← ClaudeAtlas

code-reviewerlisted

Automated code review using official Claude Code plugin with parallel agents. Integrates ralph-security for OWASP validation and ralph-frontend for accessibility checks. Uses LSP for efficient code navigation.
alfredolopez80/multi-agent-ralph-loop · ★ 146 · Code & Development · score 77
Install: claude install-skill alfredolopez80/multi-agent-ralph-loop
# Code Reviewer (Official Plugin) Integrates the official Claude Code code-review plugin. ## v2.88 Key Changes (MODEL-AGNOSTIC) - **Model-agnostic**: Uses model configured in `~/.claude/settings.json` or CLI/env vars - **No flags required**: Works with the configured default model - **Flexible**: Works with GLM-5, Claude, Minimax, or any configured model - **Settings-driven**: Model selection via `ANTHROPIC_DEFAULT_*_MODEL` env vars ## Quick Start ```bash /code-review # Review current changes /code-review --comment # Post review as PR comment ``` ## Architecture 4 parallel agents with confidence scoring (≥80): 1. Agent #1: CLAUDE.md compliance 2. Agent #2: CLAUDE.md compliance (redundancy) 3. Agent #3: Bug detection (changes only) 4. Agent #4: Git blame/history analysis ## Features - Multi-agent parallel review - Confidence-based filtering - Auto-skip closed/draft/trivial PRs - Direct GitHub code links ## Integration Official plugin: `~/.claude-sneakpeek/zai/config/plugins/cache/anthropics/code-review/` **Author**: Boris Cherny (boris@anthropic.com) **Version**: 1.0.0 ## Agent Teams Integration (v2.88) **Optimal Scenario**: Pure Custom Subagents This skill uses Pure Custom Subagents (no Agent Teams) for focused code review operations. ### Why Scenario B for Code Review - **Native multi-agent**: Already uses 4 parallel agents via official plugin - **Read-only operation**: Review should not modify code (tool restrictions critical) - **No coordin