code-review

A command that reviews uncommitted R code changes for security problems, quality issues, missing tests, documentation gaps, and R-specific best practices.

In plain words
What is it for?
Run it after writing R code to inspect the current changes and receive severity-rated findings with an approval or fix recommendation.
Why use it?
It provides a check before committing changes, when mistakes or exposed sensitive information are still easier to fix.

Command

Part of the claude-code-r-skills plugin — 8 skills, 4 commands, 3 agents, 4 hooks 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 commands/ab604/claude-code-r-skills/code-review
Clone the repo
git clone --depth 1 https://github.com/ab604/claude-code-r-skills

Or install claude-code-r-skills, the plugin that ships this one along with the rest of its 8 skills, 4 commands, 3 agents, 4 hooks.

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 708 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 $0.00022 $0.00708
Opus 5 $0.00011 $0.00354
Sonnet 5 $0.00004 $0.00142
Haiku 4.5 $0.00002 $0.00071

Measured 3d ago against content hash 8a1972bbf313, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-review 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.

commands/code-review.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/code-review - Code Quality Review

Review uncommitted code changes for security vulnerabilities, code quality issues, and R best practices.

Review Process

  1. Identify Changes - git diff --name-only HEAD
  2. Review Each File - Check against criteria below
  3. Generate Report - Severity-rated findings
  4. Block or Approve - Based on issue severity

Review Categories

Security

  • No hardcoded credentials (API keys, passwords, tokens)
  • No sensitive data exposure in outputs or logs
  • Safe file path handling
  • Parameterized database queries
  • Input validation in Shiny/Plumber apps

Code Quality (R-Specific)

  • Functions under 50 lines
  • Files under 400 lines (ideally 200-300)
  • No deep nesting (max 4 levels)
  • Proper error handling with informative messages
  • Type-stable outputs (avoid sapply, use map_*)
  • Modern tidyverse patterns (native pipe, .by, join_by)

Best Practices

  • Meaningful variable and function names (snake_case)
  • No code duplication
  • Tests included for new functionality
  • Documentation for exported functions
  • No global state modification

Severity Levels

Level Action Examples
CRITICAL Must fix before commit Hardcoded secrets, SQL injection
HIGH Should fix before commit Missing error handling, no tests
MEDIUM Fix when possible Style issues, minor refactoring
LOW Consider for improvement Documentation, naming suggestions

Report Format

## Code Review: [files reviewed]

### CRITICAL Issues
- **[file:line]** - [description]
  - Fix: [suggested fix]

### HIGH Issues
- **[file:line]** - [description]

### MEDIUM Issues
- **[file:line]** - [description]

### Suggestions
- [improvement ideas]

## Verdict: APPROVED / NEEDS CHANGES

Blocking Criteria

Block commit if:

  • Any CRITICAL issues found
  • More than 2 HIGH issues found
  • Security vulnerabilities present

Read the full file on GitHub · 108 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 · 108 lines · 22 tokens per session scan A 8a1972bbf313

Subscribe to this mod's changes

code-review is a command published in the GitHub repository ab604/claude-code-r-skills (197 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 708 once invoked, about $0.0001 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.