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/mariodefelipe/sap-bdc-plugin/sap-databricksnpx skills add MarioDeFelipe/sap-bdc-plugin --skill sap-databricksgit clone --depth 1 https://github.com/MarioDeFelipe/sap-bdc-pluginWrote 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/mariodefelipe/sap-bdc-plugin/sap-databricks)<a href="https://agentmods.dev/skills/mariodefelipe/sap-bdc-plugin/sap-databricks"><img src="https://agentmods.dev/badge/skills/mariodefelipe/sap-bdc-plugin/sap-databricks.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 | $0.00179 | $0.05485 |
| Opus 5 | $0.00089 | $0.02743 |
| Sonnet 5 | $0.00036 | $0.01097 |
| Haiku 4.5 | $0.00018 | $0.00549 |
Grade A, and why
sap-databricks 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 5d 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 — 509 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAP Databricks
Overview
SAP Databricks is a special edition of Databricks available as an application within SAP Business Data Cloud. It provides advanced AI and analytics capabilities fully integrated with your SAP landscape. Key benefits include pre-configured Delta Sharing access to BDC data products without replication, ability to combine SAP data with external data and publish results back to BDC, fully managed serverless compute and storage, and instant provisioning from SAP for Me with integrated SSO.
Key use cases: automated forecasting (time-series with automatic algorithm/hyperparameter selection), fine-tuning LLMs with your data, exploratory data analysis with collaborative multi-language notebooks, business intelligence with SQL editor and visualizations.
Supported regions: AWS (ap-northeast-1, ap-southeast-1, ap-southeast-2, ca-central-1, eu-central-1, us-east-1), GCP (asia-south1, europe-west3, us-central1), Azure (eastus, westeurope, westus2). Accounts can only deploy workspaces in a single region.
Setup & Accounts
Provisioning from SAP for Me
- Follow SAP documentation to provision SAP Databricks from the SAP for Me portal.
- Verify email and agree to terms in the Databricks sign-up flow.
- The first user added becomes the initial account admin and receives an email when ready.
- A first workspace is automatically created.
Initial Configuration
- (Optional) Configure network settings for enhanced security.
- Add users and groups manually or via SAP Cloud Identity Service Identity Provisioning (SCIM integration).
- Users log in at
login.databricks.comwith SSO credentials.
Creating Additional Workspaces
From the account console Workspaces tab:
- Click Create workspace.
- Enter workspace name and select region.
- Click Create.
- Assign users/groups permissions on the Permissions tab using Add permissions.
Note: Accounts can only deploy workspaces in a single region.
Admin Roles & Responsibilities
What ships with it
15 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.
- references/sapDatabricks.pdf 1968 KB
- references/SAPDatabricks/AI and machine learning _ SAP Databricks.pdf 179 KB
- references/SAPDatabricks/Attribute usage with serverless budget policies _ SAP Databricks.pdf 205 KB
- references/SAPDatabricks/Connect to external data sources _ SAP Databricks.pdf 122 KB
- references/SAPDatabricks/Data analysis with notebooks _ SAP Databricks.pdf 182 KB
- references/SAPDatabricks/Identity management and permissions _ SAP Databricks.pdf 150 KB
- references/SAPDatabricks/Networking and security _ SAP Databricks.pdf 125 KB
- references/SAPDatabricks/Publish data from SAP Databricks to SAP BDC _ SAP Databricks.pdf 118 KB
- references/SAPDatabricks/SAP Databricks admin best practices _ SAP Databricks.pdf 163 KB
- references/SAPDatabricks/SAP Databricks admin guide _ SAP Databricks.pdf 142 KB
- references/SAPDatabricks/SAP Databricks API reference _ SAP Databricks.pdf 501 KB
- references/SAPDatabricks/SAP Databricks documentation _ SAP Databricks.pdf 284 KB
- references/SAPDatabricks/Set up your SAP Databricks account _ SAP Databricks.pdf 146 KB
- references/SAPDatabricks/Share SAP data into SAP Databricks _ SAP Databricks.pdf 226 KB
- references/SAPDatabricks/View and query the billing logs _ SAP Databricks.pdf 473 KB
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.
- 5d ago First seen · 509 lines · 179 tokens per session scan A 949dd9f0d083
sap-databricks is a skill published in the GitHub repository MarioDeFelipe/sap-bdc-plugin (9 stars, last pushed 4mo ago), licensed MIT. It adds 179 tokens to every session and 5,485 once invoked, about $0.0009 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
tensorrt-llm
High-throughput LLM inference on NVIDIA GPUs.
google-cloud-solution-guided-gke-ai-migration
Guides the migration of existing AI workloads (Cloud Run, Gemini API, Gemini Enterprise Agent Platform) to self-hosted GKE inference using gcloud and kubectl. Use when the user has an existing AI inference workload (on Cloud Run, the Gemini API, Gemini Enterprise Agent Platform, or a custom VM) and wants to move it to…
agent-platform-tuning
Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to endpoints (use agent-platform-deploy), or managing serving endpoints (use agent-platform-endpoint-management).
gke-inference
Deploys and optimizes AI/ML inference workloads on GKE, using GPUs, TPUs, and model servers. Use when deploying GKE inference servers, configuring GKE GPU resources for inference, or deploying LLMs on GKE. Don't use for generic batch jobs or HPC task queues (use gke-batch-hpc instead).
agent-platform-endpoint-management
Manages Agent Platform serving endpoints. Use when you need to create, list, describe, update, or delete serving endpoints for model deployment on Agent Platform. Also use when troubleshooting endpoint permission, quota, or resource busy errors. Don't use for deploying models to endpoints or for running model…
modal
Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs. Use when deploying or serving AI/ML models, running GPU-accelerated workloads (training, fine-tuning, inference), serving web endpoints, scheduling batch jobs, or scaling Python code to cloud containers with the Modal SDK.