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 wardawgmalvicious/agent-config --skill fabric-ai-functionsgit clone --depth 1 https://github.com/wardawgmalvicious/agent-configWrote 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/wardawgmalvicious/agent-config/fabric-ai-functions)<a href="https://agentmods.dev/skills/wardawgmalvicious/agent-config/fabric-ai-functions"><img src="https://agentmods.dev/badge/skills/wardawgmalvicious/agent-config/fabric-ai-functions/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/wardawgmalvicious/agent-config/fabric-ai-functions"><img src="https://agentmods.dev/badge/skills/wardawgmalvicious/agent-config/fabric-ai-functions.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 | $0.00284 | $0.03975 |
| Opus 5 | $0.00142 | $0.01988 |
| Sonnet 5 | $0.00057 | $0.00795 |
| Haiku 4.5 | $0.00028 | $0.00398 |
Grade A, and why
fabric-ai-functions 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 yesterday.
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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fabric AI Functions
One-line, LLM-powered transformations applied to whole pandas or PySpark DataFrames in Fabric notebooks. Fabric handles the model endpoint, auth, request orchestration, batching, and retries — you call a DataFrame method and get an enriched column back. Nine prebuilt functions cover sentiment, classification, extraction, embeddings, grammar, custom prompts, similarity, summarization, and translation.
When to use vs not
Use AI Functions to enrich, classify, extract, summarize, translate, or embed tabular data at scale — thousands to millions of rows — with minimal code, letting Fabric manage concurrency (200 rows in parallel by default) and the built-in endpoint. This is the fastest path to apply an LLM across a column.
Skip them when you need low-level control over a single prompt/response, custom orchestration, function-calling loops, or a conversational agent — use the Azure OpenAI Python SDK or SynapseML instead. For a governed natural-language-to-data experience over your semantic models/lakehouses, that's a Data Agent (fabric-data-agent), not AI Functions.
Prerequisites
-
Paid capacity — F2 or higher, or any P edition. Not available on trial/Free.
-
Fabric Runtime 1.3+ — earlier runtimes can't run AI Functions. The
+is upstream's own wording and it does cover Runtime 2.0 (GA Aug 2026 — Spark 4.1, Delta Lake 4.2, Python 3.13), which becomes the default for new workspaces and environment items around late September 2026. One catch comes with it: pandas AI Functions on Runtime 2.0 need a temporary compatibility patch, because 2.0 shipsnest_asyncio2rather thannest_asyncio.# Runtime 2.0 only — temporary, per upstream; PySpark AI Functions need nothing. %pip install -q nest_asyncio 2>/dev/null -
Tenant switch — an admin must enable Copilot and other features powered by Azure OpenAI. Depending on region you may also need the cross-geo processing tenant setting (the built-in endpoint isn't in every region).
-
Prompts, input data, and outputs are not logged or stored by AI Functions.
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.
- yesterday Changed d00e3cdfdddc
- 7d ago Changed · +3 lines 97d834991f4c
- 11d ago First seen · 204 lines · 284 tokens per session scan A 00ab8315ebe7
fabric-ai-functions is a skill published in the GitHub repository wardawgmalvicious/agent-config (0 stars, last pushed today), licensed MIT. It adds 284 tokens to every session and 3,975 once invoked, about $0.0014 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
vendor-prompting
ANALYSIS SKILL — Audit-grade reference for Anthropic Claude and OpenAI GPT-5.6 prompting best practices. WHEN: "claude prompting", "gpt-5.6 prompting", "audit agent", "review prompt", "vendor best practices", "anthropic best practices", "openai prompting". DO NOT USE FOR: routine prompt edits where rules are already…
deploy-model
Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version/SKU/capacity/RAI policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy gpt, create deployment, model deployment, deploy openai…
azure-kusto
ANALYSIS SKILL — Query and analyze data in Azure Data Explorer (Kusto/ADX) using KQL. WHEN: "KQL queries", "Kusto database queries", "Azure Data Explorer", "ADX clusters", "time series data", "IoT telemetry", "anomaly detection". DO NOT USE FOR: App Insights / Log Analytics troubleshooting (azure-diagnostics), cost…
capacity
Discovers available Azure OpenAI model capacity across regions and projects. Analyzes quota limits, compares availability, and recommends optimal deployment locations based on capacity requirements. USE FOR: find capacity, check quota, where can I deploy, capacity discovery, best region for capacity, multi-project…
azure-ai
Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech.
azure-ai-openai-dotnet
Azure OpenAI SDK for .NET. Client library for Azure OpenAI and OpenAI services. Use for chat completions, embeddings, image generation, audio transcription, and assistants. Triggers: "Azure OpenAI", "AzureOpenAIClient", "ChatClient", "chat completions .NET", "GPT-4", "embeddings", "DALL-E", "Whisper", "OpenAI .NET".