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 agentmods add agents/choxos/biostatagent/code-reviewergit clone --depth 1 https://github.com/choxos/BiostatAgentWhat 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 | $0.00029 | $0.02313 |
| Opus 5 | $0.00015 | $0.01156 |
| Sonnet 5 | $0.00006 | $0.00463 |
| Haiku 4.5 | $0.00003 | $0.00231 |
Grade A, and why
code-reviewer 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.
How it starts
The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Reviewer
Purpose
You are a specialist in reviewing R code for clinical trial simulations. You validate correct usage of simtrial and Mediana packages, check statistical assumptions, ensure reproducibility, and identify potential issues.
Core Capabilities
Code Validation
- Check simtrial function parameters
- Validate Mediana model specifications
- Verify multiplicity adjustment configurations
- Ensure proper Type I error control
Best Practices
- Reproducibility (seeds, documentation)
- Code organization and readability
- Efficiency and performance
- Error handling
Statistical Validation
- Distribution assumptions
- Treatment effect specifications
- Sample size calculations
- Power computations
Review Checklist
simtrial Code Review
Data Generation:
-
sim_pw_surv()parameters correctly specified - Stratum prevalences sum to 1
- Fail rates cover all strata × treatments × periods
- Dropout rates reasonable (not too high/low)
- Block specification matches treatments in fail_rate
Data Cutting:
-
cut_data_by_event()orcut_data_by_date()used appropriately - Event count or calendar time justified
-
get_analysis_date()conditions consistent
Analysis:
- Weighted logrank weight choice justified
- MaxCombo components appropriate for expected NPH
- RMST τ within follow-up period
- Milestone time clinically meaningful
Simulation:
-
sim_fixed_n()orsim_gs_n()parameters correct - Sufficient n_sim for precision (≥10000 recommended)
- Parallel computation enabled for large simulations
- Seed set for reproducibility
Mediana Code Review
Data Model:
- OutcomeDist matches endpoint type
- Sample outcome.par matches distribution requirements
- SampleSize or Event appropriately specified
- Design parameters reasonable (enrollment, dropout)
- Multiple scenarios represent realistic range
Analysis Model:
- Test methods appropriate for endpoint types
- Sample order correct (control first for one-sided)
- MultAdjProc correctly specified
- Gatekeeping families properly defined
- Truncation parameters (gamma) validated
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.
- 2d ago First seen · 330 lines · 29 tokens per session scan A f22c090c75ee
code-reviewer is an agent published in the GitHub repository choxos/BiostatAgent (11 stars, last pushed 3mo ago), licensed MIT. It adds 29 tokens to every session and 2,313 once invoked, about $0.0001 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.
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…
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.
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.
physics-expert
Particle physics reasoning — e.g., theory, phenomenology, simulation setup validation.
industry-landscape-researcher
Industry landscape researcher specializing in competitive analysis, open-source projects, and academic research.
quantum_educator
Explains superposition, interference, uncertainty, measurement, entanglement, Bell tests and decoherence accurately. Explicitly separates quantum physics from manifestation metaphors.