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 PatrickGallucci/fabric-skills --skill fabric-data-agentgit clone --depth 1 https://github.com/PatrickGallucci/fabric-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/patrickgallucci/fabric-skills/fabric-data-agent)<a href="https://agentmods.dev/skills/patrickgallucci/fabric-skills/fabric-data-agent"><img src="https://agentmods.dev/badge/skills/patrickgallucci/fabric-skills/fabric-data-agent/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/patrickgallucci/fabric-skills/fabric-data-agent"><img src="https://agentmods.dev/badge/skills/patrickgallucci/fabric-skills/fabric-data-agent.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 | $0.00099 | $0.01279 |
| Opus 5 | $0.00049 | $0.00639 |
| Sonnet 5 | $0.00020 | $0.00256 |
| Haiku 4.5 | $0.00010 | $0.00128 |
Grade A, and why
fabric-data-agent 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 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.
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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Microsoft Fabric Data Agents
Build conversational AI experiences that let users ask questions in plain English against structured data in Microsoft Fabric. Fabric Data Agents translate natural language into SQL, DAX, or KQL queries, execute them securely under the caller's identity, and return data-driven answers.
When to Use This Skill
- Creating a new Fabric Data Agent from the portal or via REST API
- Configuring data sources (Lakehouse, Warehouse, Power BI Semantic Model, KQL Database, Ontology)
- Writing effective agent-level or data-source-level instructions
- Authoring example queries (few-shot examples) to improve NL2SQL/NL2DAX/NL2KQL accuracy
- Automating data agent provisioning with PowerShell and the Fabric REST API
- Integrating a published Fabric Data Agent with Azure AI Foundry agents
- Managing the Operations Agent definition (Configurations.json) programmatically
- Publishing, sharing, and versioning data agents
- remediate query generation, data source permissions, or tenant settings
Prerequisites
| Requirement | Details |
|---|---|
| Fabric capacity | Paid F2+ SKU, or Power BI Premium P1+ with Fabric enabled |
| Tenant settings | Fabric data agent, Cross-geo processing for AI, Cross-geo storing for AI all enabled |
| XMLA endpoints | Enabled if using Power BI Semantic Model data sources |
| Data source access | At least Read permission on target lakehouses, warehouses, semantic models, or KQL databases |
| PowerShell (automation) | PowerShell 7.4+, Az.Accounts module |
| Azure AI Foundry (integration) | Foundry Project endpoint, Fabric connection, model deployment |
What ships with it
8 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.
- LICENSE.txt 11 KB
- references/example-query-guide.md 4.4 KB
- references/foundry-integration.md 4.5 KB
- references/instruction-best-practices.md 4.6 KB
- references/operations-agent-schema.md 5.0 KB
- scripts/Invoke-FabricFoundryAgent.ps1 5.6 KB runs code
- scripts/New-FabricDataAgent.ps1 4.9 KB runs code
- templates/Configurations.json 1.3 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.
- 10d ago First seen · 84 lines · 99 tokens per session scan A 38d47d298ca1
fabric-data-agent is a skill published in the GitHub repository PatrickGallucci/fabric-skills (16 stars, last pushed 3mo ago), licensed MIT. It adds 99 tokens to every session and 1,279 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
data-integrity-post-normalize
Apply a composable pipeline of normalization operations to a string. Trim whitespace, fix encoding, normalize unicode, strip HTML, and more — in a single call.
multai
Intelligent Multi-AI Router & Orchestrator. Submits prompts to 7 AI platforms simultaneously (or sequentially in Cowork) and synthesizes results. Supports two runtimes automatically detected at startup: • Code tab (Mac): Playwright/Browser-Use engine — parallel, full-featured • Cowork tab (Linux sandbox)…
llm-council
Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict. Based on Karpathy's LLM Council methodology. MANDATORY TRIGGERS: 'council this', 'run the council', 'war room this', 'pressure-test this'…
umap-learn
Use UMAP-learn for nonlinear dimensionality reduction, 2D/3D embeddings, clustering preprocessing, supervised or semi-supervised UMAP, DensMAP, AlignedUMAP, and Parametric UMAP workflows.
optimize-for-gpu
GPU-accelerates scientific Python on NVIDIA hardware and verifies that the result is correct and faster. Use for CUDA/GPU optimization; CPU-bound NumPy, SciPy, pandas, scikit-learn, NetworkX, scikit-image, vector-search, image-processing, graph, simulation, or file-I/O workloads; CuPy, cuDF, cuML, cuGraph, cuVS…
arboreto
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for…