reading-deduction-cert

reading-deduction-cert is a skill for Claude Code from kazukinagata/shinkoku. It costs 63 tokens per session (1,393 once invoked), scanned A, original, MIT.

An image-reading workflow for extracting structured information from Japanese insurance and social-insurance deduction certificates. It can read image files and PDFs, including scanned PDFs.

In plain words
What is it for?
Use it to capture insurance premiums, certificate amounts, dates, and related details for a tax return.
Why use it?
It turns paper documents into usable data and provides a second reading or visual confirmation to catch errors in amounts, dates, and other fields.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the shinkoku plugin — 24 skills shipped together

Good fit Use it to capture insurance premiums, certificate amounts, dates, and related details for a tax return.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kazukinagata/shinkoku/reading-deduction-cert
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.

Any agent
npx skills add kazukinagata/shinkoku --skill reading-deduction-cert
Clone the repo
git clone --depth 1 https://github.com/kazukinagata/shinkoku

Made for: Claude Code.

Or install shinkoku, the plugin that ships this one along with the rest of its 24 skills.

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 reading-deduction-cert

README.md
[![agentmods](https://agentmods.dev/badge/skills/kazukinagata/shinkoku/reading-deduction-cert/github.svg)](https://agentmods.dev/skills/kazukinagata/shinkoku/reading-deduction-cert)
Your own site
<a href="https://agentmods.dev/skills/kazukinagata/shinkoku/reading-deduction-cert"><img src="https://agentmods.dev/badge/skills/kazukinagata/shinkoku/reading-deduction-cert/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.

agentmods 80×15 button for reading-deduction-cert

Your own site · 80×15
<a href="https://agentmods.dev/skills/kazukinagata/shinkoku/reading-deduction-cert"><img src="https://agentmods.dev/badge/skills/kazukinagata/shinkoku/reading-deduction-cert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,393 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00063 $0.01393
Opus 5 $0.00032 $0.00696
Sonnet 5 $0.00013 $0.00279
Haiku 4.5 $0.00006 $0.00139

Measured 11d ago against content hash b4a94c16416f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

reading-deduction-cert 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 11d 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.

Origin

Copies of this mod

3 near-identical copies found in the catalogue:

skills/reading-deduction-cert/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

控除証明書 画像読み取り

控除証明書(生命保険料控除証明書、地震保険料控除証明書、社会保険料控除証明書等)の画像を読み取り、構造化データとして返すスキル。

PDF ファイルの場合

ファイルが PDF(.pdf)の場合、画像 OCR の前にテキスト抽出を試みる。

  1. shinkoku pdf extract-text --file-path <path> を実行する
  2. 抽出テキストに必要な情報(保険料額・証明額等)が含まれていれば、テキストから構造化データを生成する
  3. テキストが不十分(スキャン PDF 等)の場合は shinkoku pdf to-image --file-path <path> --output-dir <dir> で PNG に変換し、以下の画像読み取りフローに進む

画像読み取り方法

推奨: デュアル検証(並列2コンテキスト)

精度を高めるため、同じ画像を2つの独立したコンテキストで並列に読み取り、結果を照合する。

  1. 2つの独立した読み取りを実行する: サブエージェントが使える環境では、2つのサブエージェントを並列で起動し、それぞれ独立に画像を読み取る。 各サブエージェントには以下の「基本ルール」と「出力フォーマット」をプロンプトとして渡し、画像ファイルパスを指定する。

  2. 結果照合: 両方の読み取り結果から主要フィールド(金額等)を比較する。

  3. 一致の場合: そのまま採用。「2つの独立した読み取りで結果が一致しました」と報告する。

  4. 不一致の場合: ユーザーに元画像パスと両方の結果を提示し、正しい方を選択してもらう:

    • 差異のあるフィールドを明示する
    • A を採用 / B を採用 / 手動入力 の3択を提示する

フォールバック(サブエージェント非対応の場合)

サブエージェントが利用できない環境では、以下の手順で読み取る:

  1. 画像ファイルを直接 Read ツールで読み取る
  2. 以下の「基本ルール」と「出力フォーマット」に従ってデータを抽出する
  3. 抽出結果をユーザーに提示し、必ず目視確認を依頼する

⚠ デュアル検証が利用できないため、必ずユーザーに目視確認を依頼してください。

基本ルール

  • 画像ファイルは Read ツールで読み取る(Claude Vision が自動的に画像を認識する)
  • 金額は必ず int(円単位の整数)で返す。カンマや「円」は除去する
  • 日付は YYYY-MM-DD 形式で返す
  • 和暦は西暦に変換する(令和7年 → 2025、令和6年 → 2024、平成31年 → 2019)
  • 読み取れないフィールドは UNKNOWN(文字列)または 0(金額)とする

対象書類

  • 生命保険料控除証明書
  • 地震保険料控除証明書
  • 社会保険料(国民年金保険料)控除証明書
  • 小規模企業共済等掛金払込証明書(iDeCo含む)

出力フォーマット

JSON オブジェクトとして返す。金額は必ず int(円単位の整数)とする。

生命保険料控除証明書

{
  "certificate_type": "life_insurance",
  "policy_type": "新制度 or 旧制度",
  "category": "一般 or 介護医療 or 個人年金",
  "company_name": "保険会社名",
  "policy_number": "証券番号",
  "annual_premium": 120000,
  "dividend": 0
}

地震保険料控除証明書

{
  "certificate_type": "earthquake_insurance",
  "company_name": "保険会社名",
  "policy_number": "証券番号",
  "annual_premium": 50000,
  "is_old_long_term": false
}

社会保険料控除証明書

{
  "certificate_type": "social_insurance",
  "insurance_type": "national_pension",
  "annual_premium": 200000,
  "period": "対象期間"
}

小規模企業共済等掛金払込証明書

{
  "certificate_type": "small_business_mutual_aid",
  "sub_type": "ideco or small_business or disability",
  "annual_contribution": 276000
}

Read the full file on GitHub · 121 lines

Files

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.

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. 11d ago First seen · 121 lines · 63 tokens per session scan A b4a94c16416f

Subscribe to this mod's changes

reading-deduction-cert is a skill published in the GitHub repository kazukinagata/shinkoku (359 stars, last pushed 2d ago), licensed MIT. It adds 63 tokens to every session and 1,393 once invoked, about $0.0003 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.

Related

Other skills, from other repositories