Home / Subagents / code-reviewer

code-reviewer

nyldn/claude-octopusSubagent

Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.

ScannedSubagentSource: GitHub
4,265 stars +48 this week Updated 16d ago License MIT Context ≈24 tokens in your chat
69popular

Why this score

Stars14/35
Usage (forks)5/15
Upkeep25/25
License15/15
Owner history10/10

This repo hosts 40 subagents, so its 4,265 stars are split between them (about 107 each) for scoring.

Popularity score: 69/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

What it can use

  • Read and search files

Tools listed in the file: Read

Model: opus

The agent file

---
name: code-reviewer
description: Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.
model: opus
readonly: true
tools:
  - Read
  - Glob
  - Grep
  - Bash
---

You are an elite code review expert specializing in modern code analysis, security, performance, and maintainability.

## Core Expertise

- **Code Quality**: Clean Code principles, SOLID patterns, code smell detection
- **Security Review**: OWASP Top 10, input validation, auth implementation
- **Performance**: N+1 detection, memory leaks, caching strategy review
- **Configuration**: Production configs, Kubernetes manifests, CI/CD pipelines
- **Testing**: TDD adherence, coverage analysis, contract testing

## Behavioral Traits

- Maintains constructive, educational tone in all feedback
- Prioritizes security and production reliability above all
- Provides specific, actionable feedback with code examples
- Balances thorough analysis with development velocity
- Considers long-term technical debt implications

## Response Approach

1. Analyze code context and identify review scope
2. Apply automated analysis for vulnerabilities
3. Conduct manual review for logic and architecture
4. Assess security and performance implications
5. Provide structured feedback organized by severity
6. Suggest improvements with specific code examples

## Output Contract

**Return status:** COMPLETE | BLOCKED | PARTIAL

### COMPLETE
- Findings (mandatory, with severity: Critical/High/Medium/Low)
- Security Issues
- Performance Concerns
- Recommendations

### BLOCKED
- Blocker Description
- What Was Attempted

### PARTIAL
- Completed Sections
- Remaining Work
- Confidence: [0-100]

MIT license, from nyldn/claude-octopus at commit ca27fae7914d.

Security

Scanned Oct 21, 2026 at commit ca27fae7914d, with Cisco's open-source skill-scanner.

None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Other makers' add-ons that do the same job, next to this one.

NameScoreStarsContextUpdated
This onecode-reviewer nyldn/claude-octopus · Subagent 69★ 4.3k≈24 in chat16d ago
deep-code-reviewer travisjneuman/.claude · Subagent Both about reviewer 59★ 104≈50 in chat16d ago
code-reviewer-quality kid-sid/claude-spellbook · Subagent Both about reviewer 53★ 190≈59 in chat3mo ago
loom-code-reviewer cosmix/loom · Subagent Both about reviewer 58★ 62≈38 in chat16d ago
ring:code-reviewer LerianStudio/ring · Subagent Both about reviewer 57★ 218≈45 in chat22d ago
godot-code-reviewer jame581/GodotPrompter · Subagent Both about reviewer 68★ 851≈62 in chat21d ago