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 j4flmao/agent-skills --skill feature-storegit clone --depth 1 https://github.com/j4flmao/agent-skillsWrote 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/j4flmao/agent-skills/feature-store)<a href="https://agentmods.dev/skills/j4flmao/agent-skills/feature-store"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/feature-store/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/j4flmao/agent-skills/feature-store"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/feature-store.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00137 | $0.04565 |
| Opus 5 | $0.00068 | $0.02282 |
| Sonnet 5 | $0.00027 | $0.00913 |
| Haiku 4.5 | $0.00014 | $0.00456 |
Grade A, and why
data-feature-store 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 561 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Store
Purpose
Manage ML features through their lifecycle: define feature definitions, compute from batch/streaming sources, serve at low latency for online inference, and generate point-in-time correct training datasets.
Agent Protocol
Trigger
Exact user phrases: "feature store", "Feast", "Tecton", "feature engineering", "feature serving", "feature registry", "point-in-time join", "online features", "offline features", "feature pipeline", "feature retrieval", "feature management", "ML feature".
Input Context
Before activating, verify:
- ML framework (PyTorch, TensorFlow, scikit-learn)
- Inference mode (batch scoring, real-time API)
- Feature sources (data warehouse, streaming, real-time APIs)
- Infrastructure (Kubernetes, cloud provider, on-prem)
- Online serving requirements (latency, throughput, freshness)
- Existing feature definitions location
Output Artifact
Feature store configuration with Feast deployment, feature definitions, serving infrastructure, and training dataset generation pipeline.
Response Format
# Feast feature definitions
# Serving config
# Feature retrieval for training
# Online feature serving
# Point-in-time join
# Feature engineering queries
No preamble. No postamble. No explanations. No filler/hedging/transitions. Compress output — why use many token when few do trick.
Completion Criteria
- Feast or Tecton deployed with offline and online store
- Feature definitions registered with types, sources, and owners
- Feature engineering pipeline producing batch and streaming features
- Point-in-time correct training dataset generation working
- Online serving endpoint providing features under 10ms p99
- Feature registry browsable for discovery and documentation
- Feature validation and monitoring configured
Max Response Length
300 lines of code and configuration.
Feast Feature Definitions
Feature Repository Structure
feature_repo/
├── feature_store.yaml # Feast config
├── features/
│ ├── user_features.py # User-related features
│ ├── order_features.py # Order-related features
│ └── merchant_features.py # Merchant features
└── analysis/
└── feature_stats.py # Feature distribution analysis
What ships with it
6 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.
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.
- 9d ago First seen · 561 lines · 137 tokens per session scan A c33d01830a9e
data-feature-store is a skill published in the GitHub repository j4flmao/agent-skills (23 stars, last pushed 6d ago), licensed MIT. It adds 137 tokens to every session and 4,565 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
Data Validation
Data quality checks to run before modeling — distribution summaries, leakage detection, class balance.
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.
arrowspace
Spectral vector search using graph Laplacian eigenstructure. Use when cosine/L2 similarity misses latent structure in your embeddings.
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.
pyhealth
Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC)…