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-sdgit 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-sd)<a href="https://agentmods.dev/skills/boxlogodev/sapstack/sap-sd"><img src="https://agentmods.dev/badge/skills/boxlogodev/sapstack/sap-sd.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high System Prompt Leakage · line 223 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 | $0.00114 | $0.05764 |
| Opus 5 | $0.00057 | $0.02882 |
| Sonnet 5 | $0.00023 | $0.01153 |
| Haiku 4.5 | $0.00011 | $0.00576 |
Grade A, and why
sap-sd 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 — 519 lines — stays where its author put it; the contents beside it link to each section on GitHub.
1. Order-to-Cash Flow
Inquiry (VA11) → Quotation (VA21) → Sales Order (VA01)
→ Outbound Delivery (VL01N) → Picking (warehouse solution에 따라 VL02N/WM/EWM)
→ Post Goods Issue / PGI (VL02N) → Billing (VF01)
→ FI Document created → Customer Payment
2. Sales Order Issues
Pricing errors
- Condition records: VK11 (create) / VK12 (change) → access sequence → condition table
- Pricing procedure determination: OVKK → sales area + doc pricing procedure + customer pricing procedure
- Manual price change: VA02 → Conditions tab → manual entry (if field status allows)
- Pricing analysis: VA02 → Conditions → Analysis (shows why each condition applied / not applied)
Availability check
- CO09: availability overview per material / plant / checking rule
- Checking rule: OVZ9 → scope of check (purchase orders / production orders / safety stock)
- Partial delivery: schedule line category → delivery block vs partial confirmation
Credit check
- ECC: FD32 → credit limit per credit control area → exposure = open orders + deliveries + billing + FI
- S/4HANA FSCM: UKM_BP → credit segment → scoring + limit → automatic rule-based check
- Release worklist은 ECC credit-management 구성에 따라
VKM1/VKM3범위를 확인하고, S/4HANA FSCM에서는 사용 중인 released app/workflow를 확인한다.
Output (forms / messages)
- NACE → output type → condition records → access sequence
- Output not triggering: check condition record exists for correct sales org / doc type / partner
Incompletion log
- V.02 → list incomplete sales orders
- Incompletion procedure: OVAU → mandatory fields per item category / schedule line category
3. Delivery and Goods Issue
Delivery creation
VL01N: 단일 reference로 manual delivery 생성. Collective delivery는VL10A/VL10B등 실제 due-list 시나리오를 사용한다.VF04는 delivery 생성이 아니라 billing due list다.- Delivery split: copy control VTLA → split criteria (shipping point / route / delivery date)
- Collective delivery: VL10A (from sales orders) / VL10B (from purchase orders)
What ships with it
15 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 7.0 KB
- references/best-practices/operational.md 5.6 KB
- references/best-practices/period-end.md 6.4 KB
- references/de/quick-guide-de.md 1.4 KB
- references/en/quick-guide-en.md 1.3 KB
- references/img/account-determination-sd.md 11 KB
- references/img/copy-control.md 13 KB
- references/img/credit-management.md 14 KB
- references/img/overview.md 6.3 KB
- references/img/pricing-procedure.md 14 KB
- references/ja/quick-guide-ja.md 1.4 KB
- references/ko/quick-guide.md 1.3 KB
- references/ko/SKILL-ko.md 4.0 KB
- references/vi/quick-guide-vi.md 1.6 KB
- references/zh/quick-guide-zh.md 1.2 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.
- 4d ago First seen · 519 lines · 114 tokens per session scan A 4d486c0ee1cd
sap-sd is a skill published in the GitHub repository BoxLogoDev/sapstack (18 stars, last pushed 8d ago), licensed MIT. It adds 114 tokens to every session and 5,764 once invoked, about $0.0006 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 2026-09-04.
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-sac-planning
SAP Analytics Cloud (SAC) planning guidance for planning models, planning-enabled stories, data actions, multi actions, version management, data locking, calendar/input workflows, allocations, value driver trees, BPC live planning, and Seamless Planning with SAP Datasphere. Use this for planning design, planning APIs…
sap-sac-custom-widget
SAP Analytics Cloud (SAC) Custom Widget development. Use when building custom visualizations, extending SAC with Web Components, or creating Widget Add-Ons. Covers JSON metadata, JavaScript Web Components, lifecycle functions, data binding with feeds, styling/builder panels, property/event/method definitions…
dependency-upgrade
Secure dependency upgrades with supply chain protection, cooldowns, and staged rollout. Use when upgrading deps, configuring security policies, or preventing supply chain attacks.
sap-dependency-security
SAP dependency security and MCP executable trust policy with secure upgrades, cooldowns, staged rollout, and supply-chain protection. Use when upgrading deps, configuring security policies, preventing supply chain attacks, pinning SAP MCP servers, or reviewing SAP CAP/UI5/Fiori/HANA/Datasphere/SAC/BTP/ABAP dependency…
sap-abap-cds
Comprehensive SAP ABAP CDS (Core Data Services) reference for data modeling, view development, and semantic enrichment. Use when creating CDS views or view entities, defining data models with annotations, working with associations and cardinality, implementing input parameters, using built-in functions, writing CASE…