agentmods.dev

sap-reference

sap-reference is a skill for Claude Code from rossumai/claude-marketplace. It costs 209 tokens per session (629 once invoked), scanned A, original, MIT.

A reference guide for connecting Rossum document processing to SAP business systems, including S/4HANA, ECC, Ariba, and VIM. SAP is enterprise software used to manage processes such as finance, purchasing, and inventory.

In plain words
What is it for?
Use it when planning integrations, exchanging master data, choosing APIs or middleware, or generating SAP-compatible invoice and order messages.
Why use it?
It explains SAP terms and helps choose how data should move between Rossum and the customer’s particular SAP setup.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the rossum-sa plugin — 35 skills, 4 hooks shipped together

not rated 5repo changed 1mo ago A scan 209 tokens original MIT

Good fit Use it when planning integrations, exchanging master data, choosing APIs or middleware, or generating SAP-compatible invoice and order messages.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rossumai/claude-marketplace/sap-reference
View source ↗ rossumai/claude-marketplace
Install

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.

Any agent
npx skills add rossumai/claude-marketplace --skill sap-reference
Clone the repo
git clone --depth 1 https://github.com/rossumai/claude-marketplace

Made for: Claude Code.

Or install rossum-sa, the plugin that ships this one along with the rest of its 35 skills, 4 hooks.

Wrote 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.

agentmods badge for sap-reference

README.md
[![agentmods](https://agentmods.dev/badge/skills/rossumai/claude-marketplace/sap-reference/github.svg)](https://agentmods.dev/skills/rossumai/claude-marketplace/sap-reference)
Your own site
<a href="https://agentmods.dev/skills/rossumai/claude-marketplace/sap-reference"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/sap-reference/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.

agentmods 80×15 button for sap-reference

Your own site · 80×15
<a href="https://agentmods.dev/skills/rossumai/claude-marketplace/sap-reference"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/sap-reference.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 209 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 629 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00209 $0.00629
Opus 5.5 $0.00084 $0.00252
Sonnet 5.5 $0.00042 $0.00126
Haiku 4.5 $0.00021 $0.00063

Measured 1mo ago against content hash e34e9c9fafd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sap-reference 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.

plugins/rossum-sa/skills/sap-reference/SKILL.md · 23 lines

What it actually says

SAP Integration Reference

Landscape for scoping, plus what three live Rossum–SAP integrations taught us about building one — the shapes, the measured API contracts, master data out, invoices in. For complete details, see reference.md. Drop-in code for the measured mechanisms is in the parts library (parts-index): the master-data/ importers and the two SAP export parts.

Use this knowledge when:

  • Scoping a Rossum-SAP integration (which SAP product, which hop — gateway, middleware, IDOC, VIM)
  • Choosing an integration pattern and estimating it: the three measured shapes carry effort signals (volume per object, endpoint latency, who owns API fixes)
  • Building or debugging a master-data feed from SAP: OData $skiptoken paging, creation-vs-change-date scoping, $expand flattening, the gateway's or rejection, the RESULT_FLAG/EV_MSG envelope, "0" boundaries, page-1-only totals, one-time vendors, goods-receipt latency
  • Designing the supplier feed: which SAP tables and API_BUSINESS_PARTNER properties carry what Rossum matches on (STCEG not TXJCD, BVTYP for VIM's bank selection)
  • Building or reviewing an export into SAP: BAPIRET2 as the verdict, timeout = unknown outcome, state before attachment, park vs post, posting date, credit-note sign, UBL 2.1 to VIM and the gateway SQL threat protection, BUS2081 attachments
  • Operating scheduled syncs: staggered crons against MDH's single ingest worker, runtime budgets, egress whitelisting, secrets in payload logs
  • Understanding SAP terminology (FICO, MIRO, GRNIV, IDOC, BAPI, LIFNR, BUKRS, ZTERM, RBSTAT, M8 535)
  • Writing SOWs that involve SAP integration
Files

What ships with it

1 file 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.

Changes

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.

  1. 1mo ago Changed · +4 lines · +139 tokens per session e34e9c9fafd6
  2. 2mo ago First seen · 19 lines · 70 tokens per session scan A 03fa6f683100

Subscribe to this mod's changes

sap-reference is a skill published in the GitHub repository rossumai/claude-marketplace (5 stars, last pushed 5d ago), licensed MIT. It adds 209 tokens to every session and 629 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 2026-08-31.

Backend and APIsFinance and fintech
Related

sap-reference compared with skills from other repositories

sap-reference next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
sap-referencerossumai/claude-marketplaceSkill55d agoMITA209Claude Code
x402browser-use/browser-useSkill121ktodayMITA166Claude Code
tushareHKUDS/Vibe-TradingSkill38ktodayMITA79Claude Code, Codex
hyperliquid-websocketgalleonlabs/hypergrok-trading-deskSkill4857d agoMITA89Claude Code
wechatpay-payment-integrationwechatpay-apiv3/wechatpay-skillsSkill3739d agoMITA330Claude Code, Codex
build-a-stripe-integrationsuperset-sh/supersetSkill16k4d agoMITA74Claude Code
freee-api-skillfreee/freee-mcpSkill518yesterdayApache-2.0A365Claude Code