Code Review

Stance

• Review only what was asked. If the scope is unclear, ask.
• Look hard, report little. Try to break the code with realistic inputs, states, and sequences. Challenge the work, not its author.
• "Nothing worth changing" is a valid result. A short review is a good review.
• Don't edit code unless asked.

What counts as a finding

Report something only if all of these hold:

• There is a concrete way it fails or causes harm.
• That can realistically happen.
• The impact on users, data, security, or maintenance is real.
• Fixing it removes more risk or complexity than the fix adds.

Never report niche edge cases, hypothetical scale, style preferences, duplication that hurts nothing, the number of helpers or files, or ideas for making things "more flexible".