Review code changes without modifying files, checking surrounding code, tests, and callers for defects introduced by the change. Receive actionable findings ranked by severity, with precise file locations and a brief assessment of remaining risks.
Perform a read-only, defect-first review of a specified code change and return every actionable finding. Use when another agent delegates review of uncommitted changes, a base-branch diff, a commit, or custom review instructions.
Reviews code changes without modifying files and reports defects introduced by those changes. It examines the complete diff, surrounding code, relevant tests, and callers to identify problems whose actual impact can be explained. Each finding includes its severity, file and line number, and the scenario in which the problem occurs. The review continues through the entire target instead of stopping at the first issue.
Use it to review uncommitted changes, changes being merged into a base branch, or a particular commit. It helps you identify concrete defects the author can consider fixing, while avoiding reports about existing problems or differences in personal preference.
It does not edit files, commit, push, or post review comments. Branch comparisons use commands such as git merge-base. If no qualifying issues are found, it returns No findings. The result ends with an overall assessment, significant test gaps, and remaining risks.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI rated this skill on four points using only the contents of its SKILL.md. Stars and popularity are not taken into account.
The total counts each point as A = 25, B = 15, C = 5. Rated by AI (OpenAI Codex) as of Oct 20, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
Inspect the requested target directly and return every finding that the author would likely fix. Do not modify files, create commits, push branches, post review comments, or delegate the review to another agent.
AGENTS.md instructions.For a base-branch review, compare the changes that would actually merge rather than diffing
directly against the branch tip. Resolve the comparison ref to the branch's upstream when that
upstream exists and is ahead of the local branch; otherwise use the local branch. Run
git merge-base HEAD <comparison-ref>, then inspect git diff <merge-base-sha>. If the local
branch cannot be resolved, try its configured upstream explicitly before reporting that the target
is unavailable.
Flag an issue only when all of these are true:
Do not flag speculative concerns, pre-existing problems, intentional behavior changes, or style nits that do not obscure the code.
Present findings first, ordered by severity. Use one entry per issue in this form:
[P1] Imperative finding title — path/to/file.rs:line
Follow the title with one short paragraph explaining the affected scenario and why the behavior is wrong. Keep the cited range as small as possible and make sure it overlaps the reviewed diff.
Use these priorities:
P0: universal release blocker or critical failure.P1: urgent defect that should be fixed next.P2: ordinary defect that should be fixed.P3: low-impact issue that is still worth fixing.If there are no qualifying findings, say No findings. Do not invent a finding to fill the result.
After the findings, add a brief overall assessment and mention any material test gaps or residual
risks.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Create photos, illustrations, product mockups, and other bitmap images, or edit existing images by replacing backgrounds, removing objects, and making transparent cutouts. Use reference images to guide style, composition, or visual variants.
Find guidance on Codex settings, pricing, and OpenAI products and APIs using current official documentation. Get cited answers for setup, troubleshooting, model comparisons, migration planning, and prompt changes, with uncertainty stated when sources are inconclusive.
Create or update Codex skills that capture task-specific guidance. Organize instructions in SKILL.md, add useful scripts, references, or assets when needed, and validate the structure while keeping the skill focused on its intended work.
Browse available Codex skills and install them from a curated list or a specified GitHub location. Supports experimental skills, private repositories with credentials, and installing several skill folders in one operation.