ml-python

A set of coding guidance for Snowflake's Python machine-learning library, covering model development and deployment workflows.

In plain words
What is it for?
Use it to review model registries, training and prediction functions, feature engineering, deployment endpoints, versioning, monitoring, and integrations such as scikit-learn or XGBoost.
Why use it?
It gives developers a focused way to investigate how the library trains, stores, versions, serves, and monitors machine-learning models.

Cursor rule

Install

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.

agentmods
npx agentmods add rules/sfc-gh-cconner/support-rules-mcp/ml-python
Clone the repo
git clone --depth 1 https://github.com/sfc-gh-cconner/support-rules-mcp
Per session 669 This file is loaded in full into every session.
When invoked 669 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00669 $0.00669
Opus 5 $0.00334 $0.00334
Sonnet 5 $0.00134 $0.00134
Haiku 4.5 $0.00067 $0.00067

Measured yesterday against content hash 79ace05ec479, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ml-python 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.

rules/connectors/ml-python.mdc · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Snowflake ML Python Investigation Guide

PURPOSE: Snowflake ML Python library patterns for machine learning workflows and model deployment.

Access Method: GitHub MCP API tools
Repository: snowflakedb/snowflake-ml-python

🔍 Quick Investigation Patterns

ML Modeling

# Model registry
mcp_github_search_code(
    query='ModelRegistry OR register_model repo:snowflakedb/snowflake-ml-python'
)

# Training functions
mcp_github_search_code(
    query='fit OR train OR predict repo:snowflakedb/snowflake-ml-python'
)

# Feature engineering
mcp_github_search_code(
    query='FeatureStore OR transform repo:snowflakedb/snowflake-ml-python'
)

ML Operations

# Model deployment
mcp_github_search_code(
    query='deploy OR serve OR endpoint repo:snowflakedb/snowflake-ml-python'
)

# Model versioning
mcp_github_search_code(
    query='version OR tag repo:snowflakedb/snowflake-ml-python'
)

# Monitoring
mcp_github_search_code(
    query='metrics OR monitor OR drift repo:snowflakedb/snowflake-ml-python'
)

Integrations

# Scikit-learn
mcp_github_search_code(
    query='sklearn OR scikit repo:snowflakedb/snowflake-ml-python'
)

# XGBoost
mcp_github_search_code(
    query='xgboost OR XGB repo:snowflakedb/snowflake-ml-python'
)

# TensorFlow/PyTorch
mcp_github_search_code(
    query='tensorflow OR pytorch OR torch repo:snowflakedb/snowflake-ml-python'
)

🎯 Key Components

Core Modules

# Model registry
mcp_github_search_code(
    query='path:snowflake/ml/registry repo:snowflakedb/snowflake-ml-python'
)

# Modeling APIs
mcp_github_search_code(
    query='path:snowflake/ml/modeling repo:snowflakedb/snowflake-ml-python'
)

# Feature store
mcp_github_search_code(
    query='path:snowflake/ml/feature_store repo:snowflakedb/snowflake-ml-python'
)

🗺️ Directory Structure

snowflake/ml/
├── registry/         # Model registry
├── modeling/        # ML algorithms
├── feature_store/   # Feature management
├── ops/            # ML operations
└── utils/          # Utilities

Read the full file on GitHub · 109 lines

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. yesterday First seen · 109 lines · 669 tokens per session scan A 79ace05ec479

Subscribe to this mod's changes

ml-python is a cursor rule published in the GitHub repository sfc-gh-cconner/support-rules-mcp (0 stars, last pushed 10mo ago), licensed Apache-2.0. It adds 669 tokens to every session, about $0.0033 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.