skills.rest
swat9013
swat9013COMMUNITY
Explore all skills by this author →
GitHub

codex-code-review

Review mixed code and documentation repositories for architecture, test strategy, API design, and behavior.

Updated Aug 27, 2026
Search Tags:#architecture#code review#api design#test strategy#design review#gpt-5.2-codex#cursor agent
One-click install
npx skills add https://github.com/swat9013/dotfiles --skill codex-code-review-swat9013
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: codex-code-review
Source: https://github.com/swat9013/dotfiles/tree/main/.claude-global/skills/codex-code-review
Command: npx skills add https://github.com/swat9013/dotfiles --skill codex-code-review-swat9013

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates high-level architecture and design reviews for repositories, consolidating findings across architecture, test strategy, API design, and behavior so maintainers can prioritize impactful design fixes instead of low-level stylistic issues.

Core Features & Use Cases

  • Model-driven reviews: Selects gpt-5.2-codex for code and gpt-5.2 for documentation to produce focused, model-appropriate analyses.
  • Sandboxed, repeatable execution: Uses Cursor Agent with sandbox enabled by default to limit workspace access and ensure safe analysis.
  • Parallel processing and structured output: Runs separate agents for code and docs in parallel, merges JSON outputs, deduplicates findings, and emits a template-based markdown report.
  • Use Case: On a mixed TypeScript and docs repository, run the skill to identify layer violations, missing critical tests, API contract issues, and behavioral mismatches, then generate actionable remediation suggestions.

Quick Start

Run the Codex Code Review skill to analyze the repository's code and documentation for architecture, test strategy, API design, and behavior and write a consolidated codex-review.md file.

Frequently Asked Questions about codex-code-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate architecture and design reviews for a mixed codebase?▼

Test strategy evaluation assesses missing critical tests by analyzing mixed repositories containing code and documentation files. It identifies behavioral mismatches and gaps in test coverage, then outputs structured JSON findings that are merged into a consolidated remediation report.

Can I use Cursor Agent to perform sandboxed code and documentation analysis?▼

API design review identifies API contract issues and behavioral mismatches by analyzing mixed repositories containing code and documentation files. It evaluates API design consistency, deduplicates findings across parallel agent runs, and outputs actionable remediation suggestions in a structured markdown report.

How does model selection work between gpt-5.2-codex and gpt-5.2 for code reviews?▼

Sandboxed execution limits workspace access during architecture and design reviews by enabling Cursor Agent sandbox mode by default. This ensures safe, repeatable analysis of source code and technical documentation without risking unintended workspace modifications during parallel processing.

What is the best way to consolidate JSON outputs from parallel code review agents?▼

Layer violations are identified by analyzing mixed repositories containing code and documentation files to evaluate architecture and design consistency. The review detects layer boundary breaches, deduplicates findings across parallel agent runs, and generates structured remediation suggestions in markdown format.

Related Skills

Explore More Software Engineering Skills→
tiagofurtiagofur

Documentation

Generate and update Markdown documentation from codebases and design notes.

Community
Intermediate
Nikhil-Chopra-7Nikhil-Chopra-7
1

code-reviewer

Identify frontend code convention violations and output severity-based reports.

Community
Advanced
creator-hiancreator-hian
10

codex-cli

Automate Codex CLI code analysis, review, and validation tasks.

Community
Intermediate
daffy0208daffy0208
34

Quality Assurance

Automate QA with test pyramids, code-quality checks, and phase-transition gates.

Community
Intermediate