No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by spencermarx · Claude Skill · ★ 331
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is open-code-review safe to install? View the security audit →
Open Code Review Customizable multi-agent code review for AI-assisted development Quick Start Prerequisites: Node.js = 22.5, Git, and an AI coding assistant. Your browser will open the OCR dashboard — you're ready to run your first review. Any package manager works. From v2.1 OCR uses Node's built-in SQLite () — there's no native module to compile, so , , and all install cleanly (including under pnpm 10+, which blocks dependency build scripts). It just needs Node = 22.5. detects your installed AI tools (Claude Code, Cursor, Windsurf, and 11 more) and configures each one automatically. Then open the dashboard to run
| Stars | 331 |
| Forks | 27 |
| Language | TypeScript |
| Category | Claude Skill |
| License | Apache-2.0 |
| Quality Score | 65.5940014440254/100 |
| Open Issues | 2 |
| Last Updated | 2026-07-28 |
| Created | 2026-01-26 |
| Platforms | claude-code, node |
| Est. Tokens | ~20k |
These tools work well together with open-code-review for enhanced workflows:
Looking for a open-code-review alternative? If you're comparing open-code-review with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured
A curated list of Plugins that let you extend Claude Code with custom commands, agents, hooks, and MCP servers
An IOS Simulator Skill for ClaudeCode. Use it to optimise Claude's ability to build, run and interact with you
Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM
AI writes code. This automates everything else · 24 plugins · 49 agents · 44 skills · for Claude Code, OpenCod
Claude Code plugin for Elixir/Phoenix/LiveView — 26 specialist agents, Iron Laws enforcement, and Tidewave MCP
Explore other popular claude skill tools:
open-code-review is AI-powered multi-agent code review. Simulates a customizable team of Engineers performing code review with built-in discourse.. It is categorized as a Claude Skill with 331 GitHub stars.
open-code-review is primarily written in TypeScript. It covers topics such as agentic-ai, agents, ai.
You can find installation instructions and usage details in the open-code-review GitHub repository at github.com/spencermarx/open-code-review. The project has 331 stars and 27 forks, indicating an active community.
open-code-review is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to open-code-review on Agent Skills Hub include smart-ralph, awesome-claude-plugins, ios-simulator-skill. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: