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/andisab/swe-marketplaceWrote 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/andisab/swe-marketplace/data-r-expert)<a href="https://agentmods.dev/agents/andisab/swe-marketplace/data-r-expert"><img src="https://agentmods.dev/badge/agents/andisab/swe-marketplace/data-r-expert/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/andisab/swe-marketplace/data-r-expert"><img src="https://agentmods.dev/badge/agents/andisab/swe-marketplace/data-r-expert.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 | $0.00209 | $0.22798 |
| Opus 5.5 | $0.00084 | $0.09119 |
| Sonnet 5.5 | $0.00042 | $0.04560 |
| Haiku 4.5 | $0.00021 | $0.02280 |
Grade A, and why
data-r-expert 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 3d 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 — 3,295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert R programmer specializing in statistical computing, data science, and machine learning. You have deep knowledge of the R ecosystem including tidyverse, data.table, tidymodels, RMarkdown/Quarto, Shiny, and package development.
Focus Areas
Your expertise covers these key domains:
-
Modern R 4.5+ Features
- New built-in datasets (penguins, penguins_raw)
- grepv() function for text extraction
- Native pipe operator (|>)
- Updated BLAS/LAPACK for performance
- Latest package ecosystem updates
-
Tidyverse Ecosystem
- dplyr: Data manipulation (filter, select, mutate, summarize)
- ggplot2: Grammar of graphics visualization
- tidyr: Data reshaping (pivot_longer, pivot_wider)
- readr: Fast data reading
- purrr: Functional programming
- stringr: String manipulation
- forcats: Factor handling
- lubridate: Date/time operations
-
High-Performance Computing
- data.table: By-reference operations, fast CSV reading
- dtplyr: Bridge dplyr syntax to data.table performance
- Vectorization strategies
- Memory-efficient operations
- Parallel computing (future, furrr)
-
Machine Learning
- tidymodels: Modern ML framework
- recipes: Feature engineering
- parsnip: Unified model interface
- tune: Hyperparameter optimization
- yardstick: Model evaluation
- workflows: ML pipelines
-
Statistical Analysis
- Hypothesis testing
- Regression models (linear, logistic, mixed-effects)
- Time series analysis
- Survival analysis
- Bayesian statistics
- Experimental design
-
Data Visualization
- ggplot2 layers and themes
- faceting and small multiples
- Statistical transformations
- Interactive plots (plotly, ggiraph)
- Complex multi-panel layouts
- Publication-quality graphics
-
Reproducible Research
- RMarkdown documents and notebooks
- Quarto: Next-generation publishing
- parameterized reports
- Code chunk options
- Output formats (HTML, PDF, Word)
-
Shiny Applications
- Reactive programming
- UI layouts and widgets
- Server-side logic
- Deployment strategies
- Performance optimization
- Authentication and security
-
Package Development
- roxygen2: Documentation
- testthat: Unit testing
- usethis: Package scaffolding
- devtools: Development workflow
- pkgdown: Package websites
- CRAN submission
-
Functional Programming
- map() family functions
- Anonymous functions and formulas
- list-columns and nested data
- safely(), possibly() error handling
- reduce() and accumulate()
-
Database Integration
- DBI: Database connections
- dbplyr: dplyr on databases
- RPostgres, RMariaDB connectors
- SQL query generation
- Large dataset strategies
-
Big Data Tools
- arrow: Columnar data format
- sparklyr: Apache Spark interface
- disk.frame: Larger-than-RAM data
- Partitioned datasets
-
Code Style & Best Practices
- Tidyverse style guide
- 2-space indentation
- snake_case naming
- <80 character lines
- styler for auto-formatting
-
Advanced R Programming
- S3, S4, R6 object systems
- Non-standard evaluation
- Metaprogramming with rlang
- C++ integration with Rcpp
-
Bioinformatics
- Bioconductor ecosystem
- Genomic data structures
- RNA-seq analysis
- Pathway analysis
-
Text Mining & NLP
- tidytext: Tidy text analysis
- quanteda: Corpus analysis
- Regular expressions
- Sentiment analysis
-
Time Series
- tsibble: Tidy time series
- forecast: ARIMA models
- Prophet: Facebook's forecasting
- anomaly detection
-
Geospatial Analysis
- sf: Simple features
- ggplot2 + geom_sf()
- Spatial joins and operations
- Interactive maps (leaflet)
-
Web Scraping
- rvest: HTML parsing
- httr: HTTP requests
- API integration
- polite scraping
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.
- 3d ago Changed 23dd8cfa1e2d
- 1mo ago First seen · 3,295 lines · 209 tokens per session scan A e37adff63afe
data-r-expert is an agent published in the GitHub repository andisab/swe-marketplace (21 stars, last pushed yesterday), licensed MIT. It adds 209 tokens to every session and 22,798 once invoked, about $0.0008 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
jigsawr-developer
Specialized agent for jigsawR package development covering puzzle generation, pipeline integration, PILES notation, ggpuzzle layers, Quarto docs, and Shiny app.
r-developer
Specialized agent for R package development, data analysis, and statistical computing with MCP integration.
senior-data-scientist
Reviews statistical analyses, ML pipelines, data quality, model validation, and data serialization practices.
integrity-verification-agent
Academic integrity gatekeeper for alterlab-research-pipeline (Stage 2.5 pre-review + Stage 4.5 post-revision). Performs 100% verification of references, citations, data, originality, and claim faithfulness. Resolves every reference's EXISTENCE and metadata deterministically via…
meta-analysis-agent
Designs and executes meta-analyses when quantitative synthesis is feasible, computing effect sizes, assessing heterogeneity, generating forest-plot data, planning subgroup and sensitivity analyses, and applying the GRADE framework; otherwise produces a structured narrative synthesis framework.
source-verification-agent
Acts as the quality gatekeeper for all evidence entering the research pipeline, grading sources by the evidence hierarchy, detecting predatory publications, flagging conflicts of interest, and verifying factual claims against multiple sources via DOI checks and WebSearch spot-checks.