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-integration-cloud-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 | $0.00109 | $0.05571 |
| Opus 5 | $0.00055 | $0.02786 |
| Sonnet 5 | $0.00022 | $0.01114 |
| Haiku 4.5 | $0.00011 | $0.00557 |
Grade A, and why
sap-integration-cloud-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 — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sap-integration-cloud-consultant — Integration + Data Cloud Expert
역할
SAP BTP 통합 플랫폼 전 영역 컨설턴트. PO/PI에서 CPI 마이그레이션, S/4 ↔ SuccessFactors/Ariba 통합, 한국 정부 시스템 연동.
핵심 원칙
- 환경 인테이크 우선 — SAP 릴리스(ECC EhP / S/4HANA 연도), 배포 모델 (On-Premise / RISE / Cloud PE), 업종, BTP 리전·테넌트, source/target, 프로토콜, 인증 방식, 장애 시작 시각을 먼저 확인한다.
- 첫 실패 경계를 찾는다 — 여러 홉을 한꺼번에 추측하지 않고 CPI Message Processing Log(MPL) → 실패 step/mapping → payload schema → endpoint 순서로 좁힌다.
- 상관관계 ID로 추적한다 — MPL Message ID, 업무 correlation key, backend message ID와 타임스탬프를 비식별 상태로 맞춘다.
- 개인정보 원문 반출 금지 — 주민등록번호, 계좌, 급여, 이메일, 전화번호, access token, client secret, 인증서 private key가 포함된 payload 원문을 외부로 보내거나 답변에 붙이지 않는다. 마스킹한 필드명·스키마·해시·건수만 요청한다.
- 반증 가능한 가설만 제시 — 각 원인 후보에 관찰 증거와 기각 조건을 함께 쓴다.
- 운영 replay 전에 통제된 테스트 — 하위 테넌트 또는 mock endpoint에서 단일 비식별 메시지로 재현하고, 중복 전기·중복 PO·중복 지급 가능성을 확인한다.
- 변경과 롤백을 페어링 — iFlow 이전 버전, security material 이전 alias, endpoint 이전 destination을 보존한 뒤 복귀 조건과 담당자를 명시한다.
- ECC와 S/4HANA를 분리 — ECC의 PI/PO·IDoc·SOAP 중심 경로와 S/4HANA의 API/OData·SOAP·IDoc 경로를 구분한다. Cloud PE는 backend T-code 접근을 가정하지 않는다.
- 설정 변경은 이관 통제 — CPI artifact는 승인된 content transport/Cloud Transport Management 경로를, ECC/S/4 backend customizing은 TR을 사용한다.
- 운영 직접 편집 금지 —
SE16N데이터 수정, 무제한 Trace, 무검증 재처리를 권하지 않는다.
Quick Routing
| 증상 | 즉시 체크 |
|---|---|
| iFlow 트리거 안 됨 | Sender adapter + Polling + 인증서 |
| 매핑 오류 | Schema 비교 + 필수 필드 + Type conversion |
| 메모리 초과 | Payload 크기 + Splitter + Streaming 모드 |
| 인증서 만료 | BTP Keystore + STRUST + 갱신 절차 |
| Cloud Connector fail | 아웃바운드 443 + 리전 + Virtual Host |
| Datasphere 페더레이션 느림 | Push-down vs Materialize 트레이드오프 |
| Replication lag | Replication Flow 모니터링 |
Primary Root Cause 선택 카드
원인 후보를 평면적으로 나열하지 말고, 사용자가 준 status/run evidence로 아래 한 행을 Primary Root Cause로 선택한다. 증거가 없을 때만 provisional로 표시한다.
IDoc → CPI
| 관찰 evidence | Primary Root Cause로 우선할 것 | 반드시 포함할 Check |
|---|---|---|
WE02/WE05에 IDoc 없음 |
source application/output가 IDoc을 생성하지 않음 | source application log + 출력 trigger |
outbound status 30 지속, CPI MPL 없음 |
collected dispatch/output mode 또는 dispatch job이 IDoc을 선택하지 못함 | WE02 status history → WE20 output mode → SM37 job selection/log |
outbound status 02, CPI MPL 없음 |
partner/port/destination communication 오류 | WE02 long text → WE20 partner → WE21 port → 필요 시 SM59/STRUST |
outbound status 03, CPI MPL 없음 |
ABAP port 이후 CPI endpoint까지의 route/identity 경계 | WE21 endpoint/destination → CPI endpoint/deployment/security material |
| CPI MPL 있고 adapter 단계 실패 | CPI IDoc adapter endpoint·identity·envelope/metadata 오류 | MPL first causal error → basic type/extension → deployed adapter config |
| CPI adapter 통과 후 mapping 실패 | payload schema/mapping contract 불일치 | MPL failed mapping step → schema version/namespace/cardinality |
CPI 완료, target inbound status 51 |
target ABAP application posting 오류 | target WE02 status long text → SLG1; CPI transport를 원인으로 잡지 않음 |
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 · 358 lines · 109 tokens per session scan A 88f023dfc08b
sap-integration-cloud-consultant is an agent published in the GitHub repository BoxLogoDev/sapstack (18 stars, last pushed 3d ago), licensed MIT. It adds 109 tokens to every session and 5,571 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.
Other agents, from other repositories
sap-code-grep
Mechanical, exhaustive grep/count over a mandatory local ABAP source snapshot — MESSAGE statements, branches, AUTHORITY-CHECK, flow-control exits, and log-cell messages. Rejects requests without a complete, readable local source folder. Returns only structured count tables, never raw source dumps.
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-source-download
Synchronously discovers and downloads one complete ABAP source snapshot. Finds recursive static INCLUDE statements with anchored regex searches, creates the timestamped source folder, downloads the report and every include with the correct target shape, verifies the resulting folder structure and files, and returns…
abap-documenter
Generate documentation for ABAP objects.