codex-manager — security grade SAFE, quality 53/100

Security audit verdict: SAFE · quality 53/100

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 ewsun22 · Codex Skill · ★ 54

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

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

About codex-manager

Codex Manager English | 简体中文 Your local control center for OpenAI Codex. Codex Manager is an unofficial, local-first desktop app for understanding and managing Codex usage on your own machine: sessions, models, reasoning effort, tokens, accounts, providers, projects, and files in one place. Download for macOS (Apple silicon) → Download Download the latest signed macOS release · Release assets and checksums · [All releases](https://github.com/ewsun22/codex-m

agents-mdai-codingcodexcodex-clicodex-desktopdeveloper-toolsllm-observabilitylocal-firstmacosopenai-codex

Quick Facts

Stars54
Forks1
LanguageRust
CategoryCodex Skill
LicenseApache-2.0
Quality Score53.0422426111387/100
Last Updated2026-09-05
Created2026-08-27
Platformscli, codex, rust
Est. Tokens~22k

Compatible Skills

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

  • codex-usage-tracker — semantic(0.37)+complementary+shared_fw(openai)+rare_topics+similar_pop+shared_platform (65%)
  • harness-experimental — semantic(0.19)+complementary+shared_fw(openai)+same_lang+similar_pop+shared_platform (65%)
  • token_proxy — semantic(0.18)+complementary+shared_fw(openai)+same_lang+similar_pop+shared_platform (64%)
  • codex-command-center — semantic(0.53)+complementary+rare_topics+similar_pop+shared_platform (63%)

codex-manager alternative? Top 6 similar tools

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

  • WhereMyTokens by jeongwookie · ⭐ 82

    Local-first Windows tray app for monitoring Claude Code and Codex tokens, costs, sessions, and rate limits

  • codex-profiles by Ducksss · ⭐ 149

    Named CODEX_HOME profiles and ChatGPT Desktop windows with separate local state, without copying tokens

  • toktrack by mag123c · ⭐ 192

    Ultra-fast token & cost tracker for LLM Token Usage (e.g. Claude Code)

  • OpenCovibe by AnyiWang · ⭐ 261

    Local-first desktop app for AI coding agents (Claude Code, Codex). Built with Tauri v2 + Svelte 5.

  • yume by aofp · ⭐ 150

    Native desktop UI for Claude Code with orchestration, streaming, background agents, and multi-provider support

  • codex-viz by onewesong · ⭐ 72

    Local-first dashboard for Codex sessions with trends, token usage, tools, and word cloud | Codex 本地数据分析仪表盘

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-manager?

codex-manager is Local-first desktop control center for OpenAI Codex — sessions, models, tokens, accounts, providers, and AGENTS.md.. It is categorized as a Codex Skill with 54 GitHub stars.

What programming language is codex-manager written in?

codex-manager is primarily written in Rust. It covers topics such as agents-md, ai-coding, codex.

How do I install or use codex-manager?

You can find installation instructions and usage details in the codex-manager GitHub repository at github.com/ewsun22/codex-manager. The project has 54 stars and 1 forks, indicating an active community.

What license does codex-manager use?

codex-manager 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-manager?

The top alternatives to codex-manager on Agent Skills Hub include WhereMyTokens, codex-profiles, toktrack. 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