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/model-reviewer)<a href="https://agentmods.dev/agents/choxos/biostatagent/model-reviewer"><img src="https://agentmods.dev/badge/agents/choxos/biostatagent/model-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/model-reviewer"><img src="https://agentmods.dev/badge/agents/choxos/biostatagent/model-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 | $0.00036 | $0.02306 |
| Opus 5.5 | $0.00014 | $0.00922 |
| Sonnet 5.5 | $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 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 — 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.
- 2mo ago First seen · 299 lines · 36 tokens per session scan A 3ede35524afe
model-reviewer is an agent published in the GitHub repository choxos/BiostatAgent (12 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 2,306 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.