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-trgit 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-tr)<a href="https://agentmods.dev/skills/boxlogodev/sapstack/sap-tr"><img src="https://agentmods.dev/badge/skills/boxlogodev/sapstack/sap-tr/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-tr"><img src="https://agentmods.dev/badge/skills/boxlogodev/sapstack/sap-tr.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 Excessive Agency · line 523 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00115 | $0.05754 |
| Opus 5.5 | $0.00046 | $0.02302 |
| Sonnet 5.5 | $0.00023 | $0.01151 |
| Haiku 4.5 | $0.00012 | $0.00575 |
Grade A, and why
sap-tr 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 — 558 lines — stays where its author put it; the contents beside it link to each section on GitHub.
1. Environment Detection
Ask before answering:
□ Classic Cash Management (ECC / S/4HANA pre-1909) or
S/4HANA Advanced Cash Management (One Exposure hub)?
□ Bank Communication Management (BCM) active?
□ Transaction Manager (TRM) activated? (money market / FX / derivatives)
□ Which SAP release? (impacts available tools significantly)
□ Bank statement format: MT940 / BAI2 / CAMT.053 / proprietary?
2. Liquidity Forecast Troubleshooting
FF7A / FF7B Missing Items
Step 1 — Check active cash-management model and derivation
- Classic Liquidity Planner: confirm source document, planning group/level, liquidity item derivation, date logic, and report selection.
- S/4HANA Advanced Cash Management: confirm active One Exposure source application, flow type/certainty level, liquidity item derivation, and app filter.
Step 2 — Check cash-flow line-item evidence
- Use the supported classic report or released Cash Flow Analyzer/Check Cash Flow Items app, filtered by the user's company code and planning date range.
- Distinguish “item exists but report filter excludes it” from “source did not generate a cash-management flow.”
Step 3 — Rebuild only through the release-specific supported procedure
- Do not recommend delete-and-rebuild from a generic symptom.
- First preserve counts/control totals, isolate source/company/date scope, prove the derivation correction in QA, and obtain close/treasury approval.
- Use the documented classic reconstruction or S/4 Flow Builder initialization path for the exact release; include a restore/reconciliation plan.
Planning Level Strategy
| Level Type | Description | Source |
|---|---|---|
| Actual | Bank-confirmed transactions | posted bank statement |
| Memo records | Manually entered forecast | FF63 (memo records) |
| Forecast | Open items / expected payments | AP/AR open items |
| Plan | Long-range planning | Manual or interface |
3. Bank Statement Processing
What ships with it
16 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 9.0 KB
- references/best-practices/operational.md 6.5 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 1.4 KB
- references/img/bank-statement.md 9.3 KB
- references/img/dmee.md 10 KB
- references/img/house-bank.md 8.6 KB
- references/img/overview.md 5.1 KB
- references/img/payment-program.md 2.5 KB
- references/ja/quick-guide-ja.md 1.5 KB
- references/ko/quick-guide.md 1.4 KB
- references/ko/SKILL-ko.md 3.3 KB
- references/liquidity-guide.md 2.3 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.
- 1mo ago First seen · 558 lines · 115 tokens per session scan A 275c1b1642e1
sap-tr is a skill published in the GitHub repository BoxLogoDev/sapstack (20 stars, last pushed 26d ago), licensed MIT. It adds 115 tokens to every session and 5,754 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…
workday-expert
Expert in Workday HCM platform, integrations, custom reports, business processes, calculated fields, and Workday Studio development. Use when the user mentions HR, finance, ERP, cloud, HCM, or Workday integration, or when the task involves Workday Modules, Integration Technologies, Reporting & Analytics, or Custom…
sap-rpt1
SAP-RPT-1-OSS local tabular prediction workflows for FI/CO prototype datasets. Use when preparing SAP finance CSV exports for classification or regression experiments with source-verified setup, leakage checks, and governance review.
frihet-mcp
Manage a connected Frihet ERP workspace: invoices, quotes, expenses, clients, products and other available business operations. Use for Frihet requests, facturas, presupuestos, gastos, cobros, overdue invoices, monthly review or revisión mensual. Reads current tool schemas before acting, separates currencies and…
accounted-api
Consume the Accounted REST API (Swedish double-entry bookkeeping SaaS, https://app.gnubok.se/api/v1). Use when building an integration, app, backend job, or agent tool layer against Accounted: invoices, customers, suppliers, supplier invoices, journal entries (bokföring), bank transactions and reconciliation, payroll…
documentos
Prepare invoices and quotes for a connected Frihet workspace. Use for preparar factura, presupuesto, invoice draft, quote or quote conversion. Resolves missing client, currency and tax data before an authorized draft creation. Also use for invoice recovery after timeout, lost response or resultado desconocido al crear.