create-model

An interactive workflow for creating Bayesian models in Stan, JAGS, WinBUGS, or PyMC. It gathers information about the outcome, predictors, groups, data size, priors, target language, and the user's experience level.

In plain words
What is it for?
Use it to start hierarchical, regression, time-series, survival, or meta-analysis models in R or Python, with optional prior choices and educational guidance.
Why use it?
It turns a statistical question into a structured model-building process and helps select a suitable modeling specialist. It also supports explanations and code detail appropriate to the user's experience.

Command

Install

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.

agentmods
npx agentmods add commands/choxos/biostatagent/create-model
Clone the repo
git clone --depth 1 https://github.com/choxos/BiostatAgent
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 796 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00022 $0.00796
Opus 5 $0.00011 $0.00398
Sonnet 5 $0.00004 $0.00159
Haiku 4.5 $0.00002 $0.00080

Measured 2d ago against content hash 3f9a1b62f5eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-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 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.

plugins/bayesian-modeling/commands/create-model.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bayesian Model Creation Workflow

You are helping the user create a Bayesian model. Follow this structured workflow:

Step 1: Gather Requirements

Ask the user to specify:

  1. Model Type (select one):

    • Hierarchical/Multilevel model
    • Regression model (linear, logistic, Poisson, etc.)
    • Time series model (AR, state-space, etc.)
    • Survival analysis model
    • Meta-analysis model
  2. Target Language:

    • Stan with cmdstanr (DEFAULT for R - recommended)
    • PyMC with ArviZ (DEFAULT for Python)
    • JAGS with R2jags
    • WinBUGS with R2WinBUGS (Windows only)
  3. Experience Level:

    • Beginner (extensive comments, educational explanations)
    • Intermediate (standard documentation)
    • Advanced (minimal comments, efficiency-focused)
  4. Data Description:

    • Outcome variable type (continuous, binary, count, time-to-event)
    • Predictor variables
    • Grouping structure (if hierarchical)
    • Sample sizes
  5. Prior Preferences (optional):

    • Specific prior distributions
    • Informative vs weakly informative
    • Domain-specific constraints

Step 2: Route to Specialist

Based on the target language:

  • Stan: Use @stan-specialist with skills:

    • stan-fundamentals for syntax
    • Appropriate model type skill (hierarchical-models, regression-models, etc.)
  • PyMC: Use @pymc-specialist with skills:

    • pymc-fundamentals for syntax
    • Appropriate model type skill
  • JAGS/WinBUGS: Use @bugs-specialist with skills:

    • bugs-fundamentals for syntax
    • Appropriate model type skill

Step 3: Generate Model

The specialist will provide:

  1. Complete model code with appropriate comments based on experience level

  2. Integration code (R or Python):

    • Data preparation
    • Model compilation/fitting
    • Basic diagnostics (posterior/ArviZ)
  3. Generated quantities for:

    • Posterior predictive checks
    • Derived quantities of interest

Step 4: Validate Output

Before presenting to user, verify:

  • Model syntax is correct for target language
  • All parameters have priors
  • Parameterization is correct (SD for Stan/PyMC, precision for BUGS)
  • Integration code is complete and runnable (R or Python)
  • Comments match experience level

Read the full file on GitHub · 107 lines

Changes

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.

  1. 2d ago First seen · 107 lines · 22 tokens per session scan A 3f9a1b62f5eb

Subscribe to this mod's changes

create-model is a command published in the GitHub repository choxos/BiostatAgent (11 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 796 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.