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-tuningnpx skills add GoogleCloudPlatform/vertex-ai-samples --skill vertex-tuninggit 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-tuning)<a href="https://agentmods.dev/skills/googlecloudplatform/vertex-ai-samples/vertex-tuning"><img src="https://agentmods.dev/badge/skills/googlecloudplatform/vertex-ai-samples/vertex-tuning.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 | $0.00000 | $0.00444 |
| Opus 5 | $0.00000 | $0.00222 |
| Sonnet 5 | $0.00000 | $0.00089 |
| Haiku 4.5 | $0.00000 | $0.00044 |
Grade A, and why
vertex-tuning 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 6d 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
name: vertex-tuning description: > Vertex AI Model Tuning Router. Use this skill when the user wants to fine-tune models using Vertex AI. This skill routes to either vertex-tuning-open-model or vertex-tuning-gemini.
Vertex AI Model Tuning (Router)
Overview
This skill acts as a router for Vertex AI tuning tasks. The tuning procedures for Open Models and Gemini Models differ significantly. Your first step is to determine which category the user intends to tune and then read the corresponding sub-skill.
Workflow Decision Tree
-
Model Category: Has the user explicitly stated whether they want to tune an Open Model or a Gemini Model?
- No → STOP. Ask the user if they want to tune an Open Model or a Gemini Model. Do not proceed or recommend any specific models until this is confirmed.
- Yes (Open Model) → The user wants to tune an Open Model. Stop
reading this file and IMMEDIATELY read the skill instructions located at
open-model/SKILL.md. Follow the instructions inside that skill to complete the task. - Yes (Gemini Model) → The user wants to tune a Gemini Model. Stop
reading this file and IMMEDIATELY read the skill instructions located at
gemini/SKILL.md. Follow the instructions inside that skill to complete the task.
What ships with it
21 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.
- gemini/SKILL.md 7.1 KB
- open-model/references/data_prep.md 2.2 KB
- open-model/references/models.md 3.2 KB
- open-model/references/requirements.txt 99 B
- open-model/references/tuning_guide.md 2.7 KB
- open-model/scripts/calculate_cost.py 5.3 KB runs code
- open-model/scripts/deploy_open_model.py 2.0 KB runs code
- open-model/scripts/prepare_dataset.py 8.2 KB runs code
- open-model/scripts/tune_open_model.py 2.8 KB runs code
- open-model/SKILL.md 9.2 KB
- README.md 2.6 KB
- references/data_formatting.md 2.2 KB
- references/data_prep.md 1.7 KB
- references/model_recommendation.md 1.6 KB
- references/models.md 2.1 KB
- references/requirements.txt 76 B
- references/tuning_guide.md 2.1 KB
- references/tuning_parameters.md 3.2 KB
- scripts/deploy_model.py 1.4 KB runs code
- scripts/prepare_dataset.py 7.6 KB runs code
- scripts/tune_model.py 2.3 KB runs code
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.
- 6d ago First seen · 50 lines · 0 tokens per session scan A 24959a3f6398
vertex-tuning is a skill published in the GitHub repository GoogleCloudPlatform/vertex-ai-samples (784 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 444 tokens. 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…