abap-review

abap-review is a skill for Claude Code, Codex from palimkarakshay/abap-mcp. It costs 60 tokens per session (475 once invoked), scanned A, original, MIT.

A review skill for ABAP, CDS, and RAP source code using static analysis. ABAP is SAP's programming language; CDS and RAP are SAP technologies for defining data and building applications.

In plain words
What is it for?
Use it for focused ABAP code reviews and to suggest small fixes. It complements SAP ATC and runtime testing rather than replacing them.
Why use it?
It identifies possible style, performance, security, cloud-readiness, and commit-readiness issues before code is merged or released.

Skill for Claude CodeCodex

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

Good fit Use it for focused ABAP code reviews and to suggest small fixes. It complements SAP ATC and runtime testing rather than replacing them.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/palimkarakshay/abap-mcp/abap-review"><img src="https://agentmods.dev/badge/skills/palimkarakshay/abap-mcp/abap-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 475 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 $0.00060 $0.00475
Opus 5 $0.00030 $0.00237
Sonnet 5 $0.00012 $0.00095
Haiku 4.5 $0.00006 $0.00047

Measured 11d ago against content hash 57f9354e4893, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

abap-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.

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.

plugins/abap-mcp/skills/abap-review/SKILL.md · 25 lines

What it actually says

ABAP Review

Use the connected abap-mcp tools to ground a senior-consultant review in observable findings.

Workflow

  1. Resolve the source in scope. The MCP server accepts source text, not paths: read any user-named workspace files first and pass their full text with stable filenames. If the scope is unclear, ask instead of guessing. Batch more than 32 files or files over 100,000 characters.
  2. Run lint_abap with the default style preset. Use focus: "Performance", "Security", or "Styleguide" only when that lens matches the request. Use full only when all relevant dependencies are supplied.
  3. Triage findings by production impact, then severity. For important or unfamiliar rule keys, call explain_abap_rule; explain why the rule matters and propose the smallest concrete fix.
  4. For ABAP Cloud or Clean Core questions, also run check_cloud_readiness. Treat language blockers separately from its dated, informational releasedApiFindings. A clean result is a static-parser verdict, not certification.
  5. If the user authorizes edits, preserve the original text, make focused changes, rerun lint_abap, then use compare_abap with before and after sources. Report new, resolved, and remaining findings and any readiness-grade movement.
  6. Finish with a concise verdict: ready for the next engineering gate, or the shortlist of changes that still gate it.

Honesty boundaries

  • The server analyzes only supplied text, entirely offline. It does not connect to SAP, inspect repository paths, run code, or execute ATC.
  • Released-API observations come from the bundled snapshot and are dated. Keep them out of the language-blocker score and say that target-system ATC is authoritative.
  • Do not claim that behavior definitions or service definitions received deep abaplint validation.
  • Review does not imply permission to edit files; make changes only when the user asks.
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 · 25 lines · 60 tokens per session scan A 57f9354e4893

Subscribe to this mod's changes

abap-review is a skill published in the GitHub repository palimkarakshay/abap-mcp (2 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 475 once invoked, about $0.0003 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.