agentmods.dev

Speech-To-Text-With-Databricks: Skill for Claude Code

.claude/skills/databricks-model-serving/SKILL.md

databricks-model-serving is a skill for Claude Code from alessandro9110/Speech-To-Text-With-Databricks. It costs 81 tokens per session (2,849 once invoked), scanned A, original, MIT.

A guide for putting machine-learning models and AI agents behind Databricks REST API endpoints. A REST API lets other programs send requests to the deployed model and receive results.

In plain words
What is it for?
Use it to deploy MLflow models or AI agents, connect them to tools such as Unity Catalog Functions or Vector Search, query endpoints, and check endpoint status.
Why use it?
It explains how to move a model or agent from code into a callable service and how to check whether that service is available. It covers traditional models, custom Python models, and conversational agents.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Codex.

This is alessandro9110/Speech-To-Text-With-Databricks's own configuration. It tells Claude Code how to work on Speech-To-Text-With-Databricks itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Speech-To-Text-With-Databricks configures →

not rated 4repo 8mo ago A scan 81 tokens original MIT
View source ↗ alessandro9110/Speech-To-Text-With-Databricks
Reuse

Borrowing it

Nothing to install: this file belongs to alessandro9110/Speech-To-Text-With-Databricks. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/alessandro9110/Speech-To-Text-With-Databricks/main/.claude/skills/databricks-model-serving/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/alessandro9110/Speech-To-Text-With-Databricks

Made for: Claude Code.

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 databricks-model-serving

README.md
[![agentmods](https://agentmods.dev/badge/skills/alessandro9110/speech-to-text-with-databricks/databricks-model-serving/github.svg)](https://agentmods.dev/skills/alessandro9110/speech-to-text-with-databricks/databricks-model-serving)
Your own site
<a href="https://agentmods.dev/skills/alessandro9110/speech-to-text-with-databricks/databricks-model-serving"><img src="https://agentmods.dev/badge/skills/alessandro9110/speech-to-text-with-databricks/databricks-model-serving/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 databricks-model-serving

Your own site · 80×15
<a href="https://agentmods.dev/skills/alessandro9110/speech-to-text-with-databricks/databricks-model-serving"><img src="https://agentmods.dev/badge/skills/alessandro9110/speech-to-text-with-databricks/databricks-model-serving.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,849 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original 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 $0.00081 $0.02849
Opus 5.5 $0.00032 $0.01140
Sonnet 5.5 $0.00016 $0.00570
Haiku 4.5 $0.00008 $0.00285

Measured 1mo ago against content hash cc0e55362999, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

databricks-model-serving 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 1mo 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.

.claude/skills/databricks-model-serving/SKILL.md · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Databricks Model Serving

Deploy MLflow models and AI agents to scalable REST API endpoints.

Quick Decision: What Are You Deploying?

Model Type Pattern Reference
Traditional ML (sklearn, xgboost) mlflow.sklearn.autolog() 1-classical-ml.md
Custom Python model mlflow.pyfunc.PythonModel 2-custom-pyfunc.md
GenAI Agent (LangGraph, tool-calling) ResponsesAgent 3-genai-agents.md

Prerequisites

  • DBR 16.1+ recommended (pre-installed GenAI packages)
  • Unity Catalog enabled workspace
  • Model Serving enabled

Foundation Model API Endpoints

ALWAYS use exact endpoint names from this table. NEVER guess or abbreviate.

Chat / Instruct Models

Endpoint Name Provider Notes
databricks-gpt-5-2 OpenAI Latest GPT, 400K context
databricks-gpt-5-1 OpenAI Instant + Thinking modes
databricks-gpt-5-1-codex-max OpenAI Code-specialized (high perf)
databricks-gpt-5-1-codex-mini OpenAI Code-specialized (cost-opt)
databricks-gpt-5 OpenAI 400K context, reasoning
databricks-gpt-5-mini OpenAI Cost-optimized reasoning
databricks-gpt-5-nano OpenAI High-throughput, lightweight
databricks-gpt-oss-120b OpenAI Open-weight, 128K context
databricks-gpt-oss-20b OpenAI Lightweight open-weight
databricks-claude-opus-4-6 Anthropic Most capable, 1M context
databricks-claude-sonnet-4-6 Anthropic Hybrid reasoning
databricks-claude-sonnet-4-5 Anthropic Hybrid reasoning
databricks-claude-opus-4-5 Anthropic Deep analysis, 200K context
databricks-claude-sonnet-4 Anthropic Hybrid reasoning
databricks-claude-opus-4-1 Anthropic 200K context, 32K output
databricks-claude-haiku-4-5 Anthropic Fastest, cost-effective
databricks-claude-3-7-sonnet Anthropic Retiring April 2026
databricks-meta-llama-3-3-70b-instruct Meta 128K context, multilingual
databricks-meta-llama-3-1-405b-instruct Meta Retiring May 2026 (PT)
databricks-meta-llama-3-1-8b-instruct Meta Lightweight, 128K context
databricks-llama-4-maverick Meta MoE architecture
databricks-gemini-3-1-pro Google 1M context, hybrid reasoning
databricks-gemini-3-pro Google 1M context, hybrid reasoning
databricks-gemini-3-flash Google Fast, cost-efficient
databricks-gemini-2-5-pro Google 1M context, Deep Think
databricks-gemini-2-5-flash Google 1M context, hybrid reasoning
databricks-gemma-3-12b Google 128K context, multilingual
databricks-qwen3-next-80b-a3b-instruct Alibaba Efficient MoE

Read the full file on GitHub · 292 lines

Files

What ships with it

9 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.

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. 1mo ago First seen · 292 lines · 81 tokens per session scan A cc0e55362999

Subscribe to this mod's changes

databricks-model-serving is a skill published in the GitHub repository alessandro9110/Speech-To-Text-With-Databricks (4 stars, last pushed 8mo ago), licensed MIT. It adds 81 tokens to every session and 2,849 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-02.

Building agentsData and AIRAG and vectorsdatabricksdelta-lakegenerative-ailakehousemachinespeech-to-text
Related

databricks-model-serving compared with skills from other repositories

databricks-model-serving next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
databricks-model-servingalessandro9110/Speech-To-Text-With-DatabricksSkill48mo agoMITA81Claude Code
databricks-expertpersonamanagmentlayer/pclSkill4411d agoApache-2.0A74Claude Code
sensitive-information-disclosurePurpleAILAB/DecepticonSkill6.5k8d agoApache-2.0A55Claude Code, Codex
vector-and-embedding-weaknessesPurpleAILAB/DecepticonSkill6.5k8d agoApache-2.0A59Claude Code, Codex
aatmf-t12-rag-poisoningPurpleAILAB/DecepticonSkill6.5k8d agoApache-2.0A41Claude Code, Codex
exportbibinprathap/VeritasGraphSkill3262d agoMITA29Claude Code
build-paths-beginneroracle-devrel/oracle-ai-developer-hubSkill4.5kyesterdaynoneA93Claude Code, Codex