jangbu-import

jangbu-import is a skill for Claude Code, Codex from kimlawtech/korean-jangbu-for. It costs 97 tokens per session (2,185 once invoked), scanned A, original, Apache-2.0.

A data-import workflow for turning bank files, card records, spreadsheets, receipts, tax invoices, and statement PDFs into a standard set of 13 transaction fields. OCR, or optical character recognition, is used to read information from document images and PDFs.

In plain words
What is it for?
Use it to import CSV and Excel records, extract transactions from receipts and financial PDFs, process supported card statements, and produce standard transaction data.
Why use it?
It reduces manual entry and gives different financial sources a consistent format, while masking sensitive information during document processing.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to import CSV and Excel records, extract transactions from receipts and financial PDFs, process supported card statements, and produce standard transaction data.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kimlawtech/korean-jangbu-for/jangbu-import
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 kimlawtech/korean-jangbu-for --skill jangbu-import
Clone the repo
git clone --depth 1 https://github.com/kimlawtech/korean-jangbu-for

Made for: Claude Code, Codex.

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 jangbu-import

README.md
[![agentmods](https://agentmods.dev/badge/skills/kimlawtech/korean-jangbu-for/jangbu-import/github.svg)](https://agentmods.dev/skills/kimlawtech/korean-jangbu-for/jangbu-import)
Your own site
<a href="https://agentmods.dev/skills/kimlawtech/korean-jangbu-for/jangbu-import"><img src="https://agentmods.dev/badge/skills/kimlawtech/korean-jangbu-for/jangbu-import/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 jangbu-import

Your own site · 80×15
<a href="https://agentmods.dev/skills/kimlawtech/korean-jangbu-for/jangbu-import"><img src="https://agentmods.dev/badge/skills/kimlawtech/korean-jangbu-for/jangbu-import.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,185 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00097 $0.02185
Opus 5 $0.00048 $0.01092
Sonnet 5 $0.00019 $0.00437
Haiku 4.5 $0.00010 $0.00218

Measured 12d ago against content hash 1be59443f8a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

jangbu-import 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 12d 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.

skills/jangbu-import/SKILL.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

jangbu-import

원본 파일 → 표준 거래내역 변환 스킬.

입력 지원

소스 포맷 MCP 도구
은행 거래내역 CSV ingest_raw(source_type="bank")
카드 거래내역 CSV ingest_raw(source_type="card")
수기 장부 엑셀 ingest_raw(source_type="manual")
영수증 JPG/PNG/PDF ocr_document(doc_type="receipt")
세금계산서 PDF ocr_document(doc_type="tax_invoice")
통장 스캔 JPG/PDF ocr_document(doc_type="bank_statement_scan")
카드사 회원이용내역서 PDF ocr_document(doc_type="card_statement_scan")

카드명세서 지원 현황:

  • 신한카드 회원이용내역서 — 완전 지원 (표 파서 구현)
  • 국민·삼성·현대·롯데·우리·하나·BC카드 — 발급사 자동 탐지만 지원, 파서는 LLM fallback

표준 스키마 (13개 필드)

필수 9 + 확장 4.

  • 필수: transaction_id, date, amount, currency, direction, counterparty, description, source, source_ref
  • 확장: raw_description, account_id, matched_account, confidence

인터뷰 플로우

Step 1. 입력 소스 확인

어떤 데이터를 추가하시겠습니까?

[1] 은행 거래내역 (CSV)
[2] 카드 거래내역 (CSV)
[3] 엑셀 장부 (xlsx)
[4] 영수증 이미지/PDF (PaddleOCR 처리)
[5] 세금계산서 PDF (PaddleOCR 처리)
[6] 카드사 회원이용내역서 PDF (PaddleOCR + 표 파서)
[7] 여러 파일 일괄 업로드

번호를 입력하세요.

[6] 카드명세서 PDF 선택 시 경고:

⚠ 카드사 회원이용내역서에는 주민번호·사업자번호 등 민감정보가
포함되어 있습니다. 처리 전 확인:

1. 본인 소유 문서가 맞습니까? [Y/n]
2. 파일은 ~/.jangbu/raw/ocr/ 에만 저장되며
   LLM에는 마스킹 뷰와 요약만 전달됩니다.

Step 2. 파일 경로·메타데이터 수집

  • 파일 경로 (절대경로 권장)
  • account_id (내부 계좌/카드 ID, 예: acct_shinhan_001, card_bc_002)
  • 은행이면 은행명 (generic / kb / shinhan / woori / hana / ibk)

Step 3. MCP 서버 호출

CSV/엑셀 (선택지 1·2·3):

ingest_raw(
    file_path="/절대/경로/파일.csv",
    source_type="bank",  # or card / manual
    account_id="acct_shinhan_001",
    bank="shinhan"  # bank일 때만
)

OCR (선택지 4·5·6·7):

ocr_document(
    file_path="/절대/경로/영수증.jpg",
    doc_type="receipt",  # receipt / tax_invoice / bank_statement_scan / card_statement_scan
    account_id="card_bc_002",  # 카드명세서면 base prefix로 사용, 카드별 last3 자동 suffix
    auto_ingest=True  # 영수증·카드명세서면 자동 거래 등록
)

카드명세서 응답 예시:

{
  "doc_type": "card_statement_scan",
  "parsed_rows": 287,
  "ingested": 285,
  "duplicates_skipped": 2,
  "issuer": "shinhan",
  "period": {"start": "2025-07-01", "end": "2025-12-31"},
  "card_last3_list": ["039", "122"],
  "unparsed_count": 3,
  "needs_llm_fallback": false,
  "structured": {
    "rows_sample": [
      {"use_date": "2025-07-01", "merchant": "가상식당 테스트점",
       "amount": "6500", "biz_id": "TK_BIZ_ID_a1b2", "card_last3": "122"}
    ]
  }
}

Read the full file on GitHub · 220 lines

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. 12d ago First seen · 220 lines · 97 tokens per session scan A 1be59443f8a6

Subscribe to this mod's changes

jangbu-import is a skill published in the GitHub repository kimlawtech/korean-jangbu-for (83 stars, last pushed 13d ago), licensed Apache-2.0. It adds 97 tokens to every session and 2,185 once invoked, about $0.0005 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.