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 efeumutaslan/SAP-SKILLS --skill sap-business-ai-joulegit clone --depth 1 https://github.com/efeumutaslan/SAP-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/efeumutaslan/sap-skills/sap-business-ai-joule)<a href="https://agentmods.dev/skills/efeumutaslan/sap-skills/sap-business-ai-joule"><img src="https://agentmods.dev/badge/skills/efeumutaslan/sap-skills/sap-business-ai-joule/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/efeumutaslan/sap-skills/sap-business-ai-joule"><img src="https://agentmods.dev/badge/skills/efeumutaslan/sap-skills/sap-business-ai-joule.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 | $0.00088 | $0.02479 |
| Opus 5 | $0.00044 | $0.01239 |
| Sonnet 5 | $0.00018 | $0.00496 |
| Haiku 4.5 | $0.00009 | $0.00248 |
Grade A, and why
sap-business-ai-joule 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 12d 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAP Business AI & Joule Development
Related Skills
sap-hana-cloud— Vector engine for embeddings, HANA Cloud as knowledge storesap-rap-comprehensive— RAP-based data access for grounding AI with SAP datasap-cap-advanced— CAP MCP plugin for AI-assisted developmentsap-build-apps— AI-powered low-code app generationsap-integration-suite-advanced— AI-assisted mapping in Integration Advisor
Quick Start
Choose your AI scenario:
| Scenario | Service | Entry Point |
|---|---|---|
| Custom ML model training/serving | AI Core | AI Launchpad → ML Operations |
| LLM orchestration (chat, completion) | Generative AI Hub | AI Core API / orchestration |
| Embed AI in SAP standard apps | Joule | Extension Center / Joule Studio |
| RAG with SAP data | GenAI Hub + HANA Vector | Orchestration service |
| Document extraction | Document Information Extraction | BTP service instance |
Minimal GenAI Hub call (Python):
from gen_ai_hub.proxy.core.proxy_clients import get_proxy_client
from gen_ai_hub.proxy.langchain import ChatOpenAI
proxy_client = get_proxy_client('gen-ai-hub')
llm = ChatOpenAI(
proxy_model_name='gpt-4o',
proxy_client=proxy_client,
temperature=0.0
)
response = llm.invoke("Summarize SAP S/4HANA extensibility options")
print(response.content)
Core Concepts
SAP AI Core Architecture
- Resource groups: Isolated execution environments (multi-tenant)
- Configurations: Define which model/pipeline + parameters to use
- Deployments: Running model inference endpoints
- Executions: One-time training or batch jobs
- Artifacts: Models, datasets registered in AI Core
Generative AI Hub
- Proxy access: Unified API for multiple LLM providers (OpenAI, Azure OpenAI, Anthropic, Google, AWS Bedrock)
- Orchestration service: Chain LLM calls with grounding, content filtering, templating
- Prompt registry: Version-controlled prompt templates
- Content filtering: Input/output moderation (hate, self-harm, sexual, violence)
What ships with it
1 file 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.
- 12d ago First seen · 263 lines · 88 tokens per session scan A d826ec506822
sap-business-ai-joule is a skill published in the GitHub repository efeumutaslan/SAP-SKILLS (5 stars, last pushed 5mo ago), licensed MIT. It adds 88 tokens to every session and 2,479 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
x-bug2rag
A knowledge-capture tool that turns reusable bug explanations into a local RAG collection, meaning a searchable store of text that an agent can retrieve later. It records the trigger, incorrect implementation, correct implementation, and observable difference.
x-dev-rag-call
A local semantic search tool that finds relevant passages in specified Markdown or text files. It uses an embedding model, which represents meaning as numbers, to return the closest passages for a question or plan.
ai-agent-rag-governance
Use this capability for AI features, RAG, citations, model-agnostic prompts, evals, hallucination reduction, prompt injection, tool use, agent sandboxes, policy gates, audit trails, autonomy levels, human approval, and AI-assisted coding governance.
Cursor rules for Next
Cursor rules for Next.js development with Tailwind CSS and TypeScript integration.
chroma-hybrid-search
Local hybrid retrieval (BM25 + ChromaDB vector + BGE-Reranker) over /.deep-memory hot and cold stores. Use when high-accuracy code/solution retrieval is needed and hallucination must be minimized. Typically invoked by deep-memory.
context-management
Strategies for managing AI agent context windows including optimization, summarization, retrieval-augmented generation, progressive disclosure, and pruning. Use when the user is hitting context limits, building long-running agents, implementing RAG, optimizing token usage, or designing systems that need to manage…