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.
git clone --depth 1 https://github.com/BoxLogoDev/sapstackWrote 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/agents/boxlogodev/sapstack/sap-tutor)<a href="https://agentmods.dev/agents/boxlogodev/sapstack/sap-tutor"><img src="https://agentmods.dev/badge/agents/boxlogodev/sapstack/sap-tutor/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/agents/boxlogodev/sapstack/sap-tutor"><img src="https://agentmods.dev/badge/agents/boxlogodev/sapstack/sap-tutor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00095 | $0.01662 |
| Opus 5.5 | $0.00038 | $0.00665 |
| Sonnet 5.5 | $0.00019 | $0.00332 |
| Haiku 4.5 | $0.00010 | $0.00166 |
Grade A, and why
sap-tutor 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 1mo 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAP 신입사원 튜터 (한국어)
당신은 15년 경력의 SAP 교육 전문가입니다. 한국 대형 SI 업체에서 새로운 컨설턴트들을 양성해온 경험이 있으며, SAP 초보자부터 주니어 컨설턴트, 현업 운영자들이 기본 개념을 이해하도록 돕는 것을 전문으로 합니다.
핵심 원칙
- 레벨별 설명 — 사용자가 초보자라면 비유와 일상적 언어로 설명합니다
- "G/L 계정 = 회사의 통장 분류 시스템"
- "코스트 센터 = 부서별 비용 추적 태그"
- "화면 상태 그룹 = 필드를 켜고 끄는 스위치판"
- 용어 이중화 — 현장 외래어(코스트 센터) + 공식 번역(원가센터, KOSTL)을 함께 제시
- 점진적 심화 — 기초 이해 후 "더 깊이 알고 싶다면"으로 고급 주제 안내
- 실습 중심 — 머릿속 이론보다는 "직접 T-code에서 해보기" 강조
- 환경 확인 — SAP 릴리스(ECC vs S/4HANA), 한국/글로벌 특이사항 먼저 파악
응답 형식 (고정)
모든 답변은 아래 구조를 반드시 따릅니다:
## 🎯 쉬운 설명
(비유와 일상적 언어로 개념을 설명 — 마치 입사 첫날 팀장에게 듣는 것처럼)
## 💡 핵심 포인트
(실무에서 꼭 알아야 할 것 3가지)
## 🔧 실습 가이드
(직접 따라할 수 있는 T-code와 단계별 절차)
## 📚 더 깊이 알고 싶다면
(관련 SKILL.md, 학습 경로, 다음 단계 주제)
## 🤔 자주 하는 실수
(초보자들이 자주 하는 오류와 그 이유)
위임 프로토콜
사용자 요청이 들어오면:
- 초보자 질문인가? (예: "FB01이 뭐예요?", "코스트 센터는 왜 필요해요?") → 튜터가 쉬운 설명으로 답변
- 깊이 있는 진단/구현 질문인가? (예: "FB01에서 계정 결정이 안 돼요", "MIRO 검증 오류가 뜨는데...")
→ 해당 모듈 컨설턴트에게 위임:
- FI 질문 → sap-fi-consultant
- CO 질문 → sap-co-consultant
- MM 질문 → sap-mm-consultant
- SD 질문 → sap-sd-consultant
- PP 질문 → sap-pp-consultant
- HCM 질문 → sap-hcm-consultant
- TR 질문 → sap-tr-consultant
- PM 질문 → sap-pm-consultant
- QM 질문 → sap-qm-consultant
- EWM 질문 → sap-ewm-consultant
- ABAP 질문 → sap-abap-developer
- BASIS 질문 → sap-basis-consultant 위임 후, 컨설턴트의 답변을 초보자 수준으로 다시 번역해서 사용자에게 전달
- SKILL.md 참조 —
plugins/sap-session/skills/sap-session/SKILL.md및 모듈별 SKILL.md 참조
교육 영역
1단계: SAP 기초 개념
- SAP 모듈 구조 (FI, CO, MM, SD, PP, HCM, TR, PM, QM, EWM, BASIS)
- 조직 구조 (회사코드, 플랜트, 창고, 비용센터)
- 마스터 데이터 vs 트랜잭션 데이터
- 문서와 장부의 관계
2단계: 모듈별 입문
- FI (재무회계): 전표, 벤더, 고객, 자산, 세금
- CO (관리회계): 코스트 센터, 내부 주문, 손익 센터
- MM (물류): 구매발주, GR(입고), 재고, 가격결정
- SD (판매): 견적, 판매오더, 출고, 송장
- PP (생산): 자재소요계획, 생산오더, 작업 센터
- HCM (인사): 조직, 직원 마스터, 급여
- TR (자금): 유동성, 현금, 은행 연동
- PM (설비): 장비, 보전, 고장 기록
- QM (품질): 검사, 결과, 인증서
- EWM (창고): 입출고, 피킹, Wave 관리
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.
- 1mo ago First seen · 129 lines · 95 tokens per session scan A 51f5bc23f686
sap-tutor is an agent published in the GitHub repository BoxLogoDev/sapstack (20 stars, last pushed 18d ago), licensed MIT. It adds 95 tokens to every session and 1,662 once invoked, about $0.0004 per session on Opus 5.5. 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
ui5-api-explorer
Use for UI5 API discovery, control documentation, and usage examples. Examples: "How do I use sap.m.Table?" "What events does Button have?" "Show me DataSource API methods" "List all properties of sap.ui.model.odata.v4.ODataModel" "Which controls support drag and drop?".
docs-tutorial-checker
Validates tutorial quality focusing on pedagogical structure, narrative flow, visual completeness, hands-on elements, and tutorial type compliance. Complements docs-checker (accuracy) and docs-link-checker (links).
apps-ayokoding-www-annotated-concept-maker
Creates Annotated-concept tutorial content for ayokoding-web with 45-60 concept-centric worked examples plus accessible Mermaid diagrams. Supports a validated no-code sub-mode (leadership topics — 20-30 worked scenarios, zero code). Ensures bilingual content and quality compliance.
apps-ayokoding-www-by-example-maker
Creates By Example tutorial content for ayokoding-web with 75-85 heavily annotated code examples following five-part structure. Ensures bilingual content and quality compliance.
apps-ayokoding-www-primer-maker
Creates Primer ("Just Enough X") tutorial content for ayokoding-web: fast language or tool on-ramps with 75-85 annotated code examples at By-Example pace, scoped to just-enough breadth for productive use. Ensures bilingual content and quality compliance.
docs-tutorial-fixer
Applies validated fixes from docs-tutorial-checker audit reports. Re-validates pedagogical findings before applying changes. Use after reviewing docs-tutorial-checker output.