sap-system-personality-report

sap-system-personality-report is a skill for Claude Code from marcellourbani/vscode_abap_remote_fs. It costs 82 tokens per session (3,371 once invoked), scanned A, original, MIT.

A process for creating a detailed report about an SAP system's custom code, business areas, development activity, health indicators, and package structure. It presents results in tables with a written summary.

In plain words
What is it for?
Use it to characterize an SAP system, collect object counts and other metrics, inspect custom code, and produce a human-readable system personality report.
Why use it?
It helps turn system database data into an understandable overview of what the SAP system contains and how it is being used.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Good fit Use it to characterize an SAP system, collect object counts and other metrics, inspect custom code, and produce a human-readable system personality report.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/marcellourbani/vscode_abap_remote_fs/sap-system-personality-report
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 marcellourbani/vscode_abap_remote_fs --skill sap-system-personality-report
Clone the repo
git clone --depth 1 https://github.com/marcellourbani/vscode_abap_remote_fs

Made for: Claude Code.

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 sap-system-personality-report

README.md
[![agentmods](https://agentmods.dev/badge/skills/marcellourbani/vscode_abap_remote_fs/sap-system-personality-report/github.svg)](https://agentmods.dev/skills/marcellourbani/vscode_abap_remote_fs/sap-system-personality-report)
Your own site
<a href="https://agentmods.dev/skills/marcellourbani/vscode_abap_remote_fs/sap-system-personality-report"><img src="https://agentmods.dev/badge/skills/marcellourbani/vscode_abap_remote_fs/sap-system-personality-report/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 sap-system-personality-report

Your own site · 80×15
<a href="https://agentmods.dev/skills/marcellourbani/vscode_abap_remote_fs/sap-system-personality-report"><img src="https://agentmods.dev/badge/skills/marcellourbani/vscode_abap_remote_fs/sap-system-personality-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,371 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00082 $0.03371
Opus 5 $0.00041 $0.01685
Sonnet 5 $0.00016 $0.00674
Haiku 4.5 $0.00008 $0.00337

Measured 12d ago against content hash 3a88edd4af31, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

sap-system-personality-report 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 12d 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.

client/media/skills/sap-system-personality-report/SKILL.md · 342 lines

How it starts

The opening of the file, as written. The whole thing — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SAP System Personality Report

Generate a rich, structured report that characterizes an SAP system in human-readable terms. You will collect data by running SQL queries, then present the results in a webview table AND provide a narrative AI summary.

CRITICAL: Before running ANY query, call abapfs_get_sql_syntax to understand ABAP SQL syntax. Use get_object_lines to check table structures before running SQL queries.

CRITICAL: All queries must use ABAP SQL syntax (e.g., ORDER BY field DESCENDING not DESC). Use the abapfs_run_sql_query tool with displayMode: "internal" to collect data, then assemble final results into a displayMode: "ui" call.


Step 1: System Identity

Get basic system information first. Use the abapfs_get_sap_system_info tool — it returns system type (S/4HANA vs ECC), release, timezone, and client details. No SQL needed for this step.


Step 2: Custom Code Landscape — Object Counts

Run these queries to count custom objects. Use displayMode: "internal" with rowRange: {start: 0, end: 5} since we only need counts.

Run all of these in parallel (they are independent):

Classes

SELECT COUNT(*) AS CNT FROM SEOCLASS WHERE CLSNAME LIKE 'Z%' OR CLSNAME LIKE 'Y%'

Interfaces

NOTE: The SEOINTERF table does NOT exist in S/4HANA. Use TADIR instead:

SELECT COUNT(*) AS CNT FROM TADIR WHERE PGMID = 'R3TR' AND OBJECT = 'INTF' AND OBJ_NAME LIKE 'Z%'

Then separately for Y:

SELECT COUNT(*) AS CNT FROM TADIR WHERE PGMID = 'R3TR' AND OBJECT = 'INTF' AND OBJ_NAME LIKE 'Y%'

Sum both counts.

Programs/Reports (by type)

CRITICAL: The TRDIR table contains ALL program types (reports, includes, class pools, etc.). Using a raw count is very misleading since includes (SUBC='I') dominate the count. Always break down by SUBC field:

SELECT SUBC, COUNT(*) AS CNT FROM TRDIR WHERE NAME LIKE 'Z%' OR NAME LIKE 'Y%' GROUP BY SUBC ORDER BY CNT DESCENDING

SUBC values: '1'=Executable Reports, 'I'=Includes, 'M'=Module Pools, 'S'=Subroutine Pools, 'K'=Class Pools, 'J'=Interface Pools, 'X'=XSLT Programs.

Read the full file on GitHub · 342 lines

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. 12d ago First seen · 342 lines · 82 tokens per session scan A 3a88edd4af31

Subscribe to this mod's changes

sap-system-personality-report is a skill published in the GitHub repository marcellourbani/vscode_abap_remote_fs (389 stars, last pushed 2d ago), licensed MIT. It adds 82 tokens to every session and 3,371 once invoked, about $0.0004 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 2026-08-30.