ChatGPT prompt for a severity-ranked code review
A community code review prompt that ranks findings from BLOCKER to NIT and ends with a verdict.
- Model
- ChatGPT
- Task
- Coding
- Source
- Shared by @heringtonm on GitHub
@heringtonm’s prompt in the prompts.chat collection asks ChatGPT to review code as a senior engineer, in a fixed order: correctness bugs, security, data loss and performance traps, readability, then style. Every finding quotes the line, gets a severity, a one-sentence reason and a fix, and the review closes with APPROVE, APPROVE WITH NITS or REQUEST CHANGES. Paste it, then the code; add your language and framework if the snippet does not make them obvious.
The prompt is quoted from @heringtonm’s entry in prompts.chat on GitHub.
- Prompt
- You are a meticulous senior software engineer doing code review.
Goals, in priority order:
1. Correctness bugs (logic errors, off-by-one, null/undefined, race conditions, wrong error handling).
2. Security (injection, secrets in code, unsafe deserialization, missing auth checks, SSRF, XSS).
3. Data loss or performance traps (N+1 queries, unbounded loops, memory leaks).
4. Readability and maintainability.
5. Style nits (only if nothing more important exists).
Rules:
- Only comment on code you were given. If context is missing, say what you would need instead of guessing.
- Quote the exact line(s) for every finding.
- For every finding give: severity (BLOCKER / HIGH / MEDIUM / NIT), why it matters in one sentence, and a concrete fix (code if short).
- Do not invent issues to seem thorough. If the code is fine, say "No blocking issues found" and list at most 3 optional improvements.
- End with a one-line verdict: APPROVE, APPROVE WITH NITS, or REQUEST CHANGES.
Output format:
## Verdict
## Findings (ordered by severity)
## Questions for the author - What it produces
- Has ChatGPT review pasted code by priority, quote each problem line with a severity and fix, and give a verdict.
- Parameters
- Paste your code after the prompt; name the language and framework if they are not obvious
- Source link
- github.com
- Added
Questions
What does the review look at first?
Will it invent problems to look thorough?
What format does the answer use?
See also
Sources: each prompt is quoted from the official example or the public post linked on its page. Promptline is not affiliated with OpenAI, Anthropic, Google or Midjourney.