r-reviewer

r-reviewer is an agent for Claude Code from pedrohcgs/claude-code-my-workflow. It costs 34 tokens per session (2,096 once invoked), scanned A, original, MIT.

A review assistant for R scripts used in academic research, with attention to code quality, reproducibility, figures, and project conventions.

In plain words
What is it for?
Use it to review script structure, headers, console output, data and computation flow, figure generation, exports, and compliance with R coding standards.
Why use it?
It finds problems that can make research code difficult to understand, rerun, or trust before publication or teaching use.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Good fit Use it to review script structure, headers, console output, data and computation flow, figure generation, exports, and compliance with R coding standards.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/pedrohcgs/claude-code-my-workflow/r-reviewer
About the project

claude-code-my-workflow is a forkable setup for using Claude Code to produce and review academic papers, slides, data analyses, and replication packages. Researchers use its agents, skills, rules, hooks, and quality checks to coordinate these tasks and verify their results. The catalogue entries define the reusable workflow components for Claude Code.

pedrohcgs/claude-code-my-workflow · 1,567 stars · on GitHub · psantanna.com

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/pedrohcgs/claude-code-my-workflow

Made for: Claude Code.

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 r-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/pedrohcgs/claude-code-my-workflow/r-reviewer.svg)](https://agentmods.dev/agents/pedrohcgs/claude-code-my-workflow/r-reviewer)
Your own site
<a href="https://agentmods.dev/agents/pedrohcgs/claude-code-my-workflow/r-reviewer"><img src="https://agentmods.dev/badge/agents/pedrohcgs/claude-code-my-workflow/r-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,096 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 $0.00034 $0.02096
Opus 5 $0.00017 $0.01048
Sonnet 5 $0.00007 $0.00419
Haiku 4.5 $0.00003 $0.00210

Measured 9d ago against content hash 52ec6032439f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

r-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 9d 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.

.claude/agents/r-reviewer.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Senior Principal Data Engineer (Big Tech caliber) who also holds a PhD with deep expertise in quantitative methods. You review R scripts for academic research and course materials.

Your Mission

Produce a thorough, actionable code review report. You do NOT edit files — you identify every issue and propose specific fixes. Your standards are those of a production-grade data pipeline combined with the rigor of a published replication package.

Review Protocol

  1. Read the target script(s) end-to-end
  2. Read .claude/rules/r-code-conventions.md for the current standards
  3. Check every category below systematically
  4. Produce the report in the format specified at the bottom

Review Categories

1. SCRIPT STRUCTURE & HEADER

  • Header block present with: title, author, purpose, inputs, outputs
  • Numbered top-level sections (0. Setup, 1. Data/DGP, 2. Estimation, 3. Run, 4. Figures, 5. Export)
  • Logical flow: setup → data → computation → visualization → export

Flag: Missing header fields, unnumbered sections, inconsistent divider style.

2. CONSOLE OUTPUT HYGIENE

  • message() used sparingly — one per major section maximum
  • No cat(), print(), sprintf() for status/progress
  • No ASCII-art banners or decorative separators printed to console
  • No per-iteration printing inside simulation loops

Flag: ANY use of cat() or print() for non-debugging purposes.

3. REPRODUCIBILITY

  • set.seed() called ONCE at the top of the script (never inside loops/functions)
  • All packages loaded at top via library() (not require())
  • All paths relative to repository root
  • Output directory created with dir.create(..., recursive = TRUE)
  • No hardcoded absolute paths
  • Script runs cleanly from Rscript on a fresh clone

Flag: Multiple set.seed() calls, require() usage, absolute paths, missing dir.create().

4. FUNCTION DESIGN & DOCUMENTATION

  • All functions use snake_case naming
  • Verb-noun pattern (e.g., run_simulation, generate_dgp, compute_effect)
  • Every non-trivial function has roxygen-style documentation
  • Default parameters for all tuning values
  • No magic numbers inside function bodies
  • Return values are named lists or tibbles (not unnamed vectors)

Read the full file on GitHub · 187 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. 9d ago First seen · 187 lines · 34 tokens per session scan A 52ec6032439f

Subscribe to this mod's changes

r-reviewer is an agent published in the GitHub repository pedrohcgs/claude-code-my-workflow (1,567 stars, last pushed 15d ago), licensed MIT. It adds 34 tokens to every session and 2,096 once invoked, about $0.0002 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

r-reviewer

R code reviewer for academic scripts. Checks code quality, reproducibility, figure generation patterns, and theme compliance. Use after writing or modifying R scripts.

brycewang-stanford/Auto-Empirical-Research-Skills · 34 tokens

simulator

Monte Carlo Simulation Pipeline — DGP design and execution.

statsclaw/statsclaw · 13 tokens

reviewer

Pipeline Convergence & Quality Gate — cross-compares all pipelines.

statsclaw/statsclaw · 15 tokens

analysis-reviewer

Adversarial reviewer of a data analysis, notebook, script, or result for the silent-failure classes that pass ordinary code review but produce wrong answers — unchecked joins, leakage, bad controls, unreconciled totals, undefined metrics, identification gaps, fished specifications, implausible magnitudes, the…

lancegui/causal-powers · 162 tokens

robustness-runner

Executes ONE pre-specified task against an already-validated dataset or model — a robustness specification, placebo/falsification test, alternative design, subsample cut, or a structural unit of work (a Monte-Carlo recovery rep at a given true-θ / seed / starting value, or one counterfactual scenario with a stated…

lancegui/causal-powers · 155 tokens

stata-analyst

End-to-end statistical analysis agent for Stata. Handles the full workflow from data loading through estimation, results retrieval, and graph export. Invoke when user wants a complete analysis, asks to "run a regression", "analyze this dataset", or describes a multi-step econometric workflow.

tmonk/mcp-stata · 62 tokens