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 efeumutaslan/SAP-SKILLS --skill sap-gui-scriptinggit clone --depth 1 https://github.com/efeumutaslan/SAP-SKILLSWrote 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/efeumutaslan/sap-skills/sap-gui-scripting)<a href="https://agentmods.dev/skills/efeumutaslan/sap-skills/sap-gui-scripting"><img src="https://agentmods.dev/badge/skills/efeumutaslan/sap-skills/sap-gui-scripting/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/efeumutaslan/sap-skills/sap-gui-scripting"><img src="https://agentmods.dev/badge/skills/efeumutaslan/sap-skills/sap-gui-scripting.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 | $0.00071 | $0.03029 |
| Opus 5 | $0.00036 | $0.01515 |
| Sonnet 5 | $0.00014 | $0.00606 |
| Haiku 4.5 | $0.00007 | $0.00303 |
Grade A, and why
sap-gui-scripting scanned grade A with 1 finding 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 9d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
subprocess.Popen([sap_logon]) How it starts
The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAP GUI Scripting & Automation
Related Skills
sap-build-process-automation— Desktop Agent uses GUI scripting under the hoodsap-testing-quality— Automated GUI testing with eCATT/CBTAsap-s4hana-extensibility— When to use API vs. GUI scripting
Quick Start
Prerequisites:
- Enable scripting on SAP server:
RZ11→ parametersapgui/user_scripting=TRUE - Enable on client: SAP GUI → Options → Accessibility & Scripting → Enable scripting
- Disable notification popups: uncheck "Notify when script attaches" and "Notify when script opens connection"
Record your first script:
- Open SAP GUI → transaction you want to automate
- Menu: Customize Local Layout (Alt+F12) → Script Recording and Playback
- Click Record, perform actions, click Stop
- Save as
.vbsfile — this is your starting template
Minimal VBScript — Run Transaction:
If Not IsObject(application) Then
Set SapGuiAuto = GetObject("SAPGUI")
Set application = SapGuiAuto.GetScriptingEngine
End If
Set connection = application.Children(0)
Set session = connection.Children(0)
session.findById("wnd[0]/tbar[0]/okcd").text = "/nMM03"
session.findById("wnd[0]").sendVKey 0
session.findById("wnd[0]/usr/ctxtRMMG1-MATNR").text = "MAT-001"
session.findById("wnd[0]").sendVKey 0
Core Concepts
Object Hierarchy
GuiApplication
└── GuiConnection (SAP system connection)
└── GuiSession (user session / window)
└── GuiFrameWindow (wnd[0], wnd[1]...)
├── GuiToolbar (tbar[0] = command, tbar[1] = app)
├── GuiUserArea (usr/)
│ ├── GuiTextField, GuiCTextField
│ ├── GuiComboBox, GuiCheckBox, GuiRadioButton
│ ├── GuiTableControl, GuiGridView (ALV)
│ ├── GuiTab, GuiTabStrip
│ └── GuiTree
├── GuiStatusbar (sbar/)
└── GuiTitlebar (titl/)
Element ID Pattern
Format: wnd[N]/area/type[row,col]
wnd[0]/tbar[0]/okcd— Command field (OKCode)wnd[0]/usr/ctxtFIELD-NAME— Context field (F4 help available)wnd[0]/usr/txtFIELD-NAME— Text input fieldwnd[0]/usr/chkFIELD-NAME— Checkboxwnd[0]/usr/radFIELD-NAME— Radio buttonwnd[0]/usr/btnBUTTON-NAME— Push buttonwnd[0]/usr/tblTABLE/ctxtFIELD[row,col]— Table cellwnd[0]/usr/cntlGRID/shellcont/shell— ALV Grid controlwnd[0]/sbar— Status bar (messages)
What ships with it
1 file 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.
- 9d ago First seen · 309 lines · 71 tokens per session scan A 549b8b81869a
sap-gui-scripting is a skill published in the GitHub repository efeumutaslan/SAP-SKILLS (5 stars, last pushed 5mo ago), licensed MIT. It adds 71 tokens to every session and 3,029 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
explore-ui
Standalone Phase 2 of SAP UI testing. Opens the target transaction in a real browser (SAP WebGUI) and explores it live to produce tests/ /test-cases/screens.md — the authoritative map of every on-screen control, its accessible name/label as Playwright will see it, and its initial state. This is about how the UI…
sap-testing
Entry point for the SAP UI test-automation environment. Explains project layout, the configured test folder, available tools, phase workflows, and bounded agent delegation. Use when the user asks about SAP UI testing, Playwright for SAP, writing tests for any ABAP report/transaction/process, generating test evidence…
sap-webgui
Authoritative SAP WebGUI behavior and locator guidance for live exploration and Playwright script generation. Covers iframes, accessible names, generated IDs, selection screens, dialogs, ALV grids, toolbars, uploads, themes, and known SapSession helper limitations. Load before explore-ui live exploration and before…
michel-ui-demo-recorder
Record polished UI demo videos and screenshots of a running web app using Playwright MCP — for client deliverables, release notes, feature walkthroughs, or bug repros. Produces an HD WebM video with chapter markers, a mandatory animated cursor overlay, and a mandatory subtitle bar that narrates each step (positioned…
ask-opencli
A helper for asking Grok or Gemini through OpenCLI, which uses an already signed-in Chrome browser session instead of a paid API.
sap-webgui-recording
Guides an agent in deciding when SAP WebGUI exploration needs a focused user recording, coaching the user through Playwright recording in Edge, and consuming the resulting reference file safely. Use when autonomous browser exploration cannot inspect a complex SAP control or when the user asks how to record a WebGUI…