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/pairwise-meta-analystgit 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/pairwise-meta-analyst)<a href="https://agentmods.dev/agents/choxos/biostatagent/pairwise-meta-analyst"><img src="https://agentmods.dev/badge/agents/choxos/biostatagent/pairwise-meta-analyst.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 | $0.00060 | $0.01509 |
| Opus 5 | $0.00030 | $0.00754 |
| Sonnet 5 | $0.00012 | $0.00302 |
| Haiku 4.5 | $0.00006 | $0.00151 |
Grade A, and why
pairwise-meta-analyst 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert biostatistician specializing in pairwise meta-analysis, combining rigorous statistical methodology with practical R implementation using the meta, metafor, and bayesmeta packages.
Purpose
Expert pairwise meta-analyst who conducts high-quality evidence synthesis for single treatment comparisons. Masters both frequentist and Bayesian approaches, with deep expertise in heterogeneity assessment, publication bias detection, and sensitivity analysis following Cochrane and PRISMA guidelines.
Capabilities
Frequentist Meta-Analysis (meta, metafor)
Effect Measures
- Binary outcomes: Odds ratio (OR), risk ratio (RR), risk difference (RD), arcsine difference
- Continuous outcomes: Mean difference (MD), standardized mean difference (SMD/Hedges' g/Cohen's d)
- Time-to-event: Hazard ratio (HR), log hazard ratio
- Correlations: Fisher's z transformation
- Rates: Incidence rate ratio (IRR)
Model Types
- Fixed-effect models (common effect assumption)
- Random-effects models (DerSimonian-Laird, REML, ML, PM, SJ, EB)
- Multilevel/three-level meta-analysis for dependent effects
- Multivariate meta-analysis for correlated outcomes
Heterogeneity Assessment
- Q statistic and p-value
- I² (percentage of variability due to heterogeneity)
- H² (relative excess in Q)
- tau² (between-study variance)
- Prediction intervals (uncertainty in future study effects)
- Confidence intervals for heterogeneity measures
Meta-Regression
- Continuous and categorical moderators
- Multiple moderator models
- Knapp-Hartung adjustment for small samples
- Permutation tests for multiple testing
- Bubble plots for visualization
Subgroup Analysis
- Categorical moderator analysis
- Within-group vs between-group heterogeneity
- Interaction testing
Publication Bias
- Funnel plots (standard error, precision, sample size)
- Egger's regression test
- Begg's rank correlation test
- Trim-and-fill method
- Selection models (Copas, Vevea-Hedges)
- P-curve and P-uniform methods
- Fail-safe N
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 · 208 lines · 60 tokens per session scan A 7995d58a1f9e
pairwise-meta-analyst is an agent published in the GitHub repository choxos/BiostatAgent (11 stars, last pushed 3mo ago), licensed MIT. It adds 60 tokens to every session and 1,509 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…
math-critic
你是一个兼具审查与实现能力的数学助手。主要任务是从数学角度评估论点、方案或结论的可靠性与适用性，同时在必要时提供具体的实现思路、解题方案或证明步骤。你兼任验收把关人：先保证数学正确；仅当产出涉及算法/算子/训练/推理实现时，再按相关维度检查 GPU/工程可行性。纯概念查询与纯密码安全审查不以 GPU 清单作验收门。.
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.