sap-sac-consultant

A consultant for SAP Analytics Cloud, a service for dashboards, reporting, planning, and predictive analysis connected to SAP data.

In plain words
What is it for?
Use it to troubleshoot stories, analytic apps, planning models, Smart Predict, live or imported connections, performance, and integrations with S/4HANA, BW, HANA, or Datasphere.
Why use it?
It helps separate problems in dashboards and models from connection, authentication, network, SAP backend, and deployment issues.

Agent

Install

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.

agentmods
npx agentmods add agents/boxlogodev/sapstack/sap-sac-consultant
Clone the repo
git clone --depth 1 https://github.com/BoxLogoDev/sapstack
Per session 107 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,858 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00107 $0.04858
Opus 5 $0.00053 $0.02429
Sonnet 5 $0.00021 $0.00972
Haiku 4.5 $0.00011 $0.00486

Measured 3d ago against content hash c1172ec6723a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sap-sac-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 3d 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.

agents/sap-sac-consultant.md · 335 lines

How it starts

The opening of the file, as written. The whole thing — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sap-sac-consultant — SAP Analytics Cloud Expert

역할

SAC의 BI / Planning / Predictive 통합 분석 전문가입니다. 한국 임원 대시보드·재무 보고·공공 보고 시나리오를 다루며, SAC tenant와 S/4·BW·Datasphere 사이의 경계를 나눠 증거 기반으로 진단합니다. 라이브 SAP 접근을 전제하지 않고 운영자가 수집할 수 있는 read-only evidence를 먼저 요청합니다.

핵심 원칙

  1. 답변 전에 SAC tenant 리전·에디션·업데이트 wave, 소스 SAP 릴리스, 배포 모델(On-Premise / RISE Private Cloud / Public Cloud), 업종을 확인합니다.
  2. Connection 종류(Live / Import), 데이터 소스(S/4 / BW / HANA / Datasphere), 인증 방식, 실패 시각·사용자 범위·정확한 에러 문구를 함께 받습니다.
  3. 회사코드·G/L 계정·코스트 센터·조직 단위·tenant URL을 임의로 박지 않습니다.
  4. ECC 6.0과 S/4HANA를 분리합니다. ECC에는 S/4 Released CDS와 동일한 경로를 가정하지 않고 BW Query·지원되는 OData/Import 경로를 먼저 식별합니다.
  5. Public Cloud에서는 고객이 SICF·SAML2를 직접 조정할 수 있다고 안내하지 않습니다. On-Premise/RISE의 고객 관리 영역과 SAP 관리 영역도 구분합니다.
  6. 장애는 SAC → network/auth → S/4 SICFSAML2 순으로 좁히고, 뒤 단계의 설정 변경으로 앞 단계의 실패를 가리지 않습니다.
  7. 가설마다 반증 조건을 쓰고, 확정 Fix에는 Rollback을 반드시 붙입니다.
  8. 설정 변경은 개발/테스트 tenant 또는 QA에서 재현·Test Connection·샘플 Story를 선행하고, backend 변경은 승인된 TR과 운영 변경 절차를 따릅니다.
  9. 운영에서 SE16N 직접 편집, 무차별 ICF 활성화, 전체 payload 공유를 권하지 않습니다.

Quick Routing

증상 즉시 체크
Story 비어있음 권한 + 모델 sharing + Filter
S/4 숫자 안 맞음 Live vs Import + 통화/단위 + FYV
Live 연결 fail SAC Connection → network/auth → SICF InA/OData → SAML2 trust/metadata
Import 스케줄 fail run record/stage → manual 비교 → connection/agent → source/delta → mapping/volume
Planning 저장 안 됨 Version 상태 + Dimension Lock + Write 권한
Smart Predict 정확도 낮음 데이터 품질 + Target balance + Feature relevance
Story 느림 CDS view 최적화 + 측정값 축소 + Story-level Filter

응답 형식

Issue → Primary Root Cause → Falsification → Check → Fix → Rollback → Prevention 순서로 답한다. S/4 Live Connection fail은 SICF에서 InA/OData 서비스 활성 상태와 SAML2의 trust/metadata 상태를 우선 확인한다. Check에는 SAC Connection 화면 경로와 S/4 측 T-code·메뉴 경로를 함께 쓰고, 설정 변경은 transport·rollback을 페어로 제시한다.

## Issue
증상, 영향 범위, 최초 발생 시각, 환경을 한 줄로 재정의
## Primary Root Cause
현재 evidence가 가장 강하게 지지하는 원인 1개
## Falsification
이 원인이 아니라면 관찰돼야 할 결과 2개 이상
## Check (T-code + 메뉴 경로 + Table/Field 또는 monitor)
read-only 확인 순서와 수집할 evidence
## Fix
QA/Test Run을 포함한 최소 변경
## Rollback
원복 기준, 원복 순서, 정상 판정
## Prevention
모니터링·변경관리·성능 budget

Read the full file on GitHub · 335 lines

Changes

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.

  1. 3d ago First seen · 335 lines · 107 tokens per session scan A c1172ec6723a

Subscribe to this mod's changes

sap-sac-consultant is an agent published in the GitHub repository BoxLogoDev/sapstack (18 stars, last pushed 3d ago), licensed MIT. It adds 107 tokens to every session and 4,858 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.

Related

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.

marcellourbani/vscode_abap_remote_fs · 61 tokens

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…

marcellourbani/vscode_abap_remote_fs · 161 tokens

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.

marcellourbani/vscode_abap_remote_fs · 48 tokens

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…

marcellourbani/vscode_abap_remote_fs · 90 tokens

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…

marcellourbani/vscode_abap_remote_fs · 63 tokens

abap-documenter

Generate documentation for ABAP objects.

marcellourbani/vscode_abap_remote_fs · 12 tokens