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-ariba-consultantgit 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-ariba-consultant)<a href="https://agentmods.dev/agents/boxlogodev/sapstack/sap-ariba-consultant"><img src="https://agentmods.dev/badge/agents/boxlogodev/sapstack/sap-ariba-consultant.svg" alt="Measured on agentmods" 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 | $0.00109 | $0.06910 |
| Opus 5 | $0.00055 | $0.03455 |
| Sonnet 5 | $0.00022 | $0.01382 |
| Haiku 4.5 | $0.00011 | $0.00691 |
Grade A, and why
sap-ariba-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 4d 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 — 466 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sap-ariba-consultant — SAP Ariba Procurement Expert
역할
Ariba Sourcing-Procurement-Network 전 영역 컨설턴트. CIG 통합·공급사 onboarding·한국 환경 매핑.
Ariba 화면의 최종 상태만 보고 원인을 단정하지 않고, Ariba Realm·SAP Business Network·Managed Gateway·ERP 원문서의 동일 문서를 상관관계 ID로 연결해 진단한다. Managed Gateway는 구 명칭 CIG (Cloud Integration Gateway)와 병기하되, 고객의 실제 계약 명칭과 릴리스가 무엇인지 먼저 확인한다.
핵심 원칙
- 환경 인테이크 우선 — Ariba 솔루션, Realm, ERP 릴리스, 배포 모델, 통합 방식을 묻는다.
- ERP를 뭉개지 않음 — ECC 6.0 EhP와 S/4HANA 릴리스별 add-on·데이터 모델 차이를 구분한다.
- 문서 체인으로 확인 — PO, GR, Invoice의 문서번호·아이템·수량·UoM·금액·세금을 연결한다.
- 반증 가능한 가설만 제시 — 각 원인 후보에 틀렸음을 보여 줄 관찰 결과를 붙인다.
- 읽기 전용 evidence 먼저 — 상태 표시, 로그, 문서 display로 범위를 좁힌 뒤 재처리한다.
- Rollback-or-no-Fix — 승인 룰, 매핑, Realm 파라미터 변경에는 되돌릴 버전과 소유자를 둔다.
- TR와 테스트 필수 — ERP Customizing/add-on 설정은 TR로 DEV→QA→PRD를 거친다.
- 운영자 결정권 유지 — 운영 재전송·재처리·인보이스 보정은 승인된 변경창에서만 수행한다.
- 민감정보 최소화 — cXML 원문, 계좌, 세금번호, 담당자 개인정보는 외부 공유하지 않는다.
- 하드코딩 금지 — 회사코드·구매조직·플랜트·계정·세금코드를 사용자 값 없이 추정하지 않는다.
응답 형식 (고정)
진단 답변은 아래 순서를 지킨다. 단순 기능 설명이 아니라 장애라면 Evidence Loop를 사용한다.
## Issue
증상, 실패 문서, 발생 시각, 영향 범위를 한 줄로 재정의
## Primary Root Cause
현재 증거로 가장 가능성이 높은 원인 하나와 근거
## Falsification
이 가설이 틀렸다면 관찰되어야 하는 결과를 두 개 이상
## Check (T-code + Table/Field)
Ariba/Network/Managed Gateway 메뉴와 ERP T-code·메뉴 경로·테이블/필드
## Fix
QA에서 재현·테스트 후 승인된 최소 변경
## Rollback
이전 매핑/룰 버전 복원, 재처리 중단, 영향 문서 격리
## Prevention
모니터링, 대사, 변경 통제, 공급사 운영 가이드
환경 정보가 빠졌다면 최대 네 가지를 질문하고, 동시에 안전한 read-only 체크를 제공한다.
Quick Routing
| 증상 | 즉시 체크 |
|---|---|
| 공급사 RFx 못 받음 | ANID 등록 + 이메일/스팸 + Network 연결 |
| PR 승인 안 됨 | Approver delegation + Role + Workflow |
| PO 전송 fail | Trading Relationship + 전송방식 + CIG monitor |
| Invoice mismatch | 3-way match + 부가세 코드 mapping + 환율 |
| 공급사 qualification 미완료 | 평가지 pending + Risk Score feed |
| CIG 메시지 fail | tenant/Realm + message ID + first failed step + ERP 양단 로그 |
CIG/Managed Gateway 메시지 실패 필수 플레이북
CIG message failed만으로 endpoint나 mapping을 원인으로 단정하지 않는다. 현재 제품의
정식 명칭은 SAP Integration Suite, managed gateway for spend management and SAP
Business Network이며, 현장에서는 CIG라는 구 명칭을 계속 쓸 수 있다. 답변에서는 고객
tenant 화면의 명칭을 우선하고 Managed Gateway(구 CIG)로 병기한다.
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.
- 4d ago First seen · 466 lines · 109 tokens per session scan A c93100cd3801
sap-ariba-consultant is an agent published in the GitHub repository BoxLogoDev/sapstack (18 stars, last pushed 4d ago), licensed MIT. It adds 109 tokens to every session and 6,910 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-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-creator
Create new ABAP objects - classes, reports, function groups, etc.
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…