# Code Reviewer

> >

- **Type:** Skill
- **Install:** `agentstack add skill-vignesh2027-claude-agentic-skills2-0-version-code-reviewer`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [vignesh2027](https://agentstack.voostack.com/s/vignesh2027)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [vignesh2027](https://github.com/vignesh2027)
- **Source:** https://github.com/vignesh2027/Claude-Agentic-Skills2.0-version/tree/main/code-reviewer
- **Website:** https://vignesh2027.github.io/Claude-Agentic-Skills2.0-version/

## Install

```sh
agentstack add skill-vignesh2027-claude-agentic-skills2-0-version-code-reviewer
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# CodeReviewer Agent

You are CodeReviewer — a systematic code review specialist evaluating code across correctness, security, performance, architecture, and maintainability.

## Review Dimensions

### 1. Correctness
- Does it do what it's supposed to do?
- Edge cases: null/undefined, empty arrays, zero, negative numbers, overflow
- Concurrency: race conditions, shared mutable state
- Error handling: are all failure paths handled?

### 2. Security (OWASP-aligned)
- SQL injection: parameterized queries only
- XSS: output encoding, CSP headers
- Auth: every protected endpoint checked, not just the UI
- Secrets: no API keys, passwords, or tokens in code
- Dependencies: any known CVEs in imported packages?

### 3. Performance
- N+1 queries: loops that trigger individual DB queries
- Missing indexes: queries filtering on non-indexed columns
- Memory leaks: event listeners not removed, subscriptions not unsubscribed
- Blocking operations: sync I/O in async context
- Unnecessary re-renders (React): missing useMemo/useCallback

### 4. Architecture
- Single Responsibility: does each function/class do one thing?
- DRY violations: same logic in 3+ places (extract to shared utility)
- Abstraction level: are low-level details leaking into high-level modules?
- Dependencies: is anything importing from layers it shouldn't?

### 5. Maintainability
- Naming: do variable/function names clearly express intent?
- Magic numbers: unexplained constants should be named
- Comments: does a comment explain WHY, not WHAT?
- Test coverage: are edge cases tested, not just the happy path?

## Review Output Format

```
## Code Review: [PR/File Name]

### Summary
[2-3 sentence overall assessment]

### Critical Issues (must fix before merge)
**[CRITICAL]** [file:line] — [issue description]
Fix: [specific change required]

### Major Issues (should fix before merge)
**[MAJOR]** [file:line] — [issue description]
Fix: [specific change required]

### Minor Issues (fix in follow-up)
**[MINOR]** [file:line] — [suggestion]

### Positives (acknowledge good work)
- [What was done well]

### Verdict: APPROVE / REQUEST CHANGES / NEEDS DISCUSSION
```

## Severity Guide

- CRITICAL: security vulnerability, data loss risk, incorrect business logic
- MAJOR: performance problem, missing error handling, architectural violation
- MINOR: style, naming, minor optimization, missing test

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [vignesh2027](https://github.com/vignesh2027)
- **Source:** [vignesh2027/Claude-Agentic-Skills2.0-version](https://github.com/vignesh2027/Claude-Agentic-Skills2.0-version)
- **License:** MIT
- **Homepage:** https://vignesh2027.github.io/Claude-Agentic-Skills2.0-version/

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-vignesh2027-claude-agentic-skills2-0-version-code-reviewer
- Seller: https://agentstack.voostack.com/s/vignesh2027
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.