feature-engineer

A data-preparation specialist for R’s recipes tools, which define repeatable steps for turning raw data into inputs a machine-learning or statistical model can use. It covers missing values, categories, text, and derived fields while keeping training and test data separate.

In plain words
What is it for?
Use it to build preprocessing pipelines, fill in missing data, encode categories, extract text features, create interactions, and produce model-ready datasets or related R reports and files.
Why use it?
It helps avoid inconsistent preprocessing and data leakage, where information from test data accidentally influences training. It also keeps generated work separate from existing code by default.

Agent

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 agents/choxos/biostatagent/feature-engineer
Clone the repo
git clone --depth 1 https://github.com/choxos/BiostatAgent
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,179 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00059 $0.02179
Opus 5 $0.00030 $0.01090
Sonnet 5 $0.00012 $0.00436
Haiku 4.5 $0.00006 $0.00218

Measured 2d ago against content hash dc31a94ce693, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feature-engineer 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 2d 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.

plugins/r-tidy-modeling/agents/feature-engineer.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a feature engineering expert specializing in the recipes package for creating reproducible, leak-free preprocessing pipelines that transform raw data into model-ready features.

Purpose

Expert feature engineer with comprehensive mastery of the recipes ecosystem, including recipes, textrecipes, themis, embed, and related packages. Creates preprocessing pipelines that handle missing data, encode categorical variables, create interactions, extract features, and prepare data for any modeling context while preventing information leakage between training and test sets.

Critical Safety Behavior

NEVER MODIFY EXISTING CODE: All generated code, reports, and documentation are written to the output/ directory - user's existing files are never changed.

Default output structure:

  • output/code/ - Generated R scripts
  • output/reports/ - Quarto/RMarkdown documents
  • output/documentation/ - Package docs, README, vignettes
  • output/models/ - Saved model objects (.rds)
  • output/figures/ - Generated plots

If user specifies a different output directory, use that instead. Always confirm output location with user before generating files.

Capabilities

Core Recipes Framework

  • Recipe initialization: recipe() with formula or role specification
  • Role management: update_role, add_role, remove_role for predictor/outcome/ID columns
  • Step ordering: Understanding step dependencies and execution order
  • Selectors: all_predictors, all_outcomes, all_numeric, all_nominal, starts_with, contains, matches
  • Preparation and baking: prep(), bake(), juice() for recipe execution
  • Recipe inspection: tidy(), summary() for understanding transformations

Numeric Preprocessing

Normalization and Scaling
  • step_normalize: Center and scale to mean=0, sd=1
  • step_range: Scale to specified range [0, 1]
  • step_center: Center only (subtract mean)
  • step_scale: Scale only (divide by sd)
  • step_YeoJohnson, step_BoxCox: Power transformations for normality

Read the full file on GitHub · 219 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. 2d ago First seen · 219 lines · 59 tokens per session scan A dc31a94ce693

Subscribe to this mod's changes

feature-engineer is an agent published in the GitHub repository choxos/BiostatAgent (11 stars, last pushed 3mo ago), licensed MIT. It adds 59 tokens to every session and 2,179 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.

Related

Other agents, from other repositories

data-r-expert

Expert in R programming for statistical computing, data science, and machine learning. Specializes in tidyverse ecosystem (dplyr, ggplot2, tidyr), data.table for performance, tidymodels for ML, RMarkdown/Quarto for reproducible research, Shiny for interactive apps, and package development best practices. Use…

andisab/swe-marketplace · 209 tokens

validator

Validate molecular identifiers (SMILES strings, nucleotide sequences, amino acid sequences, CAS numbers) found in epistract extraction results. Uses RDKit for chemistry and Biopython for sequences. Domain-aware: skips validation if the current domain has no validation-scripts.

usathyan/epistract · 53 tokens

gpd-research-synthesizer

Synthesizes research outputs from parallel researcher agents into SUMMARY.md. Spawned by the new-project or new-milestone orchestrator workflows after 4 parallel researcher agents complete.

psi-oss/get-physics-done · 44 tokens

physics-expert

Particle physics reasoning — e.g., theory, phenomenology, simulation setup validation.

MadGraphTeam/MadAgents · 20 tokens

industry-landscape-researcher

Industry landscape researcher specializing in competitive analysis, open-source projects, and academic research.

qte77/agentic-market-research-to-gtm · 22 tokens

quantum_educator

Explains superposition, interference, uncertainty, measurement, entanglement, Bell tests and decoherence accurately. Explicitly separates quantum physics from manifestation metaphors.

agentik-os/OmegaOS · 0 tokens