Dev & Engineering ✓ OpenAI · Official code-reviewdefect-detectiongit-diffread-only-reviewtest-analysis

Review Agent Code Review Skill

Find actionable regressions in code changes through a read-only, defect-first review.

FollowSkills review · FSRS-2.0
Not recommended
52/ 100 5-point scale 2.6 / 5
Trust18 / 25 · 3.6/5

The evidence shows explicit read-only boundaries: do not modify files, create commits, push branches, post comments, or delegate; it also requires reading instructions, the full diff, tests, and call sites. This supports a relatively strong trust score. Points are deducted because user confirmation is not required, and the skill does not disclose possible access to sensitive code or credentials, command execution scope, data flow, failure recovery, or rollback.

Reliability8 / 20 · 2.0/5

The review workflow and merge-base comparison rules are concrete, and it requires continuing through the whole diff and validating call paths. Points are deducted because failure feedback is incomplete for missing targets, unavailable AGENTS.md files, unresolved comparison references, or unexecutable tests; static evidence cannot establish reproducibility, so the score remains at or below 10.

Adaptability9 / 15 · 3.0/5

The description matches the capability, covering uncommitted changes, base-branch diffs, commits, and custom review instructions; allow_implicit_invocation=false reduces false triggering. Points are deducted because non-fit cases, input boundaries, machine-readable output, Chinese interaction, and mainland-China environment support are not specified.

Convention8 / 15 · 2.7/5

The skill has clear steps, decision criteria, severity priorities, and output formatting. Its metadata includes name, display name, short description, and default prompt, while repository context supplies an Apache-2.0 license and official provenance. Points are deducted because the skill lacks installation or dependency notes, versioning, changelog, maintenance ownership, update path, FAQs, and troubleshooting guidance.

Effectiveness6 / 15 · 2.0/5

The task, review scope, and finding format are clear; severity ordering, file paths, and concise explanations produce directly usable core output. Points are deducted because no representative output or static evidence verifies the claimed completeness, and actual completion of the 'every actionable finding' and test-check requirements cannot be confirmed from files alone; static calibration caps this at 7.

Verifiability3 / 10 · 1.5/5

The skill text is auditable primary material, and its rules require code-path and test-based confirmation of findings. Points are deducted because there are no committed skill tests, CI coverage, third-party execution records, or corroborating sources; this review also did not execute anything, so verifiability remains limited.

Evidence confidence:Low Reviewed Jul 19, 2026 Reviewed revision 678157acaa81
The upstream repository has new commits since this review. The score still applies to the reviewed revision shown and may not cover the latest changes.
Before you use it
  • The skill may read sensitive repository contents, but it does not define credential redaction, minimum read scope, or data-exfiltration safeguards.
  • Failure handling and diagnostic feedback are underspecified when the target is unavailable, the comparison reference cannot be resolved, or tests cannot run.
  • Chinese-language output, cross-platform differences, and mainland-China environment boundaries are not documented.
  • No tests or execution evidence for the skill itself were provided, so completeness still requires human review.
See the full review method →

What it does & when to use it

Review Agent performs a read-only, defect-first review of a specified code change. It reads applicable AGENTS.md instructions, inspects the complete diff and surrounding code, and checks relevant tests and call sites. It supports uncommitted changes, base-branch reviews, commits, and custom review instructions. It reports only concrete findings an author would likely fix and does not alter files or post review comments.

Reads applicable AGENTS.md files; inspects the full diff and enough surrounding code for each changed path; identifies meaningful correctness, security, performance, or maintainability regressions introduced by the change; checks relevant tests and call sites; for base-branch reviews, resolves the comparison reference and uses the merge base; outputs findings ordered by P0–P3 severity with a title, file path, and line number; if no qualifying issue exists, outputs “No findings.” followed by an overall assessment and any material test gaps or residual risks.

  1. A maintainer wants a read-only review of uncommitted changes before creating a commit.
  2. A reviewer needs to check whether a particular commit introduced concrete regressions.
  3. A team is preparing a base-branch merge and needs the review to reflect the changes that would actually merge.
  4. Another agent needs to delegate an independent review without allowing file edits, commits, branch pushes, or posted comments.

Pros & cons

Pros
  • Inspects the complete diff and continues after finding the first issue.
  • Requires tests and call sites to be checked so findings are concrete and actionable.
  • Has a clear read-only boundary: it does not modify files, create commits, push branches, or post comments.
  • Orders findings by severity and requires a minimal code range overlapping the reviewed diff.
Limitations
  • The skill has no documented standalone installation flow; the README describes the overall Codex CLI collection.
  • The source provides no evidence of a test suite, platform coverage, or real review results.
  • It depends on access to the target code, diff, relevant context, tests, and call sites.
  • The source does not specify detailed handling for targets that are unavailable or cannot be resolved.

How to install

The skill is located at codex-rs/skills/src/assets/samples/review-agent/SKILL.md. The README documents installation for the overall Codex CLI and bundled skill collection, for example: npm install -g @openai/codex, followed by running codex. The source does not document a standalone installation or copying procedure for this skill.

How to use

Provide the skill through an Agent Skills-compatible client and specify the review target. For example: “Review the uncommitted changes in this repository and report every actionable finding.” You can also specify a base-branch diff, commit, or custom review instructions. The source does not define a more specific command, parameter format, or output API.

FAQ

Will it change my code?
No. It is explicitly read-only and must not modify files, create commits, push branches, or post review comments.
What changes can it review?
It can review uncommitted changes, a base-branch diff, a commit, or custom review instructions.
Does it report every possible concern?
It examines the whole diff but reports only issues that are meaningful, discrete, introduced by the change, demonstrable from the code path, and likely to be fixed by the author.
Does it require network access?
The SKILL.md describes no network calls; its review workflow concerns local instructions, files, diffs, tests, and call sites.

More skills from this repository

All from openai/codex

Dev & Engineering ✓ OpenAI · Official

PR Babysitter

Continuously track a GitHub pull request’s reviews, CI, and mergeability while handling safe fixes.

Dev & Engineering ✓ OpenAI · Official

Codex Issue Digest

Turns recent openai/codex bugs and enhancement requests into focused, owner-ready digests.

Design & Frontend ✓ OpenAI · Official

Codex Image Generation

Generate, edit, and prepare practical raster image assets directly within a project workflow.

Dev & Engineering ✓ OpenAI · Official

Codex Plugin Builder

Scaffold, validate, and maintain standards-shaped plugins for Codex.

Dev & Engineering ✓ OpenAI · Official

Codex Skill Installer

Install curated or repository-hosted Codex skills without manually assembling their files and paths.

Dev & Engineering ✓ OpenAI · Official

OpenAI Official Docs Assistant

Provides current, official-source guidance for OpenAI products, APIs, Codex, and model migrations.

Dev & Engineering ✓ OpenAI · Official

Codex Pull Request Editor

Professionally update one or more GitHub pull request titles and bodies around motivation, net changes, and verification.

Dev & Engineering ✓ OpenAI · Official

Remote Executor Integration Tests

Validate Codex integration behavior across local and remote execution environments.

Dev & Engineering ✓ OpenAI · Official

V8 Version Maintainer

Updates Codex’s pinned V8 versions and validates release-candidate and build-failure paths.

Dev & Engineering ✓ OpenAI · Official

Change Size Review Guide

Keep code changes reviewable by enforcing practical size limits and staging oversized work.

Dev & Engineering ✓ OpenAI · Official

Codex Path Types Guide

Choose Rust path types that preserve cross-platform URI handling and local filesystem behavior in Codex.

Dev & Engineering ✓ OpenAI · Official

Skill Creator Guide

A practical guide to designing, validating, and refining reusable Agent Skills.

Automation & Ops ✓ OpenAI · Official

CI Push Approval Assistant

Handle CI configuration push blocks and approval handoffs

Dev & Engineering ✓ OpenAI · Official

Code Review and Testing Guidance

Helps coding agents choose and structure tests for logic changes.

Dev & Engineering ✓ OpenAI · Official

Codex Bug Triage Assistant

Determines whether an openai/codex GitHub bug should be verified, clarified, or explained as expected behavior.

Dev & Engineering ✓ OpenAI · Official

Breaking Change Reviewer

Systematically detect compatibility risks across external integration surfaces before they reach users.

Dev & Engineering ✓ OpenAI · Official

Codex TUI Interactive Testing Guide

A focused workflow for launching Codex TUI and validating changes with trace logs.

Dev & Engineering ✓ OpenAI · Official

Context Governance

Keep coding-agent context incremental, cache-stable, and strictly bounded.

Dev & Engineering ✓ OpenAI · Official

Pull Request Code Review

Orchestrate a final pull request review and consolidate every actionable finding from specialized reviewers.

Related skills