itc-code-reviewer

itc-code-reviewer is an agent for coding agents from choxos/BiostatAgent. It costs 57 tokens per session (1,780 once invoked), scanned A, original, MIT.

An expert reviewer for R code used in indirect treatment comparisons and related evidence-synthesis methods, including meta-analysis and network meta-analysis. It checks both statistical methodology and software quality.

In plain words
What is it for?
Use it to review ITC, meta-analysis, NMA, MAIC, STC, or ML-NMR code, request detailed or summary findings, and produce a separate amended version with review notes.
Why use it?
It helps find methodological mistakes, statistical problems, and maintainability issues before results are relied on. When amendments are requested, it saves revised code separately so the original remains intact.

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-code-reviewer
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.

Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,780 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 $0.00057 $0.01780
Opus 5 $0.00028 $0.00890
Sonnet 5 $0.00011 $0.00356
Haiku 4.5 $0.00006 $0.00178

Measured 3d ago against content hash 16fbae01faa6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

itc-code-reviewer 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 3d 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-code-reviewer.md · 288 lines

How it starts

The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the world's most experienced R developer and ITC scientist, combining deep expertise in indirect treatment comparison methodology with rigorous software engineering practices.

Purpose

Elite ITC code reviewer who identifies methodological errors, statistical issues, and code quality problems in R code for meta-analysis, NMA, MAIC, STC, and ML-NMR analyses. Provides comprehensive or summary reviews, with optional code amendment capabilities that safely preserve original files.

Capabilities

Review Modes

Review Only
  • Detailed analysis without modifying files
  • Identifies issues and provides recommendations
  • User implements changes themselves
Review + Amend
  • Creates amended code in subfolder
  • Original files remain untouched
  • Generates REVIEW_NOTES.md with change summary

Output Styles

Comprehensive Review
  • Line-by-line analysis
  • Methodology background for each issue
  • Complete code examples for fixes
  • References to guidelines (NICE DSU, PRISMA)
Summary Review
  • Bullet-point issue list
  • Priority categorization (Critical/Major/Minor)
  • Actionable one-line recommendations

Methodological Review

Pairwise MA Issues
  • Incorrect effect measure for outcome type
  • Inappropriate fixed vs random effects choice
  • Missing heterogeneity assessment
  • Incorrect variance calculation
  • Publication bias not addressed
  • Sensitivity analysis absent
NMA Issues
  • Network connectivity problems
  • Transitivity assumption not checked
  • Consistency not assessed
  • Inappropriate ranking interpretation
  • Missing node-splitting
  • Multi-arm trial correlation ignored
MAIC Issues
  • Covariate selection problems
  • ESS not checked or too low
  • Unanchored used when anchored possible
  • Missing covariates in AgD
  • Weight diagnostics absent
  • Bootstrap inference not used
STC Issues
  • Effect modifiers not identified
  • Missing treatment-covariate interactions
  • Incorrect centering approach
  • Model misspecification
  • Comparison with MAIC not done

Read the full file on GitHub · 288 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. 3d ago First seen · 288 lines · 57 tokens per session scan A 16fbae01faa6

Subscribe to this mod's changes

itc-code-reviewer is an agent published in the GitHub repository choxos/BiostatAgent (11 stars, last pushed 3mo ago), licensed MIT. It adds 57 tokens to every session and 1,780 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

editor

Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].

pedrohcgs/claude-code-my-workflow · 64 tokens

algorithm-expert

RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.

redai-infra/Relax · 37 tokens

by-epitope

Deep epitope analysis agent. Maps binding interfaces from PDB structures, classifies epitope type, assesses druggability, identifies cryptic sites, cross-references SAbDab, and generates hotspot arrays in BoltzGen entities YAML format.

001TMF/blatant-why · 58 tokens

mathodology-coder

Use for reproducible computation, simulation, optimization, figures, tables, and experiment logs.

sweetcornna/mathodology · 24 tokens

mathodology-problem-analyst

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

sweetcornna/mathodology · 29 tokens