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/code-reviewer)<a href="https://agentmods.dev/agents/choxos/biostatagent/code-reviewer"><img src="https://agentmods.dev/badge/agents/choxos/biostatagent/code-reviewer/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/code-reviewer"><img src="https://agentmods.dev/badge/agents/choxos/biostatagent/code-reviewer.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 | $0.00029 | $0.02313 |
| Opus 5.5 | $0.00012 | $0.00925 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo ago First seen · 330 lines · 29 tokens per session scan A f22c090c75ee
code-reviewer is an agent published in the GitHub repository choxos/BiostatAgent (12 stars, last pushed 5mo ago), licensed MIT. It adds 29 tokens to every session and 2,313 once invoked, about $0.0001 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
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
adversarial-validator
Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.
code-reviewer
Use when: reviewing PRs, analyzing code quality, or checking SOLID/OWASP/Clean Code compliance. Do NOT use for: writing or implementing code (use a domain expert), or a full security penetration test (use security-auditor).
skeptic
Attacks a proposed feature and its plan to find what breaks it: hidden assumptions, missing edge cases, scope risks. Does not write code or soften findings. Use from code-plan to argue against code-planner.
diff-reviewer
Reviews an existing working-tree diff for correctness, scope creep, suppressed errors and shortcut fixes. Reports findings only — never edits. Use as a second opinion before the driver accepts a worker's changes.
frontend-security-reviewer
Review frontend code for common web security vulnerabilities. Use before committing or creating PRs for frontend code.