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-wmgit 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-wm)<a href="https://agentmods.dev/skills/boxlogodev/sapstack/sap-wm"><img src="https://agentmods.dev/badge/skills/boxlogodev/sapstack/sap-wm/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-wm"><img src="https://agentmods.dev/badge/skills/boxlogodev/sapstack/sap-wm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00202 | $0.03394 |
| Opus 5.5 | $0.00081 | $0.01358 |
| Sonnet 5.5 | $0.00040 | $0.00679 |
| Haiku 4.5 | $0.00020 | $0.00339 |
Grade A, and why
sap-wm 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 2mo 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 — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.
1. Environment Intake (Critical)
ECC vs S/4HANA Alert: WM is DEPRECATED in S/4HANA (all releases).
- S/4HANA on-premise / RISE: Use embedded EWM (
sap-ewmskill) or Stock Room Management - ECC 6.0: WM fully supported through extended maintenance (2025)
- Dual-run transition: ECC WM → S/4HANA EWM requires process redesign (not 1:1 mapping)
Questions to ask user:
- ECC 6.0 (which EhP?) or S/4HANA already?
- Warehouse network: single, multi, or 3PL outsourced?
- RF terminal / barcode capability active?
- Current issue: process bottleneck, data accuracy, integration, or migration planning?
2. Warehouse Structure (LS01N / LS03N / LQUA)
Hierarchy & Tables
| Level | T-code | Definition | Table |
|---|---|---|---|
| Warehouse | LS01N | Top container, assigned to plants | LAGP |
| Storage Type | LS01 | Physical zone (rack, yard, high-bay, flow) | LTYP |
| Storage Section | LS03N | Sub-zone (aisle, row) | LEIN |
| Storage Bin | LS03N | Individual slot (address: WH-ST-SEC-BIN) | LQUA |
Warehouse Master (LAGP) Key Fields
- LGNUM: Warehouse number (2 chars, e.g., "01")
- LGSYS: Flag —
W(WM system) orD(Decentralized) - WERKS: Plant assignment
- LGPLA format: 3-digit ST + 3-digit section + 3-digit bin (e.g., "001001001")
Issue: "Cannot create storage bins"
Root Cause: Missing storage section linking Check: SE16N → LEIN (verify section exists); SE16N → LQUA (verify bins) Fix: LS03N → Create Section → Create Bins (batch entry) → Trigger MRP
3. Transfer Order (LT01 / LT03 / LT0E / LT06)
Key T-codes
| T-code | Function | Field |
|---|---|---|
| LT01 | Create TO manually | LGPLA (from), LGPLB (to) |
| LT03 | Release picking TO | Qty by storage section |
| LT0E | Release putaway TO | Destination bin |
| LT0A | Confirm TO execution | Updates LQUA stock |
| LT0G | RF execution (handheld) | Worker mobile entry |
| LT04 | Cancel TO | Full reversal |
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 9.2 KB
- references/best-practices/operational.md 4.5 KB
- references/best-practices/period-end.md 6.7 KB
- references/de/quick-guide-de.md 4.0 KB
- references/en/quick-guide-en.md 3.7 KB
- references/img/movement-type-and-strategy.md 6.5 KB
- references/img/overview.md 2.4 KB
- references/img/physical-inventory-wm.md 2.1 KB
- references/img/putaway-picking-strategy.md 2.2 KB
- references/img/warehouse-structure.md 4.2 KB
- references/ja/quick-guide-ja.md 4.1 KB
- references/ko/quick-guide.md 5.5 KB
- references/ko/SKILL-ko.md 337 B
- references/vi/quick-guide-vi.md 4.5 KB
- references/zh/quick-guide-zh.md 3.6 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.
- 2mo ago First seen · 362 lines · 202 tokens per session scan A 7996020bd13e
sap-wm is a skill published in the GitHub repository BoxLogoDev/sapstack (20 stars, last pushed 1mo ago), licensed MIT. It adds 202 tokens to every session and 3,394 once invoked, about $0.0008 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.
sap-wm compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sap-wmBoxLogoDev/sapstack | Skill | 20 | 1mo ago | MIT | A | 202 | Claude Code |
| rollinggo-hotel-bookingRollingGo-AI/rollinggo-hotel-skill-cn | Skill | 167 | 24d ago | MIT | A | 209 | Claude Code, Codex |
| hotel-coreRollingGo-AI/rollinggo-hotel-skill-cn | Skill | 167 | 24d ago | MIT | A | 60 | Claude Code, Codex |
| erp-integrationfinsilabs/awesome-ecommerce-skills | Skill | 63 | 15d ago | MIT | A | 32 | Claude Code, Codex |
| sap-expertpersonamanagmentlayer/pcl | Skill | 44 | 12d ago | Apache-2.0 | A | 92 | Claude Code |
| kingdee-queryWaHaiLong/KingdeeMCP | Skill | 137 | 13d ago | MIT | A | 109 | Claude Code, Codex |
| odoo-inventoryactinon-com/brass-monkey | Skill | 2 | 6d ago | MIT | A | 36 | Claude Code |