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 likweitan/abap-skills --skill abap-cloudgit clone --depth 1 https://github.com/likweitan/abap-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/likweitan/abap-skills/abap-cloud)<a href="https://agentmods.dev/skills/likweitan/abap-skills/abap-cloud"><img src="https://agentmods.dev/badge/skills/likweitan/abap-skills/abap-cloud/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/likweitan/abap-skills/abap-cloud"><img src="https://agentmods.dev/badge/skills/likweitan/abap-skills/abap-cloud.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00210 | $0.04652 |
| Opus 5.5 | $0.00084 | $0.01861 |
| Sonnet 5.5 | $0.00042 | $0.00930 |
| Haiku 4.5 | $0.00021 | $0.00465 |
Grade A, and why
abap-cloud 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- abap-cloud — 100% identical, 302 lines differ
How it starts
The opening of the file, as written. The whole thing — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ABAP Cloud & the Clean Core Level Concept
Guide for developing with the ABAP Cloud programming model, classifying extensions using the clean core level concept (A–D), and applying clean core principles.
Terminology note: SAP has evolved the former 3-tier extensibility model into the clean core level concept. The 3-tier model (Tier 1/2/3) is superseded — use Levels A, B, C, D instead. Current product naming: SAP Cloud ERP (public), SAP Cloud ERP Private (formerly S/4HANA Cloud Private Edition), SAP Business AI Platform (includes SAP BTP capabilities), SAP Build (pro-code and low-code tooling, includes ABAP Cloud).
Workflow
-
Determine the user's context:
- Understanding ABAP Cloud concepts and restrictions
- Classifying an extension into a clean core level
- Choosing between ABAP Cloud development and classic ABAP development
- Wrapping non-released APIs for use in ABAP Cloud
- Identifying released or classic API alternatives
-
Classify the extension by clean core level:
- Level A: only released APIs and extension points (stability contract)
- Level B: classic APIs and classic frameworks (nominated, no stability contract)
- Level C: SAP internal objects (conditionally clean with changelog)
- Level D: not-recommended objects and patterns (must be remediated)
-
Apply the lowest-level rule: an extension is classified by the lowest level it uses. A Level A extension that calls one internal object is a Level C extension.
-
Guide implementation toward the highest applicable level (Level A first).
Clean Core Level Concept
SAP classifies extensions into four levels, similar to energy labels. Level A is the target state reflecting the "SAP Business AI Platform first" strategy; Level D must be remediated.
| Level | Name | SAP objects qualifier | Upgrade stability | ATC behavior |
|---|---|---|---|---|
| Level A | Extend with SAP Build | [Released] SAP remote APIs, local APIs, extension points |
Guaranteed by stability contract | No finding |
| Level B | Leverage classic APIs | [Classic] SAP APIs and extension points |
Nominated by SAP experts, no formal contract | Priority 3 (information) |
| Level C | Access internal objects | [Internal] SAP objects (the default for unclassified objects) |
Not upgrade-stable; mitigate via changelog | Priority 2 (warning) |
| Level D | Not recommended | [Not recommended] SAP objects, extension points, techniques |
High risk, significant technical debt | Priority 1 (error) |
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.
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 Changed · +138 lines · +57 tokens per session 9e68070c797a
- 1mo ago First seen · 193 lines · 153 tokens per session scan A eecab060198c
abap-cloud is a skill published in the GitHub repository likweitan/abap-skills (72 stars, last pushed 11d ago), licensed MIT. It adds 210 tokens to every session and 4,652 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 2026-08-30.
Other skills, from other repositories
abap-code-writing
Structured process for building ABAP solutions. Use BEFORE writing any ABAP code — reports, classes, function modules, enhancements, or full processes. Guides through requirement validation, system exploration, architecture planning, research of existing objects, and detailed design before any code is written.
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…
sap-adt-cli
Read/write ABAP source and metadata via SAP ADT REST API: programs, classes, function modules/groups, interfaces, includes, CDS views, DDIC tables/structures, data elements/domains, type groups, transactions, packages, search, where-used, syntax check, Open SQL preview, and transport requests (list/create/release).…
sap-integration-wiki
Guide for integrating external systems (Java, Python, .NET, Node.js, low-code) with SAP (ECC 6.0, S/4HANA On-Premise/Cloud): OData V2/V4, RFC/JCo, SOAP-over-HTTP RFC without JCo, IDoc/PI-PO, BAPI, RAP, BTP Integration Suite/iFlow, Event Mesh, Cloud Connector, Communication Arrangements, FI-AA, AR/AP, Central Finance…
sap-abap-cds
Comprehensive SAP ABAP CDS (Core Data Services) reference for data modeling, view development, and semantic enrichment. Use when creating CDS views or view entities, defining data models with annotations, working with associations and cardinality, implementing input parameters, using built-in functions, writing CASE…
sap-abap
Comprehensive ABAP development skill for SAP systems. Use when writing ABAP code, working with internal tables, structures, ABAP SQL, object-oriented programming, RAP (RESTful Application Programming Model), CDS views, EML statements, ABAP Cloud development, string processing, dynamic programming, RTTI/RTTC, field…