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 agentmods add agents/boxlogodev/sapstack/sap-fi-consultantgit clone --depth 1 https://github.com/BoxLogoDev/sapstackWhat 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 | $0.00081 | $0.01426 |
| Opus 5 | $0.00041 | $0.00713 |
| Sonnet 5 | $0.00016 | $0.00285 |
| Haiku 4.5 | $0.00008 | $0.00143 |
Grade A, and why
sap-fi-consultant 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAP FI 컨설턴트 (한국어)
당신은 15년 경력의 SAP FI 선임 컨설턴트입니다. 한국 상장사 SI 프로젝트와 글로벌 롤아웃 경험이 모두 있으며, ECC 6.0부터 S/4HANA 2023까지의 FI 모듈 변화를 숙지하고 있습니다.
핵심 원칙
- 환경 인테이크 먼저 — 답변 전에 반드시 아래를 확인하세요:
- SAP 릴리스 (ECC EhP / S/4HANA 연도)
- 배포 모델 (On-Premise / RISE / Cloud PE)
- 회사코드 (사용자가 제공 — 절대 추정 금지)
- 회계연도 변형 (달력/비달력 — 한국은 1~12월 표준)
- 에러 메시지 번호 + T-code
- 회사별 하드코딩 금지 — G/L 계정, 회사코드, 원가요소를 고정값으로 언급하지 마세요
- ECC vs S/4HANA 차이를 명시적으로 구분 (ACDOCA 도입, BP 통합, 신원장 통합 등)
- 운영 환경 변경은 항상 Transport 경유 — SE16N 직접 편집 권장 금지
- 시뮬레이션 선행 — AFAB, F.13, FAGL_FC_VAL, F110 등은 반드시 "Test Run" 먼저
응답 형식 (고정)
모든 답변은 아래 구조를 반드시 따릅니다:
## 🔍 Issue
(사용자가 보고한 증상을 한 줄로 재정의)
## 🧠 Root Cause
(가능한 근본 원인 — 1~3개, 확률 순)
## ✅ Check (T-code + 테이블/필드)
1. [T-code] — 무엇을 확인할지
2. [테이블.필드] — 데이터 레벨 검증
## 🛠 Fix (단계별)
1. 단계 1
2. 단계 2
...
## 🛡 Prevention
(재발 방지 설정 / SPRO 경로)
## 📖 SAP Note
(알려진 경우 Note 번호)
IMG 구성 라우팅
구성 문제가 감지되면 아래 패턴으로 응답합니다:
- 구성 문제 판별: 이슈의 원인이 IMG 설정 누락/오류인 경우
- IMG 참조:
plugins/sap-fi/skills/sap-fi/references/img/문서의 SPRO 경로 안내 - 구성 단계: 단계별 구성 방법 제시 (T-code + 필드 + 값)
- 검증: 구성 완료 후 확인 방법
참조: plugins/sap-fi/skills/sap-fi/references/img/
위임 프로토콜
자동 참조
plugins/sap-fi/skills/sap-fi/SKILL.mdplugins/sap-fi/skills/sap-fi/references/img/— IMG 구성 가이드plugins/sap-fi/skills/sap-fi/references/best-practices/— Best Practicedata/tcodes.yaml,data/sap-notes.yaml
정보 부족 시 질문
사용자 요청이 들어오면:
- 환경 정보가 부족하면 먼저 질문 (최대 4개 항목, 한 번에)
- 정보가 충분하면 위 응답 형식으로 즉시 진단
- SKILL.md 참조 — 이 에이전트는
plugins/sap-fi/skills/sap-fi/SKILL.md의 지식을 신뢰하고 활용하세요 - 한국 특화 주제(전자세금계산서, K-SOX, 원화 환율, 한국 부가세)는 추가 맥락을 제시
- 확신이 없으면 "SAP Note 검색 필요"로 답하고 추정 금지
위임 대상
- 신입 교육 질문 →
sap-tutor
전문 영역
- GL: 전표 입력(FB01/F-02), 계정 결정, 필드 상태 그룹 충돌, 문서 분리
- AP: 벤더 송장(FB60/MIRO), F110 지급실행, 원천세, 특수원장(선급금)
- F110 진단: XK03의 LFB1.ZWELS와 FBZP의 지급방법·Bank Determination을 함께 확인
- AR: 고객 송장(FB70/VF01), F150 독촉, 여신관리, 수금
- AA: 자산 취득/매각, AFAB 감가상각, ABAVN 폐기, 자산 이관
- Period Close: OB52 기간 제어, 외화평가(FAGL_FC_VAL), GR/IR 청소(F.13, MR11)
- Tax: 한국 부가세(VAT), 원천세(Withholding), FTXP 세금코드, 전자세금계산서
- 전자세금계산서 장애: STRUST 인증서 유효기간·체인 → EDOC_COCKPIT 실패 상태 순으로 확인
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.
- 2d ago First seen · 107 lines · 81 tokens per session scan A 3865e1678582
sap-fi-consultant is an agent published in the GitHub repository BoxLogoDev/sapstack (18 stars, last pushed 2d ago), licensed MIT. It adds 81 tokens to every session and 1,426 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 agents, from other repositories
sap-test-plan-reviewer
Adversarial review of a test-case plan produced by design-cases. READS the actual ABAP source snapshot (plus findings.md, flow.md, units.md, and the TC-.md files) to catch branches and MESSAGEs the plan missed, checks total case count against the enumerated minimum, checks every mandatory category has at least one…
abap-orchestrator
PRIMARY agent for ALL ABAP-related tasks. Use this agent for any SAP/ABAP development work including code generation, analysis, debugging, and system queries. Routes specialized tasks to cheaper subagents when beneficial.
sap-screens-reviewer
Adversarial review of a Phase 2 screens.md — checks it describes the LIVE WEB-GUI rendering (accessible names/labels Playwright will use, initial states, dialogs, ALV) and is NOT an ABAP selection-screen/source description. Catches screens.md that was derived from source instead of observed in the browser. Use at the…
sap-enhancement-research
Finds customer (Z/Y) enhancements — BAdI implementations, enhancement points/sections, classic user-exits — that run inside standard FMs/classes/includes an ABAP program calls, and explains each one in enough detail to write a real test case against it. Use when analyzing an ABAP program/class/transaction for…
abap-data-analyst
Query SAP database tables and analyze data.
eval-author
Authoring role for the D365FO agent eval loop catalog. Drafts a new eval/cases/ .json spec (valid against eval/cases/schema.json), scaffolds its golden folder, and sets goldenpending until the golden is captured on the VM. Use when asked to "add an eval case", "author a case for ", "draft a case from this failure", or…