Region

Code Review prompts

Reviews for correctness, security and style.

6 prompts
Coding & Dev ¶ TEXT

Senior Engineer Code Review

A staff-level code review that separates blocking issues from nitpicks, explains the why behind every finding, and suggests concrete fixes.

✓ GPT-5✓ Claude Opus 4.5Claude Sonnet 4.5
★ 128⧉ 941◌ 0LLM Atlas Team · 2mo ago
Coding & Dev ¶ TEXT

Security-Focused Code Review (OWASP Top 10)

Audits code specifically against the OWASP Top 10 with severity ratings, proof-of-concept attack scenarios, and hardened replacement code.

✓ GPT-5Claude Opus 4.5
★ 96⧉ 712◌ 0LLM Atlas Team · 2mo ago
Coding & Dev ¶ TEXT

Two-Pass Pull Request Review

Reviews a diff in two deliberate passes — architecture and approach first, then line-level detail — so big problems surface before small ones.

GPT-5Claude Sonnet 4.5
★ 54⧉ 388◌ 0LLM Atlas Team · 1mo ago
Coding & Dev ¶ TEXT

Silent Failure & Error-Handling Audit

Audits code for the failures that page you at 2am: swallowed exceptions, ignored return values, missing timeouts, and partial writes that leave state corrupted.

GPT-5✓ Claude Opus 4.5
★ 41⧉ 305◌ 0LLM Atlas Team · 1mo ago
Coding & Dev ¶ TEXT

Bug-Only Diff Review (Zero Style Comments)

A review mode that reports nothing but genuine defects — every finding must name the input or sequence of events that triggers wrong behavior, or it does not get reported.

GPT-5✓ Claude Sonnet 4.5
★ 34⧉ 248◌ 0LLM Atlas Team · 1mo ago
Coding & Dev ¶ TEXT

Architecture Review — Boundaries & Coupling

Reviews a codebase at the module level instead of line level: dependency direction, leaky abstractions, god modules, and the two or three seams worth fixing first.

o3Claude Opus 4.5
★ 27⧉ 175◌ 0LLM Atlas Team · 1mo ago
LLM Atlas

A free map of prompts that actually work — tested on real models, starred by real people.

© 2026 LLM AtlasPrompts default to CC0 unless stated.