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 commands/choxos/biostatagent/review-modelgit 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/commands/choxos/biostatagent/review-model)<a href="https://agentmods.dev/commands/choxos/biostatagent/review-model"><img src="https://agentmods.dev/badge/commands/choxos/biostatagent/review-model.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 | $0.00017 | $0.00911 |
| Opus 5 | $0.00009 | $0.00456 |
| Sonnet 5 | $0.00003 | $0.00182 |
| Haiku 4.5 | $0.00002 | $0.00091 |
Grade A, and why
review-model 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bayesian Model Review Workflow
You are reviewing a user's existing Bayesian model. Follow this structured approach:
Step 1: Receive Model Code
Ask the user to paste their model code. Automatically detect:
- Language (Stan / JAGS / WinBUGS)
- Model type
- Complexity level
Step 2: Syntax Check
For Stan:
- Valid block order (functions → data → transformed data → parameters → transformed parameters → model → generated quantities)
- Correct array syntax (
array[N] real, notreal[N]) - Proper constraint syntax (
<lower=0>,simplex, etc.) - Semicolons on all statements
For JAGS/WinBUGS:
- Single
model { }block - Proper distribution prefix (
dfor distributions) - Correct indexing syntax
- Valid truncation syntax (
T(lower, upper))
Step 3: Statistical Review
Check the following using @model-reviewer:
Priors
- All parameters have explicit priors
- Priors are appropriate for the scale of data
- No improper priors that could cause issues
- Informative priors are justified
Parameterization
- Stan: Using SD (sigma), not precision
- BUGS/JAGS: Using precision (tau = 1/sigma²) correctly
- Covariance vs precision matrices are correct
- Hierarchical models: centered vs non-centered appropriateness
Efficiency
- Vectorization used where possible (Stan)
- No unnecessary loops
- Appropriate transformed parameter placement
- Cholesky factors for covariance matrices
Common Errors
- Integer division issues
- Missing constraints on parameters
- Potential numerical overflow/underflow
- Invalid parameter combinations
Step 4: Generate Report
Provide a structured review:
## Model Review Report
### Language Detected
[Stan / JAGS / WinBUGS]
### Model Type
[Hierarchical / Regression / Time Series / etc.]
### Syntax Issues
- [List any syntax errors or warnings]
### Statistical Concerns
- [List concerns about priors, parameterization, etc.]
### Efficiency Improvements
- [Suggestions for better performance]
### Recommended Changes
1. [Specific change with code example]
2. [Another change...]
### Corrected Model (if needed)
[Full corrected model code]
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 · 141 lines · 17 tokens per session scan A d9da2ddf0f08
review-model is a command published in the GitHub repository choxos/BiostatAgent (11 stars, last pushed 3mo ago), licensed MIT. It adds 17 tokens to every session and 911 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 commands, from other repositories
openehr-explain
One-stop router that explains or looks up any openEHR thing — auto-detects an archetype, a template, an RM/AM/BASE type, an RM structural concept, an ADL idiom, an AQL query or keyword, or a terminology code (replaces /archetype-explain, /template-explain, /type-spec, /rm-structure, /adl-idiom, /terminology).
astro-dso-doc
Generate pixinsight project information for a deep-sky object astrophotography session.
talk
Turn a paper (or several) into an academic talk — outline, slides, speaker notes, backups, rehearsal plan.
create-scene
Create a single animated scene for mathematical visualization.
ars-lit-review
ARS academic-paper lit-review mode — annotated bibliography in paper format.
checklist
Generate a custom checklist for the current feature based on user requirements.