classify

classify is a command for coding agents from michielinksee/bantou. It costs 16 tokens per session (501 once invoked), scanned A, original, MIT.

A command that classifies one Japanese business transaction into an accounting category and tax type. It checks exclusions, past corrections, known keywords, and uses AI when needed.

In plain words
What is it for?
Classifying expenses such as shop purchases, cloud services, taxis, and client entertainment, with amounts or context when available.
Why use it?
It turns a free-text expense description into a structured accounting result and flags uncertain cases for review.

Command

Part of the bantou plugin — 5 skills, 6 commands, 1 MCP server shipped together

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/classify
Clone the repo
git clone --depth 1 https://github.com/michielinksee/bantou

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.

agentmods badge for classify

README.md
[![agentmods](https://agentmods.dev/badge/commands/michielinksee/bantou/classify.svg)](https://agentmods.dev/commands/michielinksee/bantou/classify)
Your own site
<a href="https://agentmods.dev/commands/michielinksee/bantou/classify"><img src="https://agentmods.dev/badge/commands/michielinksee/bantou/classify.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 501 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.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.00501
Opus 5 $0.00008 $0.00251
Sonnet 5 $0.00003 $0.00100
Haiku 4.5 $0.00002 $0.00050

Measured 4d ago against content hash aa25a55fe925, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

classify 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 4d 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/classify.md · 70 lines

What it actually says

/bantou:classify

Classify a single Japanese business transaction through the full 3-stage pipeline.

Usage

/jp-accounting:classify <description>

Examples

/jp-accounting:classify スタバ 渋谷店 ¥580
/jp-accounting:classify Amazon Web Services ¥45,000
/jp-accounting:classify タクシー 新宿→品川 ¥3,200
/jp-accounting:classify 取引先接待 居酒屋 6名 ¥48,000

Input

A free-text transaction description. Can include:

  • Vendor/store name
  • Amount (optional but improves accuracy)
  • Location or context details
  • Number of participants (relevant for 会議費 vs 交際費)

Pipeline execution

The command runs the full classification pipeline:

  1. Exclusion check — Is this a classifiable transaction?
  2. Memory recall — Has this vendor been corrected before?
  3. Keyword match — Does it match a known category pattern?
  4. AI classification — Claude analyzes the description (if needed)

Output

Returns a structured result:

勘定科目: 会議費
税区分:   課税仕入 10%
信頼度:   92%
判定方法: Memory (過去の修正パターン一致)

If confidence is below 70%, the output shows the top-2 candidates:

勘定科目: 会議費 or 交際費 (要確認)
税区分:   課税仕入 10%
信頼度:   58%
判定方法: AI (低信頼度 — 税理士確認推奨)
候補1: 会議費 (58%) — 1人あたり¥8,000、5,000円基準超過の可能性
候補2: 交際費 (35%) — 接待目的の場合

Notes

  • If the transaction is excluded (Stage 0), the exclusion reason is shown
  • Classification results are not automatically saved; use /jp-accounting:correct to submit corrections if the result is wrong
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. 4d ago First seen · 70 lines · 16 tokens per session scan A aa25a55fe925

Subscribe to this mod's changes

classify is a command published in the GitHub repository michielinksee/bantou (2 stars, last pushed 13d ago), licensed MIT. It adds 16 tokens to every session and 501 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.