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-finpx skills add BoxLogoDev/sapstack --skill sap-figit 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-fi)<a href="https://agentmods.dev/skills/boxlogodev/sapstack/sap-fi"><img src="https://agentmods.dev/badge/skills/boxlogodev/sapstack/sap-fi.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 | $0.00132 | $0.02176 |
| Opus 5 | $0.00066 | $0.01088 |
| Sonnet 5 | $0.00026 | $0.00435 |
| Haiku 4.5 | $0.00013 | $0.00218 |
Grade A, and why
sap-fi 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
1. Environment Intake Checklist
When any FI issue is reported, collect before answering:
- SAP Release (ECC 6.0 EhPx / S/4HANA 19xx/20xx/21xx/22xx/23xx)
- Deployment model (on-premise / RISE / Cloud PE)
- Fiscal year variant (calendar / non-calendar — which month start?)
- Error message number and T-code where it occurred
- Company code (user provides — never assume)
2. AP — Accounts Payable
Top issues with T-code + table-level diagnosis:
Vendor invoice posting errors (FB60 / MIRO)
- Tax code not assigned: check FTXP → tax procedure → company code assignment
- Tolerance exceeded: OMR6 → tolerance key per company code (amount / percentage)
- GR-based IV mismatch: PO item → invoice tab → GR-based IV flag vs. goods receipt qty
Payment run (F110)
- No items selected: check open item due date, payment method on vendor master (LFB1-ZWELS), house bank assigned
- House bank not determined: FBZP → bank determination → ranking order → house bank / account ID
- DME file not generated: DMEE → payment medium tree format assigned to payment method
Withholding tax missing
- WTAD → withholding tax type not assigned to company code
- SPRO → FI → Withholding Tax → Extended Withholding Tax → Company Code → Assign Withholding Tax Types
Vendor master dual control
- FKMT → pending changes awaiting second approval
- Check: LFA1/LFB1 tables → field change log
Reconciliation account cannot be posted directly
- Root cause: LFB1-AKONT is a recon account (FS00 → recon account type = K)
- Fix: use FB60 (vendor invoice) or Special G/L (F-47/F-48) — never FB01 direct
3. AR — Accounts Receivable
Customer invoice
- FB70 (FI direct) / VF01 (SD billing — preferred for SD-integrated flows)
- Dispute management: UDM_DISPUTE (S/4HANA FSCM)
Dunning (F150)
- Dunning procedure: FBMP → dunning levels, minimum amounts, interest
- Dunning area: company code → dunning area assignment
- Block from dunning: FD02 → correspondence tab → dunning block
Credit management
- ECC: FD32 → credit limit per credit control area
- S/4HANA FSCM: UKM_BP → credit segment → limit / rule-based check
- Release blocked orders: VKM1 (orders) / VKM3 (deliveries)
What ships with it
19 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 7.6 KB
- references/best-practices/operational.md 5.0 KB
- references/best-practices/period-end.md 6.3 KB
- references/closing-checklist.md 3.6 KB
- references/de/quick-guide-de.md 4.2 KB
- references/en/quick-guide-en.md 3.4 KB
- references/img/asset-accounting.md 12 KB
- references/img/document-type-posting-key.md 9.4 KB
- references/img/gl-account-determination.md 8.3 KB
- references/img/grir-clearing.md 11 KB
- references/img/overview.md 3.2 KB
- references/img/period-control.md 9.1 KB
- references/img/tax-configuration.md 8.8 KB
- references/ja/quick-guide-ja.md 4.1 KB
- references/ko/quick-guide.md 2.6 KB
- references/ko/SKILL-ko.md 9.0 KB
- references/tcode-reference.md 3.9 KB
- references/vi/quick-guide-vi.md 4.7 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.
- yesterday First seen · 201 lines · 132 tokens per session scan A cf66eb4c4d5e
sap-fi is a skill published in the GitHub repository BoxLogoDev/sapstack (18 stars, last pushed 5d ago), licensed MIT. It adds 132 tokens to every session and 2,176 once invoked, about $0.0007 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
research
Survey how best-in-class ERPs and point solutions implement a feature, and produce a findings file at .ai/research/{slug}.md. Use when designing a new feature, evaluating approaches, or answering "how do competitors / SAP / the industry do X". Required before designing any ERP-domain feature (accounting, costing, tax…
frihet-mcp
Business-aware ERP management skill for Frihet MCP server. Manages invoices, expenses, clients, products, quotes, and webhooks with embedded Spanish tax knowledge (IVA/IGIC/IRPF), automatic expense categorization, and multi-step workflows like monthly close and quarterly tax prep. Use when the user says "create…
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.
value-advisory
Use when building a business case, calculating ROI or TCO, quantifying SAP project benefits, validating savings claims, or producing value realization frameworks for any SAP investment decision.
concur
Use when working with SAP Concur — Concur Expense, Concur Travel, Concur Invoice, Concur Request, expense policy configuration, receipt management, travel booking, approval workflows, integration with S/4HANA FI, audit rules, or compliance monitoring.
fieldglass
Use when working with SAP Fieldglass — contingent workforce management, services procurement, Statement of Work (SOW), worker management lifecycle, rate card management, approval workflows, VMS reporting, or Fieldglass integration with S/4HANA.