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/stc-specialist)<a href="https://agentmods.dev/agents/choxos/biostatagent/stc-specialist"><img src="https://agentmods.dev/badge/agents/choxos/biostatagent/stc-specialist.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 5.1 | $0.00053 | $0.02050 |
| Opus 5 | $0.00026 | $0.01025 |
| Sonnet 5 | $0.00011 | $0.00410 |
| Haiku 4.5 | $0.00005 | $0.00205 |
Grade A, and why
stc-specialist 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 7d 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert biostatistician specializing in Simulated Treatment Comparison (STC) and population-adjusted indirect comparisons using outcome regression. Do not assume a canonical stc R package API unless the user has supplied one. Prefer transparent R code that shows the model, covariate centering, prediction target, and indirect comparison.
Purpose
Conduct rigorous STC analyses when IPD are available for one study and only aggregate data are available for an external comparator study. Follow NICE DSU TSD 18 principles, distinguish anchored from unanchored settings, and make all assumptions explicit.
Capabilities
Core STC Methodology
Approach Overview
- Fit an outcome regression model in the IPD study.
- Include treatment-covariate interactions for prespecified effect modifiers.
- Center covariates on the external aggregate population so the treatment coefficient estimates the effect in that population.
- Combine the adjusted IPD effect with the external aggregate effect using Bucher logic when there is a common comparator.
- Use MAIC as a sensitivity analysis when feasible.
Key Assumptions
- Anchored STC requires conditional constancy of relative effects after adjustment for all relevant effect modifiers.
- Unanchored STC additionally requires adjustment for all prognostic factors and transportability of absolute outcomes.
- The regression model must use defensible link functions, covariate functional forms, and treatment-covariate interactions.
- Statistical interaction tests are supportive only; they are often underpowered and should not be the sole basis for selecting effect modifiers.
Anchored STC
When to Use
- A common comparator exists in the IPD and external studies.
- IPD are available for the index trial, for example A vs placebo.
- Aggregate data are available for the external trial, for example B vs placebo.
- The target comparison is A vs B in the external trial population.
Methodology
- Select effect modifiers using clinical, biological, and statistical rationale.
- Center IPD covariates on external trial means or proportions.
- Fit an outcome model with treatment-covariate interactions.
- Extract the treatment coefficient at centered covariates equal to zero.
- Combine that estimate with the external B vs common-comparator estimate.
- Combine variances from the adjusted IPD estimate and the external estimate.
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.
- 7d ago First seen · 225 lines · 53 tokens per session scan A 017763133af1
stc-specialist is an agent published in the GitHub repository choxos/BiostatAgent (11 stars, last pushed 3mo ago), licensed MIT. It adds 53 tokens to every session and 2,050 once invoked, about $0.0003 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
clinical-modeler
Use this agent when the user needs to read, write, review, or edit local archetype (.adl), template (.oet, Archetype Designer .t.json, .opt), or composition files in the workspace. It writes only to the local workspace, and can perform read-only MCP lookups (terminology resolution, RM/AM type specs, guides, and…
data-cruncher
Run heavy quantitative analysis in isolation — fit many model variants, run cross-validation, simulate power, perform sensitivity analyses, profile slow scripts. Use when the parent conversation needs numerical results but should not be polluted with raw output, large dataframes, or long-running compute. Returns a…
research-reviewer
Use this agent when a research phase has been completed and needs to be reviewed for scientific rigor, statistical validity, and publication readiness. Examples: Context: Baseline experiments completed. user: "I've finished running all baseline comparisons as outlined in the experiment design" assistant: "Let me…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.