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/googlecloudplatform/vertex-ai-samples/vertex-ainpx skills add GoogleCloudPlatform/vertex-ai-samples --skill vertex-aigit clone --depth 1 https://github.com/GoogleCloudPlatform/vertex-ai-samplesWrote 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/googlecloudplatform/vertex-ai-samples/vertex-ai)<a href="https://agentmods.dev/skills/googlecloudplatform/vertex-ai-samples/vertex-ai"><img src="https://agentmods.dev/badge/skills/googlecloudplatform/vertex-ai-samples/vertex-ai.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 | $0.00055 | $0.00476 |
| Opus 5 | $0.00028 | $0.00238 |
| Sonnet 5 | $0.00011 | $0.00095 |
| Haiku 4.5 | $0.00006 | $0.00048 |
Grade A, and why
vertex-ai 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.
What it actually says
Vertex AI Skills (Primary Router)
Overview
This skill acts as the primary router for all Vertex AI related tasks. Google Cloud Vertex AI provides capabilities for deploying open models, running inference against Generative AI models (like Gemini and open models), and fine-tuning models.
Your first step is to determine the user's main objective and then read the appropriate sub-skill.
Workflow Decision Tree
-
Objective Category: What does the user want to do with Vertex AI?
-
Use Gemini SDK (Gen AI SDK): If the user explicitly asks about using the Gemini API on Vertex AI with the Gen AI SDK, or asks for features like Live API, multimedia generation, caching, or batch prediction, stop reading this file and IMMEDIATELY read the skill instructions located at
../genai-sdk/SKILL.md. -
Deploy Models: If the user wants to deploy an Open Model from Model Garden or deploy custom weights to create a Vertex AI Endpoint, stop reading this file and IMMEDIATELY read the skill instructions located at
../vertex-deploy/SKILL.md. -
Run Inference (Text Generation, Chat, Embeddings): If the user wants to connect to Vertex AI to generate text, chat, or get embeddings using models like Gemini, Llama, DeepSeek, etc., stop reading this file and IMMEDIATELY read the skill instructions located at
../vertex-inference/SKILL.md. -
Model Tuning / Fine-Tuning: If the user wants to fine-tune an Open Model or a Gemini Model, stop reading this file and IMMEDIATELY read the skill instructions located at
../vertex-tuning/SKILL.md. -
Unknown / Not Listed: If the objective is not clearly one of the above, STOP. Ask the user to clarify whether they are looking to deploy a model, run inference, or tune a model on Vertex AI.
-
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 · 27 lines · 55 tokens per session scan A 170bee93ca06
vertex-ai is a skill published in the GitHub repository GoogleCloudPlatform/vertex-ai-samples (784 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 476 once invoked, about $0.0003 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
marimo-pair
Drive a live marimo notebook as a workspace: run Python in the same kernel the user does, inspect live notebook state, and commit durable notebook changes. Use when the user wants to start a marimo notebook or pair on an active marimo session.
add-new-model
Add support for a newly-released LLM model in pydantic-ai (e.g. openai:gpt-5.6, anthropic:claude-sonnet-5). Use when a provider ships a new model id and you need to wire literals, profile flags, and tests to recognize it. Handles SDK-lag, gateway list conventions, and capability probing.
adding-a-provider-api-feature
Add a new provider API capability (prompt caching, strict/structured tool calling, thinking/reasoning effort, service tier, safety settings, logprobs, etc.) to Pydantic AI. Use when wiring a provider feature through the library — it enforces reasoning from the existing cross-provider abstraction before designing…
setup
Configure MLflow tracing for Claude Code.
histolab
Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.
deepchem
Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first…