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 helpers-referencegit 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/helpers-reference)<a href="https://agentmods.dev/skills/marcellourbani/vscode_abap_remote_fs/helpers-reference"><img src="https://agentmods.dev/badge/skills/marcellourbani/vscode_abap_remote_fs/helpers-reference/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/helpers-reference"><img src="https://agentmods.dev/badge/skills/marcellourbani/vscode_abap_remote_fs/helpers-reference.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, 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 Prompt Injection · line 40 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 44 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 45 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 46 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 47 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 107 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 119 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00073 | $0.03769 |
| Opus 5.5 | $0.00029 | $0.01508 |
| Sonnet 5.5 | $0.00015 | $0.00754 |
| Haiku 4.5 | $0.00007 | $0.00377 |
Grade A, and why
helpers-reference 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.
How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Helpers Reference
For bounded, self-contained support work, use sap-task-helper with explicit inputs, allowed writes, and an output contract.
Non-negotiable execution gate
Using a helper does not bypass the SAP Testing phase requirements. The abapfs_run_playwright_tests tool verifies required steps, artifacts, data caches, and script checks and will reject the run if any are missing, stale, incomplete, or unverified. A helper or escape-hatch workaround cannot bypass this validation.
Why
Helpers are load-bearing. Every test in this project depends on them. A hidden bug here — a silent-swallow wait, a locator that matches the wrong element, a popup guard that dismisses a real error — makes hundreds of tests lie in unison. Treat this API like any other production dependency you can't patch yourself: understand it precisely, use it correctly, and know exactly what to do when it doesn't cover something.
Read this before assuming a capability is missing. The runtime is deliberately generic and fairly complete; most "I need a new helper" instincts are actually "I haven't found the right existing one yet."
Use this reference for runtime API contracts. For WebGUI rendering behavior, locator stability, accessible names, iframes, themes, dialogs, ALV, and uploads, load sap-webgui.
Where this actually lives (important — read this first)
Unlike test artifacts, the runtime is NOT a file in the configured test folder or workspace. Only its @sap-testing/runtime API and type declarations are exposed; runtime implementation files cannot be read or edited from the workspace. See "When a capability is genuinely missing" below.
What you CAN see: the type declarations surfaced via @sap-testing/runtime (real IntelliSense/type-checking while you write a spec), and the method reference below (this file + build-scripts §2). Between the two, you should never need to guess a method's existence or signature.
Standalone context rule
For a general API question, answer directly from this reference. If the user wants you to inspect, write, or fix a real test artifact, first complete the standalone bootstrap in the relevant phase workflow:
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 · 191 lines · 73 tokens per session scan A f4cd5aafb2f8
helpers-reference is a skill published in the GitHub repository marcellourbani/vscode_abap_remote_fs (402 stars, last pushed 3d ago), licensed MIT. It adds 73 tokens to every session and 3,769 once invoked, about $0.0003 per session on Opus 5.5. 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
implement-universal
Harness-agnostic version of /implement. Drives a single workshop ticket through the SWE→Tester loop in ONE conversation, with the role prompts bundled as agents/software-engineer.md and agents/tester.md instead of being launched as subagents. Resolves the ticket from implementyourself/tasks/, creates an…
author-test
Generate a test given sample. Parameters: C# SDK repository root; Package name: one of Azure.AI.Projects, Azure.AI.Projects.Agents or Azure.AI.Extensions.OpenAI; the sample to use as a starting point for the test.
project-knowledge
Verified, actionable gotchas for oh-my-posh. Read the matching topic file BEFORE changing shell integration scripts (pwsh, zsh, bash, fish, cmd/Clink, nu, elvish, xonsh), terminal or pty behavior, WSL or e2e shell tests, Go internals (cache, segments, streaming, serve daemon, template rendering, output sanitization)…
abap-unit-testing
Help with ABAP Unit testing including test class setup, assertions, test doubles, mocking frameworks, dependency injection, CDS test environments, SQL test environments, RAP BO test doubles, and test fixtures. Use when users ask about ABAP unit tests, test classes, test methods, CLABAPUNITASSERT, test doubles…
transport-release-gate
Run a quality gate over an SAP transport request before it is released — collect the TR's objects, check for inactive objects and foreign locks, run syntax checks, ATC, and unit tests, then produce a structured go/no-go report. Use whenever the user wants to release a transport, asks "is this TR safe to release?"…
ui-visual-regression
Automates visual regression testing for DB Console UI changes. Compares screenshots and network requests between the current branch and its merge base using roachprod, playwright-cli, and ImageMagick. Use when the user wants to verify UI changes haven't introduced visual or behavioral regressions.