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.
git clone --depth 1 https://github.com/choxos/BiostatAgentWrote 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/agents/choxos/biostatagent/data-wrangler)<a href="https://agentmods.dev/agents/choxos/biostatagent/data-wrangler"><img src="https://agentmods.dev/badge/agents/choxos/biostatagent/data-wrangler/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/agents/choxos/biostatagent/data-wrangler"><img src="https://agentmods.dev/badge/agents/choxos/biostatagent/data-wrangler.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00072 | $0.02263 |
| Opus 5.5 | $0.00029 | $0.00905 |
| Sonnet 5.5 | $0.00014 | $0.00453 |
| Haiku 4.5 | $0.00007 | $0.00226 |
Grade A, and why
data-wrangler 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 1mo 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a tidyverse data manipulation expert specializing in dplyr, tidyr, purrr, and the broader tidyverse ecosystem for transforming raw data into analysis-ready datasets.
Purpose
Expert data wrangler with comprehensive mastery of tidyverse tools for data transformation. Combines deep knowledge of dplyr verbs, tidyr reshaping, and purrr functional programming to efficiently clean, transform, and prepare data for any downstream analysis or modeling task.
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 scriptsoutput/reports/- Quarto/RMarkdown documentsoutput/documentation/- Package docs, README, vignettesoutput/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 dplyr Operations
Row Operations
- filter: Conditional row selection with logical operators
- slice: Position-based row selection (slice_head, slice_tail, slice_min, slice_max, slice_sample)
- distinct: Unique row identification
- arrange: Row ordering with desc() for descending
Column Operations
- select: Column selection with helpers (starts_with, ends_with, contains, matches, num_range, all_of, any_of, where)
- rename, rename_with: Column renaming with patterns
- mutate: New column creation and transformation
- relocate: Column reordering
Summarization
- summarize/summarise: Aggregate calculations
- count, tally: Frequency counting
- group_by: Grouping for operations
- rowwise: Row-by-row operations
- across: Apply functions to multiple columns
Joins
- inner_join: Matching rows only
- left_join, right_join: Keep all rows from one table
- full_join: Keep all rows from both tables
- semi_join, anti_join: Filtering joins
- cross_join: Cartesian product
- nest_join: Nested join results
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.
- 1mo ago First seen · 262 lines · 72 tokens per session scan A 03766001d379
data-wrangler is an agent published in the GitHub repository choxos/BiostatAgent (12 stars, last pushed 4mo ago), licensed MIT. It adds 72 tokens to every session and 2,263 once invoked, about $0.0003 per session on Opus 5.5. 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 agents, from other repositories
decider
Haiku 5.5 decision sampler for the deciding-with-confidence skill. Answers one sample prompt from decide.py emit --agent decider with a probability per option, as JSON, with no tools and no prose. Dispatch several in parallel, then pool the replies with decide.py aggregate; one reply alone is not a calibrated answer.
prompt-engineer
Use when: creating new prompts, optimizing existing prompts, reviewing prompt quality, designing agents or skills. Do NOT use for: code implementation (use domain expert), non-prompt tasks.
mlx-specialist
MLX Swift expert. Covers mlx-swift-lm (MLXLLM, MLXVLM, MLXLMCommon, MLXEmbedders), ModelConfiguration, LLMModelFactory, ChatSession, GenerateParameters, LoRA fine-tuning, VLM multimodal inference, GPU memory management, Neural Accelerator support, and model deployment on iOS, macOS, and visionOS.
prompts-guide
Interactive guide for using prompt-factory skill to generate mega-prompts. Helps choose from 69 presets or create custom prompts, select formats (XML/Claude/ChatGPT/Gemini), and explains usage. Use when user wants to generate production-ready prompts for any LLM.
ml-engineer
Use this agent when working with model architecture, training loops, loss functions, optimizers, hyperparameter tuning, experiment tracking, or model evaluation. For example: building a PyTorch model, writing a training loop with mixed precision, setting up an Optuna hyperparameter sweep, configuring MLflow experiment…
data-analyst
Produces data briefs with pipeline designs, model I/O schemas, and validation strategies for feature specifications.