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 manhvann · Codex Skill · ★ 88
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is codexkit safe to install? View the security audit →
Codex Kit Project-local Codex setup for serious multi-repository workspaces. Current release: · License: MIT · Repository: github.com/manhvann/codexkit Codex Kit installs a curated Codex workspace layer with skills, agents, hooks, workflow rules, helper scripts, plan templates, output styles, and project documentation. It is designed for umbrella repositories that contain many child repos: keep the operational knowledge in the parent workspace, while Codex can still reason about and work ac
| Stars | 88 |
| Forks | 88 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 68.2568524918151/100 |
| Last Updated | 2026-08-29 |
| Created | 2026-08-13 |
| Platforms | codex, python |
| Est. Tokens | ~15k |
These tools work well together with codexkit for enhanced workflows:
Looking for a codexkit alternative? If you're comparing codexkit with other codex skill tools, these 1 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A Codex/Claude skill that maintains per-repo operating theory documents.
Explore other popular codex skill tools:
codexkit is Project-local Codex workspace kit with reusable skills, agents, hooks, plans, docs, and helper scripts for multi-repository development.. It is categorized as a Codex Skill with 88 GitHub stars.
codexkit is primarily written in Python.
You can find installation instructions and usage details in the codexkit GitHub repository at github.com/manhvann/codexkit. The project has 88 stars and 88 forks, indicating an active community.
codexkit is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to codexkit on Agent Skills Hub include theorist. 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: