ABAP-guardian: Skill for Claude Code

.agents/skills/abap-code-review/SKILL.md

abap-code-review is a skill for Claude Code, Codex from kallolchakraborty/ABAP-guardian. It costs 29 tokens per session (1,677 once invoked), scanned A, original, MIT.

A production code-review method for ABAP, the programming language used in SAP systems. It checks architecture, performance, security, Clean ABAP style, cloud compatibility, and SAP’s ABAP Test Cockpit rules.

In plain words
What is it for?
Use it to review ABAP programs and classes, perform ATC-style analysis, refactor legacy code, improve Open SQL query performance, and check compatibility with supported SAP releases.
Why use it?
It makes reviews cover structural and operational risks before focusing on formatting. This is useful when code must run reliably in business-critical SAP environments or be modernized from older procedural style.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is kallolchakraborty/ABAP-guardian's own configuration. It tells Claude Code and Codex how to work on ABAP-guardian itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ABAP-guardian configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kallolchakraborty/ABAP-guardian. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kallolchakraborty/ABAP-guardian/main/.agents/skills/abap-code-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/kallolchakraborty/ABAP-guardian

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-code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/kallolchakraborty/abap-guardian/abap-code-review/github.svg)](https://agentmods.dev/skills/kallolchakraborty/abap-guardian/abap-code-review)
Your own site
<a href="https://agentmods.dev/skills/kallolchakraborty/abap-guardian/abap-code-review"><img src="https://agentmods.dev/badge/skills/kallolchakraborty/abap-guardian/abap-code-review/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-code-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/kallolchakraborty/abap-guardian/abap-code-review"><img src="https://agentmods.dev/badge/skills/kallolchakraborty/abap-guardian/abap-code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,677 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 $0.00029 $0.01677
Opus 5 $0.00015 $0.00839
Sonnet 5 $0.00006 $0.00335
Haiku 4.5 $0.00003 $0.00168

Measured 11d ago against content hash 7bc825f97bbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

abap-code-review 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/run_evals.py, scripts/validate_skill.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/abap-code-review/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ABAP Guardian — Industry-Grade ABAP Methodology

Overview

This skill encodes an enterprise-grade ABAP code review methodology. Use it to produce production-quality code reviews that enforce SAP's Clean ABAP standards, ABAP Cloud compliance, release compatibility (7.40+ to ABAP Cloud), ABAP Test Cockpit (ATC) compliance, and strict performance/security rules.

Core axiom: Production ABAP must be clean, performant, and secure. There is no compromise on architecture or safety.


When to Use

  • User asks you to review a snippet of ABAP code, a class, or a program.
  • User needs an SAP ABAP Test Cockpit (ATC) style analysis of their code.
  • User wants to refactor legacy procedural ABAP into modern, Clean ABAP.
  • User needs performance tuning for OpenSQL queries.

Don't use for: Frontend Fiori/UI5 debugging, pure SAP Basis administration tasks, non-ABAP languages, or legacy pre-7.40 SAP systems (e.g. R/3 4.6c).


The 4-Step Code Review Process

Execute all four steps in sequence. Do NOT skip to syntax formatting without completing architecture and security analysis first.

Step 1 — Context & Quality Gate Triage (MANDATORY)

Understand what the code is trying to achieve. Identify the pattern (e.g., RAP behavior implementation, simple report, CDS view).

Identify Red Flags immediately:

  • SELECT inside a LOOP.
  • Dynamic SQL without cl_abap_dyn_prg validation.
  • Missing AUTHORITY-CHECK.
  • Business logic residing in a UI class or function module.

Completion criterion: You have identified the core purpose of the code and flagged any critical, system-breaking "Red Flags".


Step 2 — Architecture & Clean ABAP Analysis

Analyze the structure of the code against Clean ABAP principles.

  • Are they using Object-Oriented ABAP (CL_, IF_) instead of FORM or FUNCTION?
  • Are methods small and focused (doing exactly one thing)?
  • Is naming descriptive and English-based?
  • Is error handling class-based (CX_) rather than using SY-SUBRC?
  • Does it adhere to Separation of Concerns (UI vs. Logic vs. Database)?

Read the full file on GitHub · 136 lines

Files

What ships with it

6 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 · 136 lines · 29 tokens per session scan A 7bc825f97bbe

Subscribe to this mod's changes

abap-code-review is a skill published in the GitHub repository kallolchakraborty/ABAP-guardian (5 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 1,677 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

no-bare-casts

Writing as in TypeScript or TSX production code, modifying a file that contains a bare as cast, silencing a type error with a cast, encountering as unknown as, or reviewing a cast site.

prisma/orm · 52 tokens

code-review-csharp

Perform structured code reviews of C# source code covering naming conventions, performance, security, readability, and .NET best practices. Trigger phrases include "review this C# code", "check my C# for best practices", "analyze this C# class", "find issues in my C# code".

pnp/copilot-prompts · 66 tokens

solid-principles

SOLID principles checklist with Java examples. Use when a class has too many responsibilities, an abstraction leaks, or a dependency points the wrong way, and when the user asks about Single Responsibility, Open/Closed, Liskov, Interface Segregation or Dependency Inversion. For naming, duplication and method length…

decebals/claude-code-java · 73 tokens

splitting-oversized-modules

Split an oversized Python module (a thousand-plus-line logic.py, models.py, api.py, or its test file) into a package of one module per concern, mechanically and provably without changing behavior. Use on a request to split / break up / decompose a god module or move functions out of one, once a human has agreed to…

PostHog/posthog-foss · 197 tokens

go-concurrency-safety

L1 supplement - audits Go-specific concurrency hazards in node client code: map iteration non-determinism, goroutine leaks, mutex ordering, panic boundaries, context cancellation.

PlamenTSV/plamen · 40 tokens

splitting-oversized-modules

Split an oversized Python module (a thousand-plus-line logic.py, models.py, api.py, or its test file) into a package of one module per concern, mechanically and provably without changing behavior. Use on a request to split / break up / decompose a god module or move functions out of one, once a human has agreed to…

PostHog/posthog · 197 tokens