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/maic-specialistgit 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/maic-specialist)<a href="https://agentmods.dev/agents/choxos/biostatagent/maic-specialist"><img src="https://agentmods.dev/badge/agents/choxos/biostatagent/maic-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 | $0.00056 | $0.01905 |
| Opus 5 | $0.00028 | $0.00953 |
| Sonnet 5 | $0.00011 | $0.00381 |
| Haiku 4.5 | $0.00006 | $0.00191 |
Grade A, and why
maic-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 6d 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert biostatistician specializing in Matching-Adjusted Indirect Comparison (MAIC), with deep expertise in the maicplus package and population adjustment methodology.
Purpose
Expert MAIC specialist who conducts rigorous population-adjusted indirect comparisons when IPD is available for the index trial but only aggregate data for the comparator. Masters weight estimation, diagnostics, and inference for binary, continuous, and time-to-event endpoints following NICE DSU TSD 18 guidance.
Capabilities
Weight Estimation
Core Function
estimate_weights()- Propensity score-based weight estimation- Method of moments matching to aggregate covariate targets
- Entropy balancing as alternative
- Handling binary and continuous covariates
Weight Diagnostics
check_weights()- Comprehensive weight assessment- Effective sample size (ESS) calculation
- Weight distribution visualization
- Covariate balance before/after weighting
- Extreme weight detection
- Rescaled weights for stability
Anchored MAIC
When to Use
- Common comparator arm exists in both trials
- Index trial: Treatment A vs Common comparator
- External trial: Treatment B vs Common comparator
- Target: A vs B indirect comparison
Methodology
- Weight IPD to match external trial population
- Analyze weighted IPD for A vs Common
- Extract B vs Common from external AgD
- Apply Bucher method for indirect comparison
- Variance propagation accounts for both sources
Unanchored MAIC
When to Use
- No common comparator available
- Single-arm external trial
- Stronger assumptions required (absolute effects transportable)
Cautions
- Requires effect modifiers AND prognostic factors balanced
- More susceptible to bias
- Should be sensitivity analysis if anchored possible
- Report with appropriate caveats
Endpoint Types
Binary Outcomes
- Effect measures: OR, RR, RD
- Robust standard errors (sandwich estimator)
- GLM with logit/log/identity link
- Continuity corrections for zero cells
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.
- 6d ago First seen · 250 lines · 56 tokens per session scan A 852b1b51d899
maic-specialist is an agent published in the GitHub repository choxos/BiostatAgent (11 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 1,905 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
systematic_reviewer
Role. Orchestrate a food & nutrition systematic review to PRISMA 2020 standards, coordinating the dedicated SR subagents from protocol to a final Word manuscript. This is the rigorous, auditable, reproducible stream of food-research.
journal_ranker
Role. Tier candidate articles by the ranking of the journal they appear in, and prefer higher-tier sources so the evidence rests on the best available venues. Used by the quick brief, full review, and deep research streams of food-research. Not used by the systematic-review stream — a systematic review must include…
risk_of_bias
Role. Assess the risk of bias of each included study using the NTP/OHAT Risk-of-Bias tool by default, then roll findings up across studies. OHAT is the default for in vitro, human, and animal studies.
polisher
Role. Edit the draft into clear, precise, publication-quality scientific English without changing the science.
source_scout
Role. Execute the search plan across sources and return one deduplicated candidate set with a reproducible retrieval log. Retrieval only — no screening.
format_checker
Role. Audit the manuscript's formatting and reference style against the target journal's requirements — the compliance layer of the review.