sap-ai-core

sap-ai-core is a skill for Claude Code, Codex from secondsky/sap-skills. It costs 152 tokens per session (3,128 once invoked), scanned A, original, GPL-3.0.

Development guidance for SAP AI Core and SAP AI Launchpad, services on SAP’s cloud platform for running enterprise AI and machine-learning work. It covers model deployment, AI workflows, retrieval-augmented generation (RAG), and machine-learning training pipelines.

In plain words
What is it for?
Use it to deploy generative AI models, build workflows with templates, filters, and grounding, create RAG applications, and manage training pipelines with Argo Workflows.
Why use it?
It helps developers work through the platform-specific steps for putting AI models and machine-learning processes into use. It also explains how to connect generated answers with information stored in vector databases.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the sap-ai-core plugin — 1 skill, 1 command shipped together

not rated 439repo +6 6d ago A scan Socket: passSnyk: warnSkillSpector: warn 152 tokens GPL-3.0

Good fit Use it to deploy generative AI models, build workflows with templates, filters, and grounding, create RAG applications, and manage training pipelines with Argo Workflows.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/secondsky/sap-skills/sap-ai-core
Install

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.

Any agent
npx skills add secondsky/sap-skills --skill sap-ai-core
Clone the repo
git clone --depth 1 https://github.com/secondsky/sap-skills

Made for: Claude Code, Codex.

Or install sap-ai-core, the plugin that ships this one along with the rest of its 1 skill, 1 command.

Wrote 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.

agentmods badge for sap-ai-core

README.md
[![agentmods](https://agentmods.dev/badge/skills/secondsky/sap-skills/sap-ai-core/github.svg)](https://agentmods.dev/skills/secondsky/sap-skills/sap-ai-core)
Your own site
<a href="https://agentmods.dev/skills/secondsky/sap-skills/sap-ai-core"><img src="https://agentmods.dev/badge/skills/secondsky/sap-skills/sap-ai-core/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.

agentmods 80×15 button for sap-ai-core

Your own site · 80×15
<a href="https://agentmods.dev/skills/secondsky/sap-skills/sap-ai-core"><img src="https://agentmods.dev/badge/skills/secondsky/sap-skills/sap-ai-core.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 152 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,128 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 3 Apr 2026
  • Snyk warn 3 Apr 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 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 Data Exfiltration · line 90
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 100
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00152 $0.03128
Opus 5 $0.00076 $0.01564
Sonnet 5 $0.00030 $0.00626
Haiku 4.5 $0.00015 $0.00313

Measured 10d ago against content hash 88357a4f6e03, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

sap-ai-core 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

AUTH_TOKEN=$(curl -s -X POST "$AUTH_URL/oauth/token" \
plugins/sap-ai-core/skills/sap-ai-core/SKILL.md · 292 lines

The source is not reproduced here

Licensed GPL-3.0

The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

Changes

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.

  1. 10d ago First seen · 292 lines · 152 tokens per session scan A 88357a4f6e03

Subscribe to this mod's changes

sap-ai-core is a skill published in the GitHub repository secondsky/sap-skills (439 stars, last pushed 6d ago), licensed GPL-3.0. It adds 152 tokens to every session and 3,128 once invoked, about $0.0008 per session on Opus 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 2026-08-30.

Related

Other skills, from other repositories

joule-strategy

You are a Joule and SAP AI strategy expert. Joule is SAP's generative AI copilot embedded across SAP applications. Your job is to help organizations plan, govern, and execute Joule adoption in a way that accelerates value without creating compliance risk, shadow AI behavior, or unrealistic expectations about what…

vigneshbarani24/sap-superpowers · 0 tokens

joule

Use when working with SAP Joule AI assistant — Joule capabilities and architecture, Joule in S/4HANA Cloud, Joule in SuccessFactors, Joule in Ariba, Joule in BTP, Joule extensibility, natural language transaction execution, or understanding how Joule and SAP Superpowers complement each other.

vigneshbarani24/sap-superpowers · 70 tokens

analytics

Use when working with SAP Analytics Cloud (SAC), embedded analytics in S/4HANA, CDS-based analytical views, KPI modeling, Fiori analytical apps, BW/4HANA, SAP Datasphere, planning models, or BI story design.

vigneshbarani24/sap-superpowers · 53 tokens

pipeline-architect

Designs and implements data pipelines: ETL/ELT, streaming, batch processing, schema migrations, and data warehouse architecture. Covers Kafka, Airflow, dbt, Spark, ClickHouse, BigQuery, Snowflake, Redis Streams, and more. Use this skill when the user asks about data pipelines, ETL jobs, data transformation, streaming…

mturac/hermes-supercode-skills · 148 tokens

prompt-forge

Engineers and optimizes prompts for LLMs: system prompts, few-shot examples, chain-of-thought structures, agent personas, and evaluation frameworks. Use this skill when the user wants to write or improve a system prompt, design few-shot examples, create an agent persona, optimize prompt performance, set up prompt…

mturac/hermes-supercode-skills · 129 tokens

ai-prompting-patterns

Use this skill when designing how an AI agent should communicate with developers — intent clarification, progress reporting, ambiguity handling, confirmation before irreversible actions, error communication, self-correction, task tracking, and plan mode. Also use when building agent UX or defining agent behavior…

jamestorrevillas/dev-skills · 92 tokens