問先は何社ぐらいありますか？（概算で構いません）"

Q3. Primary accounting software (メインの会計ソフト)

"メインで使っている会計ソフトを教えてください。" Options: freee / 弥生会計 / MFクラウド / TKC / 複数併用

Q4. Meal expense threshold (会議費・交際費の区分基準)

"飲食代の会議費/交際費の区分は、1人あたり何円を基準にしていますか？" Default: ¥5,000 (tax law standard) or ¥10,000 (2024 revision)

Q5. Overseas SaaS handling (海外SaaSの処理)

"海外SaaS（AWS, GitHub, Slack等）の仕訳ルールを教えてください。" Covers: reverse charge, withholding tax, yen conversion timing

Q6. Invoice system status (インボイス制度対応)

"適格請求書発行事業者の登録番号をお持ちですか？免税事業者の顧問先はありますか？"

Q7. Payroll processing (給与計算)

"給与計算も事務所で処理していますか？使用している給与ソフトがあれば教えてください。"

Q8. Report sharing method (レポート共有方法)

"顧問先へのレポート共有はどの方法がメインですか？" Options: email / chatwork / LINE WORKS / Slack / PDF郵送

Output

After the interview, the setup command:

Generates a customized CLAUDE.md from the standard baseline template
Configures the keyword dictionary based on the firm's conventions
Suggests freee/Yayoi API connection setup if applicable
Saves the firm profile to data/firm-profile.json

Notes

Setup can be re-run at any time to update the configuration
All answers are stored locally, never sent to cloud services
The generated CLAUDE.md can be manually edited afterward

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.

5d ago First seen · 75 lines · 16 tokens per session scan A b18798ee6c41

Subscribe to this mod's changes

setup is a command published in the GitHub repository michielinksee/bantou (2 stars, last pushed 14d ago), licensed MIT. It adds 16 tokens to every session and 605 once invoked, about $0.0001 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.

Finance and fintech accounting ai-agent automation bookkeeping claude fintech

setup