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 efeumutaslan/SAP-SKILLS --skill sap-s4hana-extensibilitygit clone --depth 1 https://github.com/efeumutaslan/SAP-SKILLSWrote 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/efeumutaslan/sap-skills/sap-s4hana-extensibility)<a href="https://agentmods.dev/skills/efeumutaslan/sap-skills/sap-s4hana-extensibility"><img src="https://agentmods.dev/badge/skills/efeumutaslan/sap-skills/sap-s4hana-extensibility/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/efeumutaslan/sap-skills/sap-s4hana-extensibility"><img src="https://agentmods.dev/badge/skills/efeumutaslan/sap-skills/sap-s4hana-extensibility.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00118 | $0.02748 |
| Opus 5 | $0.00059 | $0.01374 |
| Sonnet 5 | $0.00024 | $0.00550 |
| Haiku 4.5 | $0.00012 | $0.00275 |
Grade A, and why
sap-s4hana-extensibility 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 12d 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAP S/4HANA Extensibility & Clean Core
Related Skills
sap-rap-comprehensive— RAP business object development and extensionsap-security-authorization— Authorization for extensionssap-abap-advanced— ABAP Cloud Tier 1/Tier 2 patterns and classic-to-cloud migrationsap-migration— S/4HANA system conversion and data migration
Quick Start
Choose your extensibility approach:
| Need | Approach | Who |
|---|---|---|
| Add field to standard object | Key-User: Custom Fields app (F1481) | Consultant |
| Add validation/defaulting logic | Key-User: Custom Logic app (F6957) or Developer: Cloud BAdI in ADT | Consultant/Developer |
| New standalone business object | Key-User: Custom Business Objects app or Developer: RAP BO | Consultant/Developer |
| Complex app on BTP | Side-by-Side: CAP/Fiori on BTP via released APIs | Developer |
| Extend CDS view with custom field | Developer: EXTEND VIEW ENTITY in ADT |
Developer |
| Extend RAP BO behavior | Developer: extend behavior for in ADT |
Developer |
Check if your API is released:
ADT → Project Explorer → Released Objects → filter by object type
or: api.sap.com → Package S4HANACloudBADI (for Cloud BAdIs)
Core Concepts
Clean Core 4-Level Model
| Level | Name | What's Allowed | Upgrade Safety |
|---|---|---|---|
| A | Fully Compliant | Released APIs only (C0/C1/C2), ABAP Cloud | Fully safe |
| B | Compliant | Level A + classic APIs (BAPIs, standard BAdIs) | Generally safe |
| C | Partially Compliant | SAP internal objects, unrestricted ABAP | Risk of breakage |
| D | Non-Compliant | Modifications, direct table writes, implicit enhancements | High risk |
Target: Level A for all new development.
Extensibility Availability Matrix
| Type | Public Cloud | Private Cloud | On-Premise |
|---|---|---|---|
| Key-User (In-App) | Yes | Yes | Yes (limited) |
| Developer (ABAP Cloud) | Yes | Yes | Yes (2022+) |
| Side-by-Side (BTP) | Yes | Yes | Yes |
| Classic ABAP (unrestricted) | No | Yes | Yes |
| SAP GUI (SE80, SE38...) | No | Yes | Yes |
| Code modifications | No | No | Yes (discouraged) |
What ships with it
9 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/cbo-guide.md 7.3 KB
- references/cds-extension-patterns.md 5.9 KB
- references/clean-core-levels.md 4.5 KB
- references/cloud-badi-catalog.md 4.9 KB
- references/tier2-wrapper-guide.md 7.7 KB
- scripts/check-clean-core.sh 3.4 KB runs code
- templates/badi-implementation.abap 1.5 KB
- templates/cds-extend.cds 1.2 KB
- templates/tier2-wrapper.abap 2.8 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.
- 12d ago First seen · 258 lines · 118 tokens per session scan A ccad9558d327
sap-s4hana-extensibility is a skill published in the GitHub repository efeumutaslan/SAP-SKILLS (5 stars, last pushed 5mo ago), licensed MIT. It adds 118 tokens to every session and 2,748 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 2026-08-31.
Other skills, from other repositories
cao-provider
Create a new CLI agent provider for CAO (CLI Agent Orchestrator). Use this skill whenever the user wants to add support for a new CLI-based AI agent (e.g., a new coding assistant CLI), integrate a new provider, or scaffold a provider implementation. Also use when the user asks about the provider architecture, what…
adt-api-discovery
Investigate SAP ADT REST API endpoints. Use when the user asks about ADT API endpoints, request/response XML formats, content types, or how a specific ADT feature works under the hood. Teaches how to trace from discovery documents → RESAPP classes → handler classes → Simple Transformations → XML schemas. Requires the…
api-design
REST/GraphQL/gRPC API design best practices. Use when designing APIs, defining contracts, handling versioning. Covers OpenAPI 3.2, GraphQL Federation, gRPC streaming.
ask-opencli
A helper for asking Grok or Gemini through OpenCLI, which uses an already signed-in Chrome browser session instead of a paid API.
gemma4-local-deploy
A guide for running Gemma 4 12B, an AI language model, locally on a Mac or Apple Silicon computer. It uses downloaded model files and a local service that provides an OpenAI-compatible API or Ollama access when requested.
config-secrets-environments
Design, audit, and verify configuration, environment separation, secrets, BYOK flows, key rotation, config schema validation, and drift checks across local, dev, staging, and production. Use when adding env vars, changing runtime config, handling API keys or user-provided keys, diagnosing config drift, or preparing…