review-r

name	review-r
description	Review existing R analysis code for quality and reproducibility.

Review R Scripts

Run the comprehensive R code review protocol.

Steps

1. Identify scripts to review:

   • If $ARGUMENTS is a specific .R filename: review that file only
   • If $ARGUMENTS is a name pattern (e.g., model_name): glob for matching .R files. If multiple matches, ask the user to choose conversationally. Do not use request_user_input here because the selection may be multi-file and Codex question UI is single-choice only.
   • If $ARGUMENTS is all: review all R scripts in scripts/R/ and Figures/*/
   • If $ARGUMENTS is empty, glob for all .R files. If multiple are found, ask the user to choose conversationally as above.

2. For each script, read agents/r-reviewer.md and apply that review protocol.

   • Follow the full protocol in the agent instructions
   • Read rules/r-code-conventions.md for current standards
   • Create quality_reports/ if it is missing before saving
   • Save the report to quality_reports/[script_name]_r_review.md
   • If the user explicitly requested delegated review, you may run the r-reviewer as a separate subagent and merge the result

3. After all reviews complete, present a summary:

   • Total issues found per script
   • Breakdown by severity (Critical / High / Medium / Low)
   • Top 3 most critical issues

4. IMPORTANT: Do NOT edit any R source files. Only produce reports. Fixes are applied after user review.