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 skills add BoxLogoDev/sapstack --skill sap-sacgit 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/skills/boxlogodev/sapstack/sap-sac)<a href="https://agentmods.dev/skills/boxlogodev/sapstack/sap-sac"><img src="https://agentmods.dev/badge/skills/boxlogodev/sapstack/sap-sac/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/skills/boxlogodev/sapstack/sap-sac"><img src="https://agentmods.dev/badge/skills/boxlogodev/sapstack/sap-sac.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 750 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00133 | $0.11268 |
| Opus 5.5 | $0.00053 | $0.04507 |
| Sonnet 5.5 | $0.00027 | $0.02254 |
| Haiku 4.5 | $0.00013 | $0.01127 |
Grade A, and why
sap-sac 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 — 757 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sap-sac — SAP Analytics Cloud
1. Environment Intake Checklist
- SAC tenant region — eu10 / us10 / kr-canary 등?
- Edition — SAC for BI / Planning / Smart Predict / Augmented Analytics?
- Connection type — Live (HANA, BW, S/4) vs. Import (Datasphere, Files)?
- Underlying data source — S/4HANA Cloud / On-Premise / BW / Datasphere / non-SAP?
- Use case — BI Story, Analytic App, Planning, Predictive scenario?
- User role — Story creator, Modeler, Planning user, Admin?
- SAP release — ECC 6.0 EhP 또는 S/4HANA release year?
- Deployment — On-Premise / RISE Private Cloud / Public Cloud?
- Industry — 제조·유통·금융·공공 등 데이터 통제와 마감 패턴은 무엇인가?
- Failure scope — 전체/특정 사용자, 최초 시각, 재현 빈도, 정확한 에러 문구?
- Authentication path — SAML SSO / OAuth / basic / identity propagation 중 무엇인가?
- Change history — 인증서·metadata·proxy·role·model 변경 직후인가?
환경이 부족해도 답을 멈추지 않는다. 위 질문을 최대 4개로 묶어 요청하고, 동시에 운영 변경 없는 provisional diagnosis와 read-only check를 제시한다.
2. Core Concepts
2.1 Connection Models
- Live Connection — real-time query, no data copy. HANA, BW, S/4 CDS views.
- Import Connection — periodic data load. Files, Datasphere, non-SAP DBs.
2.2 Models
- Analytic Model — flexible, dimension/measure-based, for BI Story
- Planning Model — supports input, version, allocation, value driver
- Predictive Model — Smart Predict / Augmented (regression, classification, time series)
2.3 Stories vs. Analytic Applications
- Story — drag-drop dashboards, smart insight, easy for business users
- Analytic Application — scriptable (JS), customizable UI, for app developers
3. Typical Issues
Data Issues
- "Story is empty" — check connection, model permissions, member filter
- "Numbers don't match S/4" — live vs. import mismatch, currency/unit conversion
- "Hierarchy missing" — refresh hierarchy in connection, check role mapping
- "Live connection failed" — SAC connection → network/auth → S/4
SICF→SAML2순서
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/best-practices/governance.md 1.8 KB
- references/best-practices/operational.md 1.4 KB
- references/best-practices/period-end.md 1.5 KB
- references/de/quick-guide-de.md 2.8 KB
- references/en/quick-guide-en.md 2.7 KB
- references/img/connection-setup.md 2.1 KB
- references/img/model-story-governance.md 1.9 KB
- references/img/overview.md 1.2 KB
- references/img/planning-data-locking.md 2.0 KB
- references/ja/quick-guide-ja.md 3.0 KB
- references/ko/quick-guide.md 2.7 KB
- references/vi/quick-guide-vi.md 3.1 KB
- references/zh/quick-guide-zh.md 2.5 KB
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 · 757 lines · 133 tokens per session scan A d10831d12bbc
sap-sac is a skill published in the GitHub repository BoxLogoDev/sapstack (20 stars, last pushed 19d ago), licensed MIT. It adds 133 tokens to every session and 11,268 once invoked, about $0.0005 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 2026-09-04.
Other skills, from other repositories
sap-expert
Expert in SAP ERP systems, ABAP programming, SAP HANA, S/4HANA, Fiori applications, and SAP integration patterns including OData, RFC, and IDoc. Use when the user mentions ERP, enterprise, business apps, ABAP, HANA, or S/4HANA, or when the task involves SAP Ecosystem, ABAP Development, Integration Technologies, or…
sap-customizing
Navigate and understand SAP Customizing (SPRO/IMG). Use when the user asks about customizing settings, SPRO activities, configuration tables, maintenance views, view clusters, or needs to read/understand any customizing data. This skill teaches how to systematically trace from an SPRO activity to the actual tables…
sap-system-personality-report
Generate a comprehensive SAP System Personality Report. Analyzes custom code landscape, functional footprint, development activity, health metrics, and package breakdown. Use when a user asks to characterize a system, understand a system, get a system overview, system report, system personality, or "what does this…
abap-research
Techniques for navigating and finding objects in SAP systems. Use when searching for transactions, programs, FMs, classes, error messages, BAPIs, tables, custom objects, or anything in an unfamiliar SAP system. Teaches the mindset and metadata knowledge a senior ABAP developer uses to find anything in any system. Load…
connect-tool
Use when the user names a specific tool to connect to the agent (an ERP, accounting or desktop program, CRM, WhatsApp, a spreadsheet, a database): research its real docs, choose the safest route, build 01-TOOLS/ / with a test that proves it, and guide the user. NOT a full typed API client (that is…
light-data-engineering
A research data-checking guide for finding, evaluating, preparing, and splitting datasets. It explains whether data can support a study and checks for data leakage, where information accidentally crosses from training data into test data.