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 angieruiz17 · Codex Skill · ★ 143
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is codex-gpt-plugin safe to install? View the security audit →
Codex Gpt Plugin A Codex plugin that gives your agent a direct line to a logged-in ChatGPT Pro session. Codex is great at execution. For the hard parts — architecture, system design, research synthesis, tradeoff calls, gnarly debugging strategy — you sometimes want a second, stronger brain. Codex Gpt Plugin lets a Codex agent phone that brain: it drives a real, logged-in ChatGPT Pro browser session, attaches your repo as context, sends a message, reads the answer, and writes a receipt — no API key, no password handling, no scraped cookies. It's a phone line, not a scraper. Demo Codex Gpt Plugin call: Repo monofile attachment: Why The strongest ChatGPT Pro reasoning isn't exposed on the API — it lives in the website. So this bridges to the website, deliberately and safely. The human stays logged in; the automation is text-only and deterministic; and every call is recorded to disk. You get Pro-level collaboration inside your Codex loop without handing an agent your credentials. Use it for high-leverage work — architecture, specs, feature design, research synthesis, tradeoff review, cross-repo planning, and hard debugging strategy. Don't spend the line on trivial syntax checks.
| Stars | 143 |
| Forks | 1,048 |
| Language | JavaScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 75.6457053043196/100 |
| Last Updated | 2026-09-14 |
| Created | 2026-07-08 |
| Platforms | codex, node |
| Est. Tokens | ~15k |
These tools work well together with codex-gpt-plugin for enhanced workflows:
Looking for a codex-gpt-plugin alternative? If you're comparing codex-gpt-plugin 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.
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
DevOps discipline for AI coding agents: shape the work, track it as a graph, and get each change judged by a c
Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-f
Opinionated AI coding agent and dev environment automation for macOS
Production-ready AI agent profiles for Claude Code, Cursor, Codex, OpenClaw, and Hermes. Search, install, and
An AI agent that applies to jobs for you - searches boards, tailors your resume, fills applications, messages
Explore other popular codex skill tools:
codex-gpt-plugin is codex gpt plugin that gives agent a direct line to logged-in chatgpt pro session. It is categorized as a Codex Skill with 143 GitHub stars.
codex-gpt-plugin is primarily written in JavaScript. It covers topics such as agent-assistant, chatgpt-session, codex.
You can find installation instructions and usage details in the codex-gpt-plugin GitHub repository at github.com/angieruiz17/codex-gpt-plugin. The project has 143 stars and 1048 forks, indicating an active community.
codex-gpt-plugin is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to codex-gpt-plugin on Agent Skills Hub include Overture, agentops, maestro. 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: