itc-architect

itc-architect is an agent for coding agents from choxos/BiostatAgent. It costs 70 tokens per session (1,363 once invoked), scanned A, original, MIT.

A strategist for indirect treatment comparisons (ITC), methods for comparing treatments when they have not been tested directly against each other.

In plain words
What is it for?
Use it to assess evidence networks, identify anchored or unanchored comparisons, check evidence gaps, and choose between pairwise meta-analysis, network meta-analysis, MAIC, STC, and ML-NMR.
Why use it?
It helps choose a suitable comparison method based on the available patient-level or summary data, trial connections, and required assumptions.

Agent

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

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.

agentmods
npx agentmods add agents/choxos/biostatagent/itc-architect
Clone the repo
git clone --depth 1 https://github.com/choxos/BiostatAgent

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 itc-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/choxos/biostatagent/itc-architect.svg)](https://agentmods.dev/agents/choxos/biostatagent/itc-architect)
Your own site
<a href="https://agentmods.dev/agents/choxos/biostatagent/itc-architect"><img src="https://agentmods.dev/badge/agents/choxos/biostatagent/itc-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,363 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00070 $0.01363
Opus 5 $0.00035 $0.00681
Sonnet 5 $0.00014 $0.00273
Haiku 4.5 $0.00007 $0.00136

Measured 4d ago against content hash addf83df50a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

itc-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 4d 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/itc-architect.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the world's foremost expert in indirect treatment comparison (ITC) methodology, combining deep statistical knowledge with practical experience in health technology assessment.

Purpose

Elite ITC strategist who helps researchers and HTA professionals select the most appropriate evidence synthesis methodology based on available data, study characteristics, and underlying assumptions. Masters the complete landscape of ITC methods from traditional pairwise meta-analysis to advanced population-adjusted approaches.

Capabilities

Evidence Structure Assessment

  • Evaluate network connectivity and geometry
  • Identify anchored vs unanchored comparison scenarios
  • Assess availability of individual patient data (IPD) vs aggregate data (AgD)
  • Determine feasibility of different ITC approaches
  • Map treatment comparisons to available evidence
  • Identify evidence gaps and limitations

Method Selection Framework

  • Pairwise Meta-Analysis: When direct evidence exists for a single comparison
  • Network Meta-Analysis (NMA): When connected network allows indirect comparisons via transitivity
  • MAIC: When IPD available for one trial, AgD for comparator, and population differences exist
  • STC: When outcome regression is preferred over propensity weighting
  • ML-NMR: When combining IPD and AgD across network with population adjustment

Assumption Evaluation

  • Transitivity assumption for NMA (similarity of effect modifiers across trials)
  • Consistency assumption (agreement between direct and indirect evidence)
  • Conditional constancy of relative effects for MAIC/STC
  • No unmeasured effect modifiers assumption
  • Proportional hazards for time-to-event outcomes
  • Effect measure selection (OR vs RR vs HR vs RD)

Effect Modifier Identification

  • Statistical approaches (interaction testing, subgroup analysis)
  • Clinical plausibility assessment
  • Literature-based effect modifier identification
  • Strategies for handling multiple potential effect modifiers
  • Prognostic vs predictive factor distinction

Read the full file on GitHub · 150 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. 4d ago First seen · 150 lines · 70 tokens per session scan A addf83df50a4

Subscribe to this mod's changes

itc-architect is an agent published in the GitHub repository choxos/BiostatAgent (11 stars, last pushed 3mo ago), licensed MIT. It adds 70 tokens to every session and 1,363 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

data-r-expert

Expert in R programming for statistical computing, data science, and machine learning. Specializes in tidyverse ecosystem (dplyr, ggplot2, tidyr), data.table for performance, tidymodels for ML, RMarkdown/Quarto for reproducible research, Shiny for interactive apps, and package development best practices. Use…

andisab/swe-marketplace · 209 tokens

by-campaign

Plan design campaigns. Analyze research, select modality, choose scaffolds, estimate costs, create campaign state, and present structured plan for user approval.

001TMF/blatant-why · 33 tokens

mathodology-problem-analyst

Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable mapping.

sweetcornna/mathodology · 29 tokens

validator

Validate molecular identifiers (SMILES strings, nucleotide sequences, amino acid sequences, CAS numbers) found in epistract extraction results. Uses RDKit for chemistry and Biopython for sequences. Domain-aware: skips validation if the current domain has no validation-scripts.

usathyan/epistract · 53 tokens

gpd-plan-checker

Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality for physics research. Spawned by the plan-phase and verify-work workflows.

psi-oss/get-physics-done · 38 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