codex-rewind — security grade SAFE, quality 67/100

Security audit verdict: SAFE · quality 67/100

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 extracurricular-ai · Codex Skill · ★ 51

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

🔒 Is codex-rewind safe to install? View the security audit →

About codex-rewind

codex-rewind English · 简体中文 An unofficial distribution of OpenAI Codex CLI. For what Codex CLI is, how to sign in, and how to use it, read the official README. Everything there applies here. This page only covers what this distribution adds. Not affiliated with, endorsed by, or supported by OpenAI. Apache-2.0, same as upstream. Report problems here, not to OpenAI — and include the npm version, which is the only one that names the release. See Reporting a bug. What this adds: rewind Upstream Codex can take you back to an earlier point in a conversation. It cannot take your files back with it — so the model ends up reasoning from a conversation that predates the code sitting on disk. This distribution adds the missing half. restores the workspace to how it looked at the prompt you pick, and puts

agentic-codingai-coding-assistantcheckpointclicodexcodex-clicoding-agentdeveloper-toolsopenai-codexrewind

Quick Facts

Stars51
Forks9
LanguageRust
CategoryCodex Skill
LicenseApache-2.0
Quality Score66.9954777498912/100
Last Updated2026-09-27
Created2026-08-14
Platformscli, codex, rust
Est. Tokens~26k

codex-rewind alternative? Top 6 similar tools

Looking for a codex-rewind alternative? If you're comparing codex-rewind 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.

  • palot by ItsWendell · ⭐ 190

    Just another desktop client for OpenCode 2. Manage projects, sessions, parallel agents, requests, and changes

  • fast-resume by angristan · ⭐ 167

    Find that one coding agent session you want to get back to!

  • acodex by maksimzayats · ⭐ 57

    Local MCP automation bridge for the Codex desktop app, with CLI, HTTP server, and live codex_app.* tool access

  • dgk-gpt by dgk-dev · ⭐ 56

    Safe Codex CLI setup installer with skills, AGENTS.md, profiles, and MCP defaults

  • aiwg by jmagly · ⭐ 218

    Cognitive architecture for AI-augmented software development. Specialized agents, structured workflows, and mu

  • recall by zippoxer · ⭐ 198

    Full-text search and resume for Claude/Codex conversations

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Rust Agent Tools

Frequently Asked Questions

What is codex-rewind?

codex-rewind is Unofficial distribution of OpenAI Codex CLI that adds /rewind and /redo — restores your files, not just the conversation. Git-free snapshots that never touch your git state. Tracks upstream releas. It is categorized as a Codex Skill with 51 GitHub stars.

What programming language is codex-rewind written in?

codex-rewind is primarily written in Rust. It covers topics such as agentic-coding, ai-coding-assistant, checkpoint.

How do I install or use codex-rewind?

You can find installation instructions and usage details in the codex-rewind GitHub repository at github.com/extracurricular-ai/codex-rewind. The project has 51 stars and 9 forks, indicating an active community.

What license does codex-rewind use?

codex-rewind is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to codex-rewind?

The top alternatives to codex-rewind on Agent Skills Hub include palot, fast-resume, acodex. 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