codex-keysmith — security grade SAFE, quality 65/100

Security audit verdict: SAFE · quality 65/100

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 Jia-Ethan · Codex Skill · ★ 4.5k

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

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

About codex-keysmith

Illustrative preview / 示意预览;实际路径与输出以本机 dry-run 为准。 codex-keysmith Versioned Codex instruction deployment with preview, ownership manifests, hook isolation, and layered uninstall. 简体中文 · English · Contributing · Security · License [!IMPORTANT] Global behavior boundary / 全局行为边界 A confirmed deployment changes the top-level in the selected Codex configuration. The instruction therefore applies to every new Codex session that loads that configuration; it is not a per-p

clicodexcodex-cliconfiguration-managementdeveloper-toolslocal-firstprompt-engineeringpython

Quick Facts

Stars4,531
Forks712
LanguagePython
CategoryCodex Skill
LicenseMIT
Quality Score64.9052404114974/100
Open Issues5
Last Updated2026-09-18
Created2026-06-28
Platformscli, codex, python
Est. Tokens~24k

Compatible Skills

These tools work well together with codex-keysmith for enhanced workflows:

  • ctx — semantic(0.27)+complementary+same_lang+similar_pop+shared_platform (60%)
  • claude-code-tools — semantic(0.22)+complementary+same_lang+similar_pop+shared_platform (58%)
  • ccgram — semantic(0.20)+complementary+same_lang+similar_pop+shared_platform (57%)
  • hol-guard — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (56%)
  • cli — semantic(0.17)+complementary+same_lang+similar_pop+shared_platform (56%)

codex-keysmith alternative? Top 6 similar tools

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

  • quint-code by m0n0x41d · ⭐ 1.3k

    Engineering decisions engine that know when they're stale. Frame, compare, decide — with evidence decay and p

  • superset by superset-sh · ⭐ 14.4k

    Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscrip

  • pilot-shell by maxritter · ⭐ 2.1k

    Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software

  • claude-code-tools by pchalasani · ⭐ 2.0k

    Practical productivity tools for Claude Code, Codex-CLI, and similar CLI coding agents.

  • ai-devkit by codeaholicguy · ⭐ 1.6k

    The control plane for AI coding agents.

  • antigravity-workspace-template by study8677 · ⭐ 1.3k

    Give Claude Code, Cursor, Codex CLI a ChatGPT for your codebase. Multi-agent knowledge engine, grounded Q&A wi

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is codex-keysmith?

codex-keysmith is Versioned Codex instruction deployment with preview, ownership manifests, hook isolation, scenario evaluation, and recovery.. It is categorized as a Codex Skill with 4.5k GitHub stars.

What programming language is codex-keysmith written in?

codex-keysmith is primarily written in Python. It covers topics such as cli, codex, codex-cli.

How do I install or use codex-keysmith?

You can find installation instructions and usage details in the codex-keysmith GitHub repository at github.com/Jia-Ethan/codex-keysmith. The project has 4.5k stars and 712 forks, indicating an active community.

What license does codex-keysmith use?

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

What are the best alternatives to codex-keysmith?

The top alternatives to codex-keysmith on Agent Skills Hub include quint-code, superset, pilot-shell. 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