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 design-casesgit 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/design-cases)<a href="https://agentmods.dev/skills/marcellourbani/vscode_abap_remote_fs/design-cases"><img src="https://agentmods.dev/badge/skills/marcellourbani/vscode_abap_remote_fs/design-cases/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/design-cases"><img src="https://agentmods.dev/badge/skills/marcellourbani/vscode_abap_remote_fs/design-cases.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 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 62 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 64 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 67 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 Excessive Agency · line 212 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.
- medium Excessive Agency · line 279 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 | $0.00133 | $0.07319 |
| Opus 5 | $0.00067 | $0.03660 |
| Sonnet 5 | $0.00027 | $0.01464 |
| Haiku 4.5 | $0.00013 | $0.00732 |
Grade A, and why
design-cases 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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Cases — Phase 3 (of 7)
If one business scenario has ordered stages on different SAP connections, load and follow
multi-system-workflows alongside this skill. Split it into linked TC-NNN stage cases;
never put multiple systems inside one case script.
Phase order: analyze-and-plan (1) → explore-ui (2) → design-cases (3) → define-data (4) → prepare-data (5) → build-scripts (6) → run-scripts (7).
This phase produces TC-XXX.md files plus the rebuilt _index.md/_index.docx. It does NOT author .data.md files (Phase 4) and does NOT write specs (Phase 6). Each TC-XXX.md still DECLARES dataRequired: yes|no; the sidecar itself is written in Phase 4.
For bounded, self-contained support work, use sap-task-helper with explicit inputs, allowed writes, and an output contract. Never delegate the whole phase.
Non-negotiable execution gate
abapfs_build_test_index is GATED: it refuses to build unless you pass reviewerConfirmation certifying the sap-test-plan-reviewer agent already returned PASS. You cannot produce the index — and therefore cannot hand off — without the reviewer actually running. Downstream phases and abapfs_run_playwright_tests reject cases whose plan was never reviewed.
Why
The test case is the contract for everything after it: Phase 6 writes exactly what the case says, and Phase 7 proves exactly what the case claims. A case that buckets three validations into one, omits the overlapping-range scenario, or claims "records inserted correctly" without a verification step is a coverage hole dressed up as coverage. Because there are many cases to write, the temptation is to skim — which is precisely why this is its own phase and why an independent reviewer gates it. Write each case as if it is the only defence against a million-dollar defect, because it is.
Tool availability (read this if a tool seems missing)
Naming: when these docs say call X, X is a tool (you invoke it and get a result); delegate to / invoke X is an agent (a subagent you launch); load / follow X is a skill (a procedure you read). A name without a verb: see the overview's "Skills, tools, and agents" list.
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 · 285 lines · 133 tokens per session scan A 5f92f3fe6a21
design-cases is a skill published in the GitHub repository marcellourbani/vscode_abap_remote_fs (388 stars, last pushed today), licensed MIT. It adds 133 tokens to every session and 7,319 once invoked, about $0.0007 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
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
Accumulated project memory: verified gotchas and prior findings for oh-my-posh work. Consult BEFORE touching shell integration scripts (zsh, pwsh, fish, bash, cmd/Clink), terminal or pty behavior, WSL-based shell testing, or internals (cache, segments, streaming, serve daemon). Read only the topic files relevant to…
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/.
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…
oss-write-tests
Write tests for untested OSS code as a standalone contribution. Identifies coverage gaps, studies the repo's test conventions, and guides the user through writing tests that match existing patterns. Use when contributing tests to an open source repo, looking for a low-risk first contribution, or improving test…