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.
npx skills add kimlawtech/korean-jangbu-for --skill jangbu-taxgit clone --depth 1 https://github.com/kimlawtech/korean-jangbu-forWrote 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/kimlawtech/korean-jangbu-for/jangbu-tax)<a href="https://agentmods.dev/skills/kimlawtech/korean-jangbu-for/jangbu-tax"><img src="https://agentmods.dev/badge/skills/kimlawtech/korean-jangbu-for/jangbu-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/kimlawtech/korean-jangbu-for/jangbu-tax"><img src="https://agentmods.dev/badge/skills/kimlawtech/korean-jangbu-for/jangbu-tax.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00082 | $0.01043 |
| Opus 5 | $0.00041 | $0.00522 |
| Sonnet 5 | $0.00016 | $0.00209 |
| Haiku 4.5 | $0.00008 | $0.00104 |
Grade A, and why
jangbu-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 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.
What it actually says
jangbu-tax
세무용 재무제표 생성 스킬.
생성 가능한 리포트
| 리포트 | 도구 | 집계 기준 |
|---|---|---|
| 손익계산서 (PL) | export_report(report_type="pl") |
기간 내 수익·비용 |
| 재무상태표 (BS, 간이) | export_report(report_type="bs") |
as_of 기준 누적 잔액 |
인터뷰 플로우
Step 1. 리포트 유형 선택
어떤 리포트를 생성하시겠습니까?
[1] 손익계산서 (PL) — 기간 수익·비용
[2] 재무상태표 (BS) — 특정 시점 자산·부채·자본
[3] 둘 다
번호를 입력하세요.
Step 2. 기간 입력
PL 선택 시:
기간을 지정해주세요.
[1] 직전 월 (2026-03)
[2] 직전 분기 (2026 Q1)
[3] 올해 누적 (2026-01-01 ~ 오늘)
[4] 직접 입력 (YYYY-MM-DD ~ YYYY-MM-DD)
BS 선택 시:
기준일(as_of)을 입력하세요. 기본값: 오늘.
Step 3. 사전 검증
list_transactions(unclassified_only=True)호출- 미분류 건이 있으면 경고:
미분류 거래 N건이 있습니다. 리포트에 반영되지 않습니다. [1] 그대로 진행 [2] 먼저 jangbu-tag로 분류
Step 4. 리포트 생성
# PL
export_report(
report_type="pl",
period_start="2026-04-01",
period_end="2026-04-30",
fmt="json"
)
# BS
export_report(
report_type="bs",
as_of="2026-04-30",
fmt="json"
)
Step 5. 결과 표시
MCP 서버는 요약만 반환. 예시:
손익계산서 (2026-04-01 ~ 2026-04-30)
- 매출: 15,000,000원
- 비용: 8,500,000원
- 순이익: 6,500,000원
출력 파일: ~/.jangbu/reports/pl_2026-04-22.json
전체 계정별 내역은 로컬 파일에서 확인.
Step 6. CSV 변환 옵션
CSV로도 받으시겠습니까?
(세무사·회계사무소 전달용)
[1] 네 → fmt="csv"로 재호출
[2] 아니오
국세청 계정 매핑
- 내부 계정
광고선전비_구글→ 국세청광고선전비(코드 833) - 매핑 테이블:
accounts/nts_standard.json - BS/PL 구분은 매핑 테이블의
statement필드
한계 (명시 필수)
- 분개 엔진 없음 — 정식 BS는 복식부기 분개가 필요. 현재는 현금주의 기반 간이 집계.
- 자산 감가상각 미반영 — 비품·차량 구입 시 전액 비용 처리. 감가상각은 세무사 조정 필요.
- 부가세 처리 간이 — 매입세액·매출세액 자동 상계 없음. 부가세 신고는 별도 프로세스 권장.
- 주석 미생성 — 외감용 주석은 포함되지 않음.
리포트 출력 말미에 반드시 다음 면책 표시:
※ 본 리포트는 참고용 초안입니다.
※ 법인세 신고 전 세무사 검토 필수.
※ 외감 대상은 공인회계사 감사 필수.
보안
export_report는 MCP 서버 내부에서 언마스킹된 원본으로 집계- LLM에 반환되는 응답은 요약 + 파일 경로만
- 세부 계정별 금액 열람은 사용자가 직접 파일을 열어 확인
- 모든 호출은 audit.log 기록
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.
- 12d ago First seen · 129 lines · 82 tokens per session scan A a49cc3a2fc47
jangbu-tax is a skill published in the GitHub repository kimlawtech/korean-jangbu-for (83 stars, last pushed 14d ago), licensed Apache-2.0. It adds 82 tokens to every session and 1,043 once invoked, about $0.0004 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
bookkeeping
Use when a small business needs audit-ready books — a chart of accounts, posting a transaction to the right account and side, clearing an uncategorized bank feed, cash vs accrual, or a ledger that won't tie to the bank. NOT interpreting the numbers — runway, burn, P&L cadence (that is finance-ops), NOT issuing…
countbean-accounting
Rules for writing correct double-entry Beancount transactions when managing a Countbean cloud book — account naming, how to balance postings, categorisation, and safe ingestion. Use whenever recording, importing, or correcting financial data in a Countbean book.
bukio-cli
Drive bukio-cli — agent-first double-entry bookkeeping for SMEs across eleven jurisdictions. Book invoices, archive the originals, keep the books balanced.
QuickBooks Automation
Automate QuickBooks accounting workflows including invoicing, expenses, reporting, and bank reconciliation.
ledger
Use for ANY monetary, accounting, ledger, journal, balance, P&L, fee, FX, invoice, tax, cost-basis, or valuation work. Exact Money.from (never floats or parseFloat), double-entry via JournalEntry + validateEntry + Ledger.apply, MCP moneycompute / ledgerpost, canon citations, Zero-Skip + Canonical Financial Artifact.…
ledger-audit
Whole-repo financial audit. Use for ledger-audit, financial audit, or /ledger-audit. Scan for non-kernel money math, reconstruct flows as JournalEntry sequences, prove with validateEntry + Ledger.apply + runTrace + auditHash.