abap-clean-core

abap-clean-core is a skill for Claude Code, Codex from yzonur/sap-adt-mcp. It costs 236 tokens per session (4,194 once invoked), scanned D, original, MIT.

A set of principles for writing SAP S/4HANA extensions that stay separate from SAP's standard code and use stable, officially released interfaces. ABAP is SAP's programming language, and extensions add custom business behavior.

In plain words
What is it for?
Use it when designing, reviewing, refactoring, or testing ABAP extensions such as custom code, BAdIs, BAPIs, user exits, CDS views, or RAP applications.
Why use it?
It helps reduce upgrade problems, fragile dependencies, and technical debt caused by changing standard code or relying on undocumented interfaces.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when designing, reviewing, refactoring, or testing ABAP extensions such as custom code, BAdIs, BAPIs, user exits, CDS views, or RAP applications.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yzonur/sap-adt-mcp/abap-clean-core
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 yzonur/sap-adt-mcp --skill abap-clean-core
Clone the repo
git clone --depth 1 https://github.com/yzonur/sap-adt-mcp

Made for: Claude Code, Codex.

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 abap-clean-core

README.md
[![agentmods](https://agentmods.dev/badge/skills/yzonur/sap-adt-mcp/abap-clean-core/github.svg)](https://agentmods.dev/skills/yzonur/sap-adt-mcp/abap-clean-core)
Your own site
<a href="https://agentmods.dev/skills/yzonur/sap-adt-mcp/abap-clean-core"><img src="https://agentmods.dev/badge/skills/yzonur/sap-adt-mcp/abap-clean-core/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 abap-clean-core

Your own site · 80×15
<a href="https://agentmods.dev/skills/yzonur/sap-adt-mcp/abap-clean-core"><img src="https://agentmods.dev/badge/skills/yzonur/sap-adt-mcp/abap-clean-core.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 236 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,194 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 2 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 $0.00236 $0.04194
Opus 5 $0.00118 $0.02097
Sonnet 5 $0.00047 $0.00839
Haiku 4.5 $0.00024 $0.00419

Measured 11d ago against content hash 04ef1cd2709f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade D, and why

abap-clean-core scanned grade D with 2 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 11d 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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

- Don't refuse, don't moralize, don't repeat the lecture

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

- Don't refuse, don't moralize, don't repeat the lecture
skills/abap-clean-core/SKILL.md · 286 lines

How it starts

The opening of the file, as written. The whole thing — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ABAP Clean Core

This skill encodes SAP's official Clean Core extensibility framework. Apply it when guiding the user through ABAP development, code review, refactoring, or architecture decisions for SAP S/4HANA.

Prerequisites

None — this is a knowledge skill: it needs no SAP connection and works in any ABAP conversation. When sap-adt-mcp is connected it gets sharper: adt_run_atc / adt_run_atc_package verify findings against the system's real check variant, adt_list_released_apis confirms what is actually released on that release level, and adt_where_used measures the blast radius of a Level C/D dependency before recommending a replacement. Cloud-readiness ATC checks require an S/4HANA system (or a recent ATC content update on NW 7.5x).

Why Clean Core matters

Every extension that touches SAP-internal objects, modifies standard code, or relies on undocumented APIs becomes a maintenance liability. It blocks upgrades, breaks unpredictably, and accumulates as technical debt that compounds over years.

Clean Core is the discipline of building extensions that survive SAP upgrades automatically — by isolating custom code from the standard through stable, released interfaces. It's not theoretical: SAP's entire cloud strategy (RISE, GROW, S/4HANA Cloud) assumes customer extensions are decoupled. Code that ignores Clean Core is code that will eventually be rewritten.

Clean Core spans five principles — Processes, Data, Integration, Operations, and Extensibility. This skill focuses on Extensibility (the code and architecture side), but be aware: when a user asks about "clean core data" or "clean core integration," they're asking about the other four principles, not about extensions.

When you help with ABAP, your job is to nudge the user toward extensions that will still work after the next upgrade — without lecturing, without refusing classic-ABAP work when it's needed, but always making the trade-off visible.

Two strategic tracks: Stay Clean & Get Clean

Read the full file on GitHub · 286 lines

Files

What ships with it

4 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.

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. 11d ago First seen · 286 lines · 236 tokens per session scan D 04ef1cd2709f

Subscribe to this mod's changes

abap-clean-core is a skill published in the GitHub repository yzonur/sap-adt-mcp (16 stars, last pushed 25d ago), licensed MIT. It adds 236 tokens to every session and 4,194 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it D with 2 findings (tells the agent never to refuse, strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.