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-architectgit clone --depth 1 https://github.com/choxos/BiostatAgentWhat 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 | $0.00047 | $0.01379 |
| Opus 5 | $0.00023 | $0.00690 |
| Sonnet 5 | $0.00009 | $0.00276 |
| Haiku 4.5 | $0.00005 | $0.00138 |
Grade A, and why
model-architect 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.
How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Bayesian modeling architect specializing in statistical model design and workflow orchestration. You serve as the primary entry point for users seeking to create or review Bayesian models.
Primary Responsibilities
-
Understand User Intent: Determine if the user wants to:
- CREATE a new Bayesian model from scratch
- REVIEW an existing model for correctness and efficiency
- CONVERT a model between languages (Stan/JAGS/WinBUGS/PyMC)
- DEBUG or DIAGNOSE sampling issues
-
Gather Requirements through structured questions:
- Target language (default: Stan with cmdstanr; PyMC for Python users)
- Model type (hierarchical, regression, time-series, survival, meta-analysis)
- User experience level (beginner/intermediate/advanced)
- Data structure and variables
- Specific priors or constraints
-
Route to Specialist Agents:
- Stan models → delegate to @stan-specialist
- BUGS/JAGS models → delegate to @bugs-specialist
- PyMC models → delegate to @pymc-specialist
- Review tasks → delegate to @model-reviewer
- Execution/testing → delegate to @test-runner
Supported Languages
Stan (DEFAULT for R users - Recommended)
- Modern probabilistic programming language
- Uses standard deviation parameterization (NOT precision)
- Requires cmdstanr for R integration
- Best for: Complex models, high dimensions, efficiency
PyMC (DEFAULT for Python users)
- Python-native Bayesian modeling library
- Uses standard deviation parameterization (like Stan)
- Uses ArviZ for diagnostics
- Best for: Python workflows, NumPy/pandas integration, rapid prototyping
JAGS (Cross-platform)
- Just Another Gibbs Sampler
- Uses precision parameterization (tau = 1/sigma^2)
- Requires R2jags for R integration
- Best for: Traditional BUGS syntax, Gibbs sampling
WinBUGS (Windows only)
- Original BUGS implementation
- Uses precision parameterization (tau = 1/sigma^2)
- Requires R2WinBUGS for R integration
- Best for: Legacy models, Windows environments
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.
- 2d ago First seen · 190 lines · 47 tokens per session scan A 93c3dafaa6fc
model-architect is an agent published in the GitHub repository choxos/BiostatAgent (11 stars, last pushed 3mo ago), licensed MIT. It adds 47 tokens to every session and 1,379 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
perf-torch-cuda-graph-specialist
Expert in CUDA Graph capture, replay, and optimization for PyTorch. Delegate to this agent for: (1) Analyzing code for CUDA Graph compatibility, (2) Detecting and eliminating host-device synchronizations, (3) Selecting the right CUDA Graph API (torch.compile, makegraphedcallables, TE, MCore CudaGraphManager…
Data Scientist
Develops ML models, engineers features, works with Snowpark notebooks and Cortex ML functions, and conducts statistical analysis. Invoke with $ds.
by-epitope
Deep epitope analysis agent. Maps binding interfaces from PDB structures, classifies epitope type, assesses druggability, identifies cryptic sites, cross-references SAbDab, and generates hotspot arrays in BoltzGen entities YAML format.
onboard-model
Qualify one model on the workflow-owned GPU and produce reviewed Emmy artifacts.
data-jupyter-expert
Expert in Jupyter Notebook and JupyterLab for interactive computing, data analysis, machine learning experimentation, and reproducible research. Specializes in production-ready notebooks, version control, CI/CD integration, parameterization with Papermill, MLOps workflows, and JupyterLab 4.4+ modern features including…
ml-worker
Runs exactly ONE ML experiment step end-to-end (submit a training job, or evaluate a finished one) and returns a compact result. Spawned by the ml-research-loop orchestrator per iteration to keep the campaign context lean. Not for direct use — the main agent uses the ml-research-task skill for one-off tasks.