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-update-recordgit 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-update-record)<a href="https://agentmods.dev/skills/ilia-inovaflow/s4hana-create-record-skills/s4hana-update-record"><img src="https://agentmods.dev/badge/skills/ilia-inovaflow/s4hana-create-record-skills/s4hana-update-record/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-update-record"><img src="https://agentmods.dev/badge/skills/ilia-inovaflow/s4hana-create-record-skills/s4hana-update-record.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 | $0.00282 | $0.02593 |
| Opus 5.5 | $0.00113 | $0.01037 |
| Sonnet 5.5 | $0.00056 | $0.00519 |
| Haiku 4.5 | $0.00028 | $0.00259 |
Grade A, and why
s4hana-update-record scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. **If neither**: auto-create `./.env` from the bundled template (curl from `https://raw.githubusercontent.com/ilia-inovaflow/s4hana-create-record-skills/main/.env.example`), append `.env` to `.gitignore` if not already How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
s4hana-update-record
Generic update skill for SAP S/4HANA records. Verified pattern against <your-tenant>.s4hana.cloud.sap 2026-05-12 — 6 different entity types successfully PATCH'd; 2 confirmed entity-disabled; 1 "silent success" trap documented.
When to trigger
Verbs: update / change / edit / modify / patch / set / rename / adjust / correct / backdate / amend Objects: any existing S/4HANA record — PO, supplier, customer, BP, PIR, SES, product description, etc.
When NOT to trigger
- User wants to CREATE a record → use
s4hana-create-*skills - User wants to DELETE → Cloud Public blocks DELETE on most entities. Use block-and-rename (PATCH
BusinessPartnerIsBlocked=trueetc.) instead. - User wants to update Supplier Invoice or Material Document → those are entity-disabled (405). They need cancel-and-recreate (use the cancellation flow in the relevant create skill instead).
Hard rules (never violate)
- GET before PATCH, GET after PATCH. Always show user the BEFORE state, then PATCH, then VERIFY the change actually took effect with a fresh GET. Many fields return 204 "success" but don't actually update — only the post-PATCH GET reveals the truth.
- Confirm with user before PATCHing batches >3. Show the planned BEFORE/AFTER diff for the first record, get explicit confirmation, then proceed.
- If post-PATCH GET shows unchanged value, surface it as a "silent failure" — DON'T claim success.
- Never invent values. If the user says "set PO X date to Aug 2025", use a specific date they confirmed, not a random one.
- Scripts go in
mcp-server/src/sap/.tmp/<user>-<YYYYMMDD-HHMM>/update-<entity>/. Never commit, never modify.env.
Phase 0 — Setup check (MANDATORY, no exceptions)
Before any API call, before any tool use, do this check. Even if you already know credentials from earlier in the conversation — IGNORE that knowledge and re-check from scratch each invocation.
- Announce: tell the user "Checking for SAP credentials in
<current cwd>..." - Check ONLY these two sources:
- A
.envfile at./.env(in the current working directory — NOT parent dirs, NOT~/.env, NOT any memory file) - Shell-exported env vars:
SAP_HOSTANDSAP_AUTH_MODEboth present
- A
- If neither: auto-create
./.envfrom the bundled template (curl fromhttps://raw.githubusercontent.com/ilia-inovaflow/s4hana-create-record-skills/main/.env.example), append.envto.gitignoreif not already there, tell the user clearly what to fill in (auth mode + host + creds), and wait for them to say "ready" before making any API call. Never overwrite an existing.env. - If credentials are present: report back to the user: "✓ Loaded credentials for
<host>in<auth-mode>mode. Proceeding with [task]."
What ships with it
4 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 · 152 lines · 282 tokens per session scan A b201503799fb
s4hana-update-record is a skill published in the GitHub repository ilia-inovaflow/s4hana-create-record-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 282 tokens to every session and 2,593 once invoked, about $0.0011 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). 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".