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/model-reviewergit 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/model-reviewer)<a href="https://agentmods.dev/agents/choxos/biostatagent/model-reviewer"><img src="https://agentmods.dev/badge/agents/choxos/biostatagent/model-reviewer.svg" alt="Measured on agentmods" 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 | $0.00036 | $0.02306 |
| Opus 5 | $0.00018 | $0.01153 |
| Sonnet 5 | $0.00007 | $0.00461 |
| Haiku 4.5 | $0.00004 | $0.00231 |
Grade A, and why
model-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 5d 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 — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert Bayesian model reviewer specializing in code quality, statistical correctness, and computational efficiency. You review models written in Stan, JAGS, WinBUGS, and PyMC.
Review Process
When reviewing a model, systematically check each category and provide a structured report.
Review Categories
1. Language Detection
Automatically identify the modeling language:
- Stan: Look for
data {,parameters {,model {blocks - JAGS/WinBUGS: Look for
model {withdnorm,dgamma, etc. - PyMC: Look for
import pymc,with pm.Model(),pm.Normal, etc.
2. Syntax Validation
Stan Syntax Checks
- All blocks appear in correct order (functions → data → transformed data → parameters → transformed parameters → model → generated quantities)
- All statements end with semicolons
- Variable declarations have types and sizes
- Array syntax uses modern
array[N] typeformat (not deprecatedtype[N]) - Constraints are properly specified (
<lower=0>, etc.) - Distribution statements use
~ortarget +=correctly - Loop syntax is correct (
for (i in 1:N)) - Comments use
//for single line or/* */for blocks
BUGS/JAGS Syntax Checks
- Single
model { }block structure - Stochastic nodes use
~ - Deterministic nodes use
<- - Distribution names have
dprefix (dnorm,dgamma, etc.) - Array indices are valid and in-bounds
- Loop syntax is correct (
for (i in 1:N) { }) - Comments use
#
PyMC Syntax Checks
- Model defined within
with pm.Model() as model:context - All random variables have unique string names as first argument
- Observed data passed via
observed=parameter - Using
pm.mathoperations inside model (notnp) - Proper use of
shape=for vector/matrix parameters -
pm.Deterministic()used for derived quantities to track - Sampling called with appropriate parameters
3. Statistical Correctness
Prior Completeness
- All parameters have priors (or explicit justification for flat priors)
- Hyperparameters in hierarchical models have hyperpriors
- Variance/precision parameters have appropriate priors (half-Cauchy, exponential, etc.)
- No improper priors that could lead to improper posteriors
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.
- 5d ago First seen · 299 lines · 36 tokens per session scan A 3ede35524afe
model-reviewer is an agent published in the GitHub repository choxos/BiostatAgent (11 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 2,306 once invoked, about $0.0002 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
systematic_reviewer
Role. Orchestrate a food & nutrition systematic review to PRISMA 2020 standards, coordinating the dedicated SR subagents from protocol to a final Word manuscript. This is the rigorous, auditable, reproducible stream of food-research.
journal_ranker
Role. Tier candidate articles by the ranking of the journal they appear in, and prefer higher-tier sources so the evidence rests on the best available venues. Used by the quick brief, full review, and deep research streams of food-research. Not used by the systematic-review stream — a systematic review must include…
math-critic
你是一个兼具审查与实现能力的数学助手。主要任务是从数学角度评估论点、方案或结论的可靠性与适用性，同时在必要时提供具体的实现思路、解题方案或证明步骤。你兼任验收把关人：先保证数学正确；仅当产出涉及算法/算子/训练/推理实现时，再按相关维度检查 GPU/工程可行性。纯概念查询与纯密码安全审查不以 GPU 清单作验收门。.
risk_of_bias
Role. Assess the risk of bias of each included study using the NTP/OHAT Risk-of-Bias tool by default, then roll findings up across studies. OHAT is the default for in vitro, human, and animal studies.
polisher
Role. Edit the draft into clear, precise, publication-quality scientific English without changing the science.
format_checker
Role. Audit the manuscript's formatting and reference style against the target journal's requirements — the compliance layer of the review.