clean-abap

clean-abap is a skill for Claude Code, Codex from Ciltress/sap-abap-mcp. It costs 140 tokens per session (3,596 once invoked), scanned A, a copy of clean-abap, MIT.

A checker for ABAP code based on Clean ABAP, SAP’s style guidance for readable and maintainable ABAP. When connected to an SAP system, it can read the code and use syntax checks, automated checks, formatting, and ABAP Unit tests.

In plain words
What is it for?
Use it to review ABAP classes and their tests, check naming and method design, detect obsolete syntax, run available automated checks, and assess error handling and code quality.
Why use it?
It finds style, structure, syntax, and testing problems that can make ABAP harder to understand, change, or maintain.

Skill for Claude CodeCodex

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

Good fit Use it to review ABAP classes and their tests, check naming and method design, detect obsolete syntax, run available automated checks, and assess error handling and code quality.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/ciltress/sap-abap-mcp/clean-abap"><img src="https://agentmods.dev/badge/skills/ciltress/sap-abap-mcp/clean-abap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 140 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,596 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 95% copy Near-identical to another mod 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 $0.00140 $0.03596
Opus 5 $0.00070 $0.01798
Sonnet 5 $0.00028 $0.00719
Haiku 4.5 $0.00014 $0.00360

Measured 11d ago against content hash 533bdfd8a06c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

clean-abap 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 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.

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.

Origin

This is a copy

95% identical to clean-abap — 45 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/ABAP/skills/clean-abap/SKILL.md · 536 lines

How it starts

The opening of the file, as written. The whole thing — 536 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clean ABAP

This skill provides comprehensive checking of ABAP code against Clean ABAP principles, based on the Clean ABAP style guide which adapts Robert C. Martin's Clean Code for ABAP.

Step 0 - is there a system?

Check whether the ABAP ADT MCP server's tools are available (readAbapObject, syntaxCheckCode, createAtcRun).

  • Yes -> read references/mcp-adt-tools.md and follow it. Fetch the code yourself with readAbapObject - do not ask the user to paste code you can read - then let the system decide the mechanical half (obsolete syntax, types, formatting, tests) and spend your review on the half it cannot: names, comments, method design, error handling.
  • No -> review by hand exactly as below, from the code the user provides.

The 15 categories and the output format are the same either way. What changes is who answers which category, and that is tabulated in references/mcp-adt-tools.md section 3.

How to Use This Skill

When checking ABAP code for Clean ABAP compliance:

  1. Get the code - readAbapObject by name when a system is reachable (and read the class's includes.testclasses, or note its absence); otherwise take what the user provides
  2. Run the checks the system can answer - syntaxCheckCode, ATC, prettyPrinter, unitTestRun. If the syntax check reports errors, report those first: code that does not compile is not ready for a style review
  3. Categorize issues by Clean ABAP sections (Names, Language, Constants, Variables, Tables, Strings, Booleans, Conditions, Ifs, Classes, Methods, Error Handling, Comments, Formatting, Testing)
  4. Identify violations with specific line references when available
  5. Provide actionable recommendations with code examples showing both the problem and the clean solution
  6. Prioritize issues by impact (critical, major, minor)
  7. Attribute every finding - say whether it came from the system or from your judgement. They are different kinds of claim and a reader weighs them differently

Read the full file on GitHub · 536 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 · 536 lines · 140 tokens per session scan A 533bdfd8a06c

Subscribe to this mod's changes

clean-abap is a skill published in the GitHub repository Ciltress/sap-abap-mcp (3 stars, last pushed 18d ago), licensed MIT. It adds 140 tokens to every session and 3,596 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to clean-abap, differing in 45 lines, and is treated as a copy.