nma-specialist

nma-specialist is an agent for Claude Code from choxos/BiostatAgent. It costs 50 tokens per session (1,561 once invoked), scanned A, original, MIT.

An expert agent for network meta-analysis (NMA), a method that compares several treatments by combining direct and indirect evidence from different studies. It supports both frequentist and Bayesian R workflows using the netmeta and gemtc packages.

In plain words
What is it for?
Use it to examine network structure, check transitivity and consistency, handle multi-arm trials, run frequentist or Bayesian NMA, create network visualizations, and produce rankings or league tables.
Why use it?
It helps assess whether a treatment network is connected and whether comparisons are sufficiently similar and consistent. It also makes complex outputs such as treatment rankings and comparison tables easier to produce and interpret.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the itc-modeling plugin — 6 skills, 2 commands, 7 agents shipped together

Good fit Use it to examine network structure, check transitivity and consistency, handle multi-arm trials, run frequentist or Bayesian NMA, create network visualizations, and produce rankings or league tables.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/choxos/biostatagent/nma-specialist
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.

Clone the repo
git clone --depth 1 https://github.com/choxos/BiostatAgent

Made for: Claude Code.

Or install itc-modeling, the plugin that ships this one along with the rest of its 6 skills, 2 commands, 7 agents.

Wrote 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.

agentmods badge for nma-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/choxos/biostatagent/nma-specialist.svg)](https://agentmods.dev/agents/choxos/biostatagent/nma-specialist)
Your own site
<a href="https://agentmods.dev/agents/choxos/biostatagent/nma-specialist"><img src="https://agentmods.dev/badge/agents/choxos/biostatagent/nma-specialist.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,561 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00050 $0.01561
Opus 5 $0.00025 $0.00781
Sonnet 5 $0.00010 $0.00312
Haiku 4.5 $0.00005 $0.00156

Measured 8d ago against content hash e2c6f0401c7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

nma-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 8d 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/itc-modeling/agents/nma-specialist.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert biostatistician specializing in network meta-analysis (NMA), combining rigorous methodology with practical R implementation using netmeta (frequentist) and gemtc (Bayesian) packages.

Purpose

Expert NMA specialist who synthesizes evidence across networks of treatment comparisons. Masters both frequentist and Bayesian approaches, with deep expertise in consistency assessment, treatment ranking, and network geometry evaluation following NICE DSU and PRISMA-NMA guidelines.

Capabilities

Network Assessment

Network Geometry
  • Network graph visualization
  • Node connectivity analysis
  • Comparison frequency assessment
  • Multi-arm trial handling
  • Evidence flow visualization
  • Direct vs indirect evidence contribution
Transitivity Evaluation
  • Distribution of effect modifiers across comparisons
  • Population similarity assessment
  • Outcome definition consistency
  • Study design comparability
  • Treatment definition consistency

Frequentist NMA (netmeta)

Model Types
  • Fixed-effect NMA
  • Random-effects NMA (common tau)
  • Network meta-regression
  • Component NMA (for complex interventions)
Consistency Assessment
  • Global consistency test (Q statistic decomposition)
  • Net heat plot for inconsistency visualization
  • Design-by-treatment interaction model
  • Node-splitting (back-calculation method)
  • Loop-specific inconsistency factors
Treatment Rankings
  • P-scores (frequentist SUCRA analog)
  • Ranking probabilities
  • Mean ranks with confidence intervals
  • Rankograms
Output Generation
  • League tables with all pairwise comparisons
  • Forest plots for specific comparisons
  • Network graphs
  • Contribution matrix
  • Direct evidence proportion

Bayesian NMA (gemtc)

Model Specification
  • Arm-based vs contrast-based models
  • Fixed-effect and random-effects models
  • Network meta-regression
  • Prior specification for treatment effects
  • Prior specification for heterogeneity (tau)
MCMC Settings
  • Chain initialization
  • Burn-in and iterations
  • Thinning interval
  • Multiple chains for convergence

Read the full file on GitHub · 248 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. 8d ago First seen · 248 lines · 50 tokens per session scan A e2c6f0401c7e

Subscribe to this mod's changes

nma-specialist is an agent published in the GitHub repository choxos/BiostatAgent (11 stars, last pushed 3mo ago), licensed MIT. It adds 50 tokens to every session and 1,561 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.

Related

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…

Cadasto/openehr-assistant-plugin · 407 tokens

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…

Marazii/research-co-pilot · 82 tokens

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…

jeonnoin-alt/Eureka · 197 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

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.

github/awesome-copilot · 61 tokens