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 marcellourbani/vscode_abap_remote_fs --skill sap-webgui-recordinggit clone --depth 1 https://github.com/marcellourbani/vscode_abap_remote_fsWrote 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/marcellourbani/vscode_abap_remote_fs/sap-webgui-recording)<a href="https://agentmods.dev/skills/marcellourbani/vscode_abap_remote_fs/sap-webgui-recording"><img src="https://agentmods.dev/badge/skills/marcellourbani/vscode_abap_remote_fs/sap-webgui-recording/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/marcellourbani/vscode_abap_remote_fs/sap-webgui-recording"><img src="https://agentmods.dev/badge/skills/marcellourbani/vscode_abap_remote_fs/sap-webgui-recording.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 45 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00065 | $0.01004 |
| Opus 5 | $0.00032 | $0.00502 |
| Sonnet 5 | $0.00013 | $0.00201 |
| Haiku 4.5 | $0.00006 | $0.00100 |
Grade A, and why
sap-webgui-recording 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAP WebGUI Recording — User-Assisted Evidence
For bounded, self-contained support work, use sap-task-helper with explicit inputs, allowed writes, and an output contract.
How to use this skill
Use this workflow to decide whether user-assisted recording is necessary, coach the user, and consume the resulting evidence in the active phase:
- follow
explore-uifor exploration coverage and_screens.md; - follow
sap-webguito assess locator stability and interpret generated code; - follow
build-scriptsto translate evidence intoSapSessionspecs; - follow
run-scriptsto diagnose failures.
Recordings are reference evidence
The command ABAP FS: Record SAP WebGUI Flow writes:
<TEST_FOLDER>/recordings/<descriptive-name>.recording.ts
A recording is not a test case or production spec:
- never run it through
abapfs_run_playwright_tests; - never copy it verbatim into
test-scripts/; - never treat generated IDs, iframe names, or positions as approved locators;
- persist verified observations into
_screens.md; - keep it until the translated spec passes its first headed run, then offer to remove it if it is no longer referenced.
Decide who should explore
Explore autonomously first
Use the integrated browser when you can safely:
- open and snapshot the screen;
- read labels, roles, titles, initial values, and visible state;
- navigate a non-destructive path;
- inspect dialogs, toolbars, and ordinary tables;
- reproduce the path without business judgement.
Do not ask the user to record merely to offload normal exploration.
Ask for a focused recording
Escalate only when one or more apply:
- the integrated browser cannot reach or inspect the authenticated WebGUI frame;
- a complex control exposes no understandable labels or roles;
- the path depends on user-specific personalization or business knowledge;
- interaction sequencing cannot be inferred from snapshots, traces, or source;
- the interaction changes business data and the safe stopping point must be agreed with the user;
- run evidence is insufficient to explain a repeatable locator failure.
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.
- 10d ago First seen · 93 lines · 65 tokens per session scan A 76815045361c
sap-webgui-recording is a skill published in the GitHub repository marcellourbani/vscode_abap_remote_fs (388 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 1,004 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 2026-08-30.
Other skills, from other repositories
test-ui
Test the BrowserOS app extension UI by starting the dev environment and visually verifying changes via CDP. Covers the new tab page (left sidebar — Home, Scheduled Tasks, Settings, etc.) and the right side panel (chat interface). Use after making UI changes to apps/app/.
apify-cli
Patterns for invoking the Apify CLI (apify) from agents. Covers authentication, creating/running/pushing Actors, calling Actors in the cloud, and reading results from datasets and key-value stores.
ai-sdk
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI…
browseros-neo
The user's dedicated browser for agents — a real browser signed into their accounts, with live logins and a persistent profile. Use it for any task that touches a website or browser (open, read, act, fill, sign in, download, verify). The user installed it precisely so agents default here unprompted — over in-app…
zpa-application_segment-pra-onboard
End-to-end onboarding of a new Privileged Remote Access (PRA) application in Zscaler Private Access. Walks through the full dependency chain — App connector group, server group, segment group, PRA credential, PRA portal, PRA application segment with appsconfig (RDP/SSH targets), and access policy rule — for RDP and…
zpa-application_segment-ba-onboard
End-to-end onboarding of a new Browser Access (BA) application in Zscaler Private Access. Walks through the full dependency chain — App connector group, server group, segment group, BA TLS certificate, BA application segment with appsconfig, and access policy rule — for web apps that should be reachable through the…