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 ilia-inovaflow/s4hana-create-record-skills --skill s4hana-comm-managementgit clone --depth 1 https://github.com/ilia-inovaflow/s4hana-create-record-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/ilia-inovaflow/s4hana-create-record-skills/s4hana-comm-management)<a href="https://agentmods.dev/skills/ilia-inovaflow/s4hana-create-record-skills/s4hana-comm-management"><img src="https://agentmods.dev/badge/skills/ilia-inovaflow/s4hana-create-record-skills/s4hana-comm-management/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/ilia-inovaflow/s4hana-create-record-skills/s4hana-comm-management"><img src="https://agentmods.dev/badge/skills/ilia-inovaflow/s4hana-create-record-skills/s4hana-comm-management.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 | $0.00248 | $0.02542 |
| Opus 5.5 | $0.00099 | $0.01017 |
| Sonnet 5.5 | $0.00050 | $0.00508 |
| Haiku 4.5 | $0.00025 | $0.00254 |
Grade A, and why
s4hana-comm-management 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
s4hana-comm-management
Create and wire up Communication Management objects on SAP S/4HANA Cloud Public Edition via API: Communication Users, Systems (incl. OAuth 2.0 inbound + redirect URI), and Arrangements — plus the admin work around inbound/outbound user assignment and OAuth client registration. Verified end-to-end 2026-06-24/26 on my438741-api.s4hana.cloud.sap: built 3 full environments (dev/staging/prod), each with a comm user, an OAuth2 system, and 9 arrangements, authenticating live.
This is a Cloud Public Edition capability (scenario SAP_COM_0A48, delivered 2408). On-prem / Private Edition does not expose these OData V4 services (returns 500) — there, comm objects are Fiori-only. Confirm the tenant before starting.
When to trigger
Verbs: create / set up / configure / register / clone / mirror / wire up / repoint Objects: communication user(s), communication system(s), communication arrangement(s), OAuth client, inbound/outbound user, redirect URI, integration setup, "admin work"
Do NOT use for business-record creation — defer to s4hana-create-invoice, s4hana-create-po, s4hana-create-supplier, or generic s4hana-create-record.
Hard rules
- Confirm the boundary first. Default to CREATE-only. Modifying/deleting existing comm objects (especially anything serving prod) is destructive — get explicit authorization and sequence for zero-downtime. The harness may block writes that look like "modify/delete" until the user authorizes.
- Idempotent. GET-before-create on every object (filter by
ID/Name); skip if present, create if missing. Never overwrite blindly. - Never improvise DRF/replication values against the tenant. For 0008/0009 use the documented "inactive outbound services" trick (below), not guessed
OUTPUT_MODEvalues. - Bootstrap + auth. The comm user you authenticate as must be the inbound user of a
SAP_COM_0A48arrangement (set up once in Fiori "Maintain Communication Users" + "Communication Arrangements"). Comm users lock after a burst of failed logons — if you see repeated 401 "Logon failed" / "Anmeldung fehlgeschlagen", the account is likely locked; ask the user to unlock in Maintain Communication Users. Stop hammering it. - Stop and report on any ambiguous required field or unrecoverable error. Do not guess against the tenant.
What ships with it
3 files 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.
- 1mo ago First seen · 78 lines · 248 tokens per session scan A f87847850fac
s4hana-comm-management is a skill published in the GitHub repository ilia-inovaflow/s4hana-create-record-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 248 tokens to every session and 2,542 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
spine-design
Produce a system design doc — components, data flow, decisions made, tradeoffs, failure modes. Not a list of options. An actual design with calls made. Use when asked for "system design for", "architect this", "how should we build", or "design the backend".
warden-harden
Produce a hardening spec and implement it — auth patterns, security headers, rate limiting, input validation, secrets management, dependency hygiene. Use when asked to "harden this", "add security to this service", "what security do I need", or "secure this before launch".
cortex-integrate
Design and implement an AI feature integration — model selection, architecture pattern, system prompt, data flow, error handling, cost estimate. Use when asked to "add AI to this", "LLM integration", "add Claude/GPT", or "AI-powered feature".
spine-api
Design and spec an API — endpoints, request/response shapes, error codes, auth pattern, pagination. Applies Stripe's consistency principles. Use when asked to "design an API", "build API endpoints", "create REST API", or "API for this feature".
spine-perf
Find and fix performance bottlenecks — N+1 queries, missing indexes, sync bottlenecks, caching gaps. Use when asked "why is this slow", "performance issue", "optimize this endpoint", or "N+1 queries".
spine-review
API and backend code review — REST conventions, auth, validation, error handling, pagination, rate limiting, test coverage. Use when asked to "review this API", "code review", "review backend", or "pre-launch backend check".