Skip to main content
skill CX Codex

reviewing-code · julianobarbosa — Claude Code skill: code review and installation

The reviewing-code skill asks Codex to review code for bugs, security concerns, and implementation practices. Use it when you want a second assessment of a file or change.

MIT 101 installs ★ 17 updated 2026-10-14

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add julianobarbosa/claude-code-skills --skill reviewing-code -a claude-code
Open on GitHub

What reviewing-code does

The skill calls mcp__codex__spawn_agent to send Codex a code-review task. Ask it to assess implementation quality, look for edge cases or security issues, or check a specific snippet for performance concerns and language conventions.

Codex can rank findings differently across runs, so pin the model version when repeatable results matter. Staged changes that have not been committed are outside its default view; large diffs above 500 LOC are summarized rather than checked line by line. Pass staged changes explicitly and split broad reviews into focused file groups.

What it helps with

  • spot likely bugs and edge cases
  • check code for security flaws
  • assess whether an implementation follows language practices
  • review code quality and patterns
  • identify performance concerns

Example prompts for the agent

  • Review src/auth.ts for bugs and security risks.
  • Check this Go snippet against common Go conventions.
  • Look over these changes for performance problems and explain the risks you find.

How to install reviewing-code

1Skills CLI (Vercel)

npx skills add julianobarbosa/claude-code-skills --skill reviewing-code -a claude-code

2Manually: put the files in place

~/.claude/skills/reviewing-code/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/reviewing-code/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about reviewing-code

How do I install reviewing-code in Claude Code?

Run npx skills add julianobarbosa/claude-code-skills --skill reviewing-code -a claude-code, then use ~/.claude/skills/reviewing-code/SKILL.md.

What does reviewing-code do?

It sends a review request to Codex, which can examine code quality, potential bugs, security issues, and implementation practices.

Does Codex review staged changes?

Staged changes that have not been committed are not part of Codex's default input. Pass them with --include-staged or provide a diff through a pipe.

Source text

SKILL.md · MIT
---
name: reviewing-code
description: Get code review from Codex AI for implementation quality, bug detection, and best practices. Use when asked to review code, check for bugs, find security issues, or get feedback on implementation patterns.
allowed-tools: Read, Grep, Glob, mcp__codex__spawn_agent
---

# Code Review with Codex

Use `mcp__codex__spawn_agent` for code review.

## When to Use

- Review code quality and patterns
- Find potential bugs or edge cases
- Validate against best practices
- Check for security issues

## Usage

```json
{
  "prompt": "Review this code for [quality/bugs/security]: [code or file]"
}
```

## Prompt Examples

- "Review for code quality and Go best practices: [code]"
- "Analyze for security vulnerabilities: [code]"
- "Review for performance issues: [code]"
- "Does this follow idiomatic patterns? [code]"

---

## Gotchas

- **Codex review is non-deterministic** — same code with different invocations gets different priority orderings; pin model version when reproducibility matters.
- **Codex doesn't see staged-but-uncommitted changes by default** — pass them explicitly via `--include-staged` or piped diff.
- **Diff-only review misses cross-file effects** — a renamed function's callsite in another file isn't in the diff, so the rename's blast radius isn't surfaced.
- **Review output ranks by Codex's internal severity heuristic** — not by user-defined priority; re-rank manually for project-specific concerns.
- **Whitespace-only diffs trigger reviews** — pass `--ignore-whitespace` or you get noise.
- **Large diffs (>500 LOC) get summarized**, not reviewed line-by-line — split into focused reviews per file group.

© julianobarbosa · MIT · julianobarbosa/claude-code-skills

Similar skills

All skills for Code review and refactoring →

reviewing-code by other authors comes first.

reviewing-code spencerpauly reviewing-code — a skill that walks your code through a checklist: correctness, maintainability, performance, types and tests. Useful when a change needs review before merge. CX Codex +1 562installs reviewing-security osmontero The reviewing-security skill reviews code before a merge or release by tracing attacker-controlled input to the operation and impact it can reach. CX Codex +1 185installs reviewing-technical-prose riekelt reviewing-technical-prose — a skill for reviewing someone else's technical writing: it flags banned constructions, unsupported claims and structural defects, then runs a delivery checklist before a document ships. CX Codex +1 26,900installs ac-reviewing-codebase souliane ac-reviewing-codebase — a skill for holistic review of a repo portfolio: it checks skill quality, code health and infrastructure alignment across repositories. CX Codex +1 1,000installs reviewing-oracle-to-postgres-migration official github reviewing-oracle-to-postgres-migration reviews Oracle-to-PostgreSQL migration risks and checks whether migration artifacts and integration tests cover the relevant behavior changes. CX Codex +1 1,800installs gjalla-code-review gjalla gjalla-code-review reviews PRs and diffs before merge from the perspective of an architect, security analyst, and QA engineer. Groups findings by severity. CX Codex +1 865installs code-review jwynia code-review is a Claude Code skill for finding defects and assessing code quality. It activates on requests to review code, check a PR, or evaluate changes systematically. CX Codex +1 505installs

From the same set37

The whole set →
pyroscope Guides and configs for Grafana Pyroscope continuous profiling: Helm deployments, Go/Java/Python SDK setups, object storage, and trace correlation. CX Codex +1 108installs using-cloud-cli The using-cloud-cli skill sets patterns for bq, gcloud, and aws. Use it for BigQuery queries, cloud resource commands, and AWS or GCP service decisions. CX Codex +1 108installs tempo A practical Grafana Tempo guide for OpenTelemetry tracing, covering Helm deployment, object storage, TraceQL queries, and Kubernetes troubleshooting. CX Codex +1 107installs using-git-worktrees using-git-worktrees creates a git worktree under .claude/worktrees/, opens it in a tmux window of the current session and sends the task there. CX Codex +1 106installs looking-up-docs looking-up-docs retrieves version-specific library documentation and live API examples through Context7 inside your coding agent. CX Codex +1 106installs defectdojo Connects Claude Code with DefectDojo to inspect vulnerabilities, filter security findings, and manage test engagements from your terminal. CX Codex +1 105installs external-dns external-dns — a skill for automatic DNS record synchronization with Azure DNS, AWS Route53, Cloudflare and Google Cloud DNS based on Kubernetes Ingress and Service resources. CX Codex +1 105installs keyvault-csi-driver keyvault-csi-driver is a skill for connecting Azure Key Vault to Kubernetes with the Secrets Store CSI Driver. It guides SecretProviderClass setup, secret mounts, and access-error troubleshooting. CX Codex +1 102installs

Project sponsors

Companies that keep this analytics open