Engineering Code Review Role Prompt

Senior Code Reviewer Role Prompt

A principal-level code reviewer role prompt — blast-radius thinking, severity-ranked findings, and style left to the linter where it belongs.

Overview

'Review my code' without a role gets you a line-by-line commentary that treats a typo and an injection risk as equals. This role prompt builds the reviewer experienced teams actually have: one who reviews the change's blast radius rather than just its lines, separates must-fix from nit explicitly, and leaves style to the linter so attention goes to correctness, security, and design. The principal level adds reversibility awareness — extra caution exactly where mistakes are expensive.

How to use this resource

  1. Open in the generator

    Principal level, Technology industry, Risk-Aware style, Correctness + Security focus — pre-set.

  2. Generate, paste, then add the diff

    Role prompt first, then the code or diff with one line of context about what it's supposed to do.

  3. Demand the severity split

    The must-fix/should-fix/nit contract is the difference between a review and a reaction.

Why This Works

  • Blast-radius framing catches the integration bugs that line-by-line review misses
  • Severity discipline makes the feedback actionable in priority order
  • Questions-over-verdicts keeps the review collaborative — the reviewer can be wrong too

Best for

  • Solo developers without access to senior review
  • Teams that want a consistent first-pass review bar
  • Security-sensitive changes that deserve paranoid eyes

Not for

  • An automated PR-review pipeline with output contracts — the System Prompt Generator's code review assistant covers that
  • Style and formatting enforcement — configure a linter instead

Use cases

  • Getting severity-ranked review feedback instead of a flat comment list
  • Pre-reviewing your own PR before human reviewers see it
  • Teaching junior developers what experienced reviewers look for

FAQ

What output format does the senior code reviewer role prompt produce?

It outputs findings tagged by severity — must-fix, should-fix, or nit — each with a file reference, so a typo and an injection risk never sit at the same priority. When it rejects an approach it proposes the alternative rather than just objecting. You paste your diff and run it in ChatGPT, Claude, or Gemini — the severity contract is the format, not an automated pipeline.

Why does this code review prompt skip style and formatting comments?

By design it treats style as the linter's job and points the reviewer's attention at logic, security, and design instead. That's why it won't fill the review with spacing and naming nits — those are cheaper to enforce automatically, so spending a human-style review on them wastes it. Configure a linter for formatting and let this prompt focus on correctness and security, its two weighted focus areas.

When should I not use the code reviewer role prompt for reviews?

Don't reach for it when you need an automated PR-review pipeline with a fixed output contract wired into CI — this is a conversational role prompt you drive by hand, one diff at a time. It also won't replace a linter for style enforcement. Use it when you want a principal-level pass on correctness and security before you open the PR, not an unattended gate.

Does this role prompt actually review my code, or do I still run it myself?

You run it yourself — NewPrompt gives you the role prompt, and you paste it plus your diff into your own AI tool to get the review. The findings are a prioritized, senior-level read on correctness and security, not a guarantee that every bug or vulnerability is caught. Treat must-fix items as a strong signal to verify, and keep a human reviewer accountable for merging.

More resources from Role Prompt Generator

Resources that pair well

Related tools

Guides for this resource

Tip: Save time by exploring related resources and tools that integrate with this resource.