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 Ciltress/sap-abap-mcp --skill clean-abapgit clone --depth 1 https://github.com/Ciltress/sap-abap-mcpWrote 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/ciltress/sap-abap-mcp/clean-abap)<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.
<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>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 | $0.00140 | $0.03596 |
| Opus 5.5 | $0.00056 | $0.01438 |
| Sonnet 5.5 | $0.00028 | $0.00719 |
| Haiku 4.5 | $0.00014 | $0.00360 |
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 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.
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.
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.mdand follow it. Fetch the code yourself withreadAbapObject- 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:
- Get the code -
readAbapObjectby name when a system is reachable (and read the class'sincludes.testclasses, or note its absence); otherwise take what the user provides - 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 - Categorize issues by Clean ABAP sections (Names, Language, Constants, Variables, Tables, Strings, Booleans, Conditions, Ifs, Classes, Methods, Error Handling, Comments, Formatting, Testing)
- Identify violations with specific line references when available
- Provide actionable recommendations with code examples showing both the problem and the clean solution
- Prioritize issues by impact (critical, major, minor)
- 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
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.
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 First seen · 536 lines · 140 tokens per session scan A 533bdfd8a06c
clean-abap is a skill published in the GitHub repository Ciltress/sap-abap-mcp (3 stars, last pushed 6d ago), licensed MIT. It adds 140 tokens to every session and 3,596 once invoked, about $0.0006 per session on Opus 5.5. 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.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…