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 agentmods add skills/marcellourbani/vscode_abap_remote_fs/multi-system-workflowsnpx skills add marcellourbani/vscode_abap_remote_fs --skill multi-system-workflowsgit 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/multi-system-workflows)<a href="https://agentmods.dev/skills/marcellourbani/vscode_abap_remote_fs/multi-system-workflows"><img src="https://agentmods.dev/badge/skills/marcellourbani/vscode_abap_remote_fs/multi-system-workflows.svg" alt="Measured on agentmods" 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 | $0.00062 | $0.00867 |
| Opus 5 | $0.00031 | $0.00434 |
| Sonnet 5 | $0.00012 | $0.00173 |
| Haiku 4.5 | $0.00006 | $0.00087 |
Grade A, and why
multi-system-workflows 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 6d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-System Workflows
Use this guidance alongside the active SAP Testing phase skill. This is not an eighth phase and does not add multi-system support inside one spec.
Current boundary
One Playwright spec runs against exactly one connectionId. Do not open a second SAP system
inside that spec, switch SAP_SYSTEM, or use Playwright projects as business-process stages.
The current abapfs_run_playwright_tests tool also has one global connectionId per invocation.
Represent one cross-system business scenario as linked stage cases/scripts, one per system:
TC-021— create PO onS4DEV100.TC-022— create appointment for that PO onEWMDEV100.
Record the relationship in each case's ## Notes for automation: a shared workflow name,
stage number, target connection, predecessor, values produced, and values consumed. Keep
normal TC-NNN filenames so index, data, verification, and evidence tooling continue to work.
Design rules
- Give each stage its own TC file, data spec when needed, script, verification, and evidence.
- Make the target connection explicit in Preconditions and Notes; never hardcode credentials.
- State the ordered dependency: producer before consumer. These stages are never one parallel batch.
- If a stage can be independently retried, define its idempotency/precondition behavior.
- Do not claim one logical aggregated PASS: today each stage has its own status. Report the workflow passed only after every stage and every post-test check passed.
Passing runtime values
Prepared inputs remain in each stage's normal per-system data.json. Do not overwrite or
repurpose it with values created during execution.
When a producer creates a key a later stage needs (PO number, delivery, appointment ID), use an explicit workflow JSON artifact under:
tests/<PROGRAM>/test-results/workflows/<workflow-name>/state.json
The producer writes only after SAP confirms success; write atomically (temporary file then rename). The consumer reads the named value and fails loudly when the file/key is missing. Never guess, rediscover, or silently substitute a different business object. Do not store credentials or session cookies there. Notes for automation must name every produced/consumed key and the JSON path.
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.
- 6d ago First seen · 84 lines · 62 tokens per session scan A fd2b33b45cd9
multi-system-workflows is a skill published in the GitHub repository marcellourbani/vscode_abap_remote_fs (388 stars, last pushed 4d ago), licensed MIT. It adds 62 tokens to every session and 867 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
sap-sac-test-automation
SAP Analytics Cloud (SAC) automated testing skill for designing capability-gated browser discovery and deterministic Playwright test suites for SAC stories, dashboards, reports, planning workflows, comments, permissions, visual regression, and reusable QA automation. This skill should be used when building SAC…
sap-tcd-chain
Drives a complete headless O2C business-document chain — sales order → outbound delivery → goods issue → billing — over RFC BAPIs, so regression testing gets whole document flows, not isolated documents. Each step is created via its SAP write BAPI, committed (WAIT='X'), and VBFA-verified before the next step (VBTYPN…
sap-test-replay
Turns a recorded business scenario into a re-runnable pass/fail GUI regression test — the eCATT/CBTA equivalent the suite lacks — so a regression cycle stops meaning "re-test transactions by hand and paste screenshots into Word". A scaffold-recorded linear scenario (control IDs + screen identity + popup transitions…
sap-user-guide
Turns a recorded transaction walkthrough into an end-user training guide + UAT script — the unfunded rollout mandate everyone hand-makes from screenshots pasted into Word — composed from ground truth the suite already owns: /sap-gui-probe drives/records the transaction step by step with full screen identity, DDIC…
sap-fiori-testing
SAP Fiori/UI5 testing, accessibility, and modern UI skill. Use when writing wdi5 E2E tests, OPA5 integration tests, implementing WCAG 2.1 accessibility, using UI5 Web Components, or migrating UI5 to TypeScript. If the user mentions wdi5, OPA5, Fiori test, UI5 accessibility, WCAG, or UI5 TypeScript migration, use this…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.