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 skills/boxlogodev/sapstack/sap-mmnpx skills add BoxLogoDev/sapstack --skill sap-mmgit 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-mm)<a href="https://agentmods.dev/skills/boxlogodev/sapstack/sap-mm"><img src="https://agentmods.dev/badge/skills/boxlogodev/sapstack/sap-mm.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 | $0.00117 | $0.08196 |
| Opus 5 | $0.00059 | $0.04098 |
| Sonnet 5 | $0.00023 | $0.01639 |
| Haiku 4.5 | $0.00012 | $0.00820 |
Grade A, and why
sap-mm 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 yesterday.
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 — 651 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAP Materials Management (MM) Skill
0. Environment Intake and Safety Contract
Before diagnosing or recommending an MM action, collect:
- Release: ECC 6.0 EhP or S/4HANA release year
- Deployment: On-Premise, RISE/Private Cloud, or Public Cloud
- Industry/process: manufacturing, retail, project procurement, services, or regulated industry
- Scope keys: user-provided purchasing organization, plant, storage location, PO, and material
- Evidence: exact message class/number, T-code or Fiori app, timestamp, last normal document
- Control state: posting period, approval status, GR-based IV flag, and whether QM/batch/serial control applies
Never invent company codes, G/L accounts, cost centers, plants, purchasing organizations, or tolerance
values. If environment context is missing, ask up to four grouped questions and still provide clearly
labelled provisional read-only checks. Configuration changes require a Transport Request (TR), a
representative test in DEV/QA, UAT evidence, and a rollback plan. Never edit production tables with
SE16N.
1. Procurement Cycle
PR (ME51N) → RFQ (ME41) → Quotation (ME47) → PO (ME21N)
→ GR (MIGO 101) → IV (MIRO) → Payment (F110)
Shortcut flows:
- Without RFQ: PR → PO (ME58 — auto-convert PR to PO)
- Consignment: PO item cat K → GR → settlement (MRKO)
- Subcontracting: PO item cat L → GI components → GR finished
2. Purchase Order Issues
Account assignment errors
- Category K (cost center): cost center must exist and be active
- Category A (asset): asset master must exist, depreciation area active
- Category F (internal order): order must be in Released status
- Category P (project/WBS): WBS element must be open for costs
Tolerance check (MIRO)
- OMR6 → tolerance keys: BD (amount) / VP (moving avg price variance) / PP (price)
- Tolerance = percentage + absolute amount — both must be within limits
GR-based invoice verification
- PO item → Invoice tab → GR-Based IV flag = X
- With flag: MIRO only possible after GR; invoice quantity = GR quantity
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 8.8 KB
- references/best-practices/operational.md 7.1 KB
- references/best-practices/period-end.md 6.6 KB
- references/de/quick-guide-de.md 3.7 KB
- references/en/quick-guide-en.md 3.3 KB
- references/img/account-determination.md 9.3 KB
- references/img/movement-type.md 7.6 KB
- references/img/overview.md 4.4 KB
- references/img/purchasing-org.md 14 KB
- references/img/tolerance-limits.md 11 KB
- references/ja/quick-guide-ja.md 3.6 KB
- references/ko/quick-guide.md 1.3 KB
- references/ko/SKILL-ko.md 4.4 KB
- references/vi/quick-guide-vi.md 3.9 KB
- references/zh/quick-guide-zh.md 3.2 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.
- yesterday First seen · 651 lines · 117 tokens per session scan A 03f0317450f8
sap-mm is a skill published in the GitHub repository BoxLogoDev/sapstack (18 stars, last pushed 5d ago), licensed MIT. It adds 117 tokens to every session and 8,196 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
abap-check
The catalogue of ABAP problems a green CI does not catch - abapGit round-trip and import failures (BOM, line endings, trailing whitespace, EOF newline, 255-character lines, metadata sidecars for CLAS and for DDLS/BDEF/TABL), activation errors abaplint does not model (classconstructor visibility, LOCAL FRIENDS, generic…
explore-ui
Standalone Phase 2 of SAP UI testing. Opens the target transaction in a real browser (SAP WebGUI) and explores it live to produce tests/ /test-cases/screens.md — the authoritative map of every on-screen control, its accessible name/label as Playwright will see it, and its initial state. This is about how the UI…
sap-testing
Entry point for the SAP UI test-automation environment. Explains project layout, the configured test folder, available tools, phase workflows, and bounded agent delegation. Use when the user asks about SAP UI testing, Playwright for SAP, writing tests for any ABAP report/transaction/process, generating test evidence…
helpers-reference
Reference for the bundled SAP Testing runtime (SapSession, SapArtifacts, resolveTestData, buildFixture, format helpers), importable in specs as "@sap-testing/runtime". Use when the user asks how a helper works or why a capability seems missing. Load sap-webgui for rendering, locator, theme, iframe, and…
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…
abap-performance-ecc
ABAP performance best practices for ECC / traditional database systems (Oracle, DB2,MSSQL, MaxDB). Use when writing or reviewing ABAP code on NON-HANA systems.IMPORTANT: First use the SAP system info tool to check the system type — if the system is S/4HANA or runs on HANA DB, load the abap-performance-hana skill…