human-review — security grade SAFE, quality 70/100

Security audit verdict: SAFE · quality 70/100

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 petergyang · Codex Skill · ★ 1.3k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is human-review safe to install? View the security audit →

About human-review

Human Review Edit HTML and Markdown files directly, leave comments like a Google Doc, and send all your feedback to your AI agent at once. Read the full launch post https://github.com/user-attachments/assets/7cab09c9-eaa0-4e8b-984d-2925e810b5c2 Problem Giving AI feedback on files in chat is painful. Sometimes you want to change one sentence yourself. Instead, you end up typing: In the third paragraph, change X to Y. Cut the third card because it repeats the first one. Also rewrite the CTA. Then the agent changes the file and you have to check whether it understood every instruction. This gets even harder when you’re reviewing a long plan, Markdown document, landing page, or multi-page website. How to install /human-review The easiest way to install the skill is to paste this into ChatGPT, Claude Code, Codex, or your favorite coding agent: You can also install it with : How to use /human-review Open an HTML or Markdown file: Review a page running on localhost: Human Review opens the file in your browser. Make direct edits, leave comments, and click Send. Your agent receives all

ai-agentsclaude-codeclicodexfeedbackhtmlhuman-in-the-loopmarkdownreview

Quick Facts

Stars1,267
Forks102
LanguageJavaScript
CategoryCodex Skill
LicenseMIT
Quality Score70.3144664342019/100
Open Issues29
Last Updated2026-09-17
Created2026-07-27
Platformsclaude-code, cli, codex, node
Est. Tokens~13k

Compatible Skills

These tools work well together with human-review for enhanced workflows:

  • html-visual-editor — semantic(0.27)+complementary+same_lang+similar_pop+shared_platform (59%)

human-review alternative? Top 6 similar tools

Looking for a human-review alternative? If you're comparing human-review with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • readme-ai by eli64s · ⭐ 3.0k

    README file generator, powered by AI.

  • ralphex by umputun · ⭐ 1.5k

    Extended Ralph loop for autonomous AI-driven plan execution

  • claude-codex-settings by fcakyon · ⭐ 1.1k

    Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM

  • crit by tomasz-tomczyk · ⭐ 1.1k

    Your feedback loop with the agent

  • pydantic-deepagents by vstorm-co · ⭐ 1.0k

    Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-callin

  • codexia by milisp · ⭐ 915

    Lightweight Agent Workstation for Codex CLI + Claude Code — with task scheduler, git worktree & remote control

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular JavaScript Agent Tools

Frequently Asked Questions

What is human-review?

human-review is A visual tool to edit HTML and Markdown files, leave comments like a Google Doc, and send feedback to your AI agent. Works inside your favorite AI harness.. It is categorized as a Codex Skill with 1.3k GitHub stars.

What programming language is human-review written in?

human-review is primarily written in JavaScript. It covers topics such as ai-agents, claude-code, cli.

How do I install or use human-review?

You can find installation instructions and usage details in the human-review GitHub repository at github.com/petergyang/human-review. The project has 1.3k stars and 102 forks, indicating an active community.

What license does human-review use?

human-review is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to human-review?

The top alternatives to human-review on Agent Skills Hub include readme-ai, ralphex, claude-codex-settings. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Codex Skill tools