Minke — security grade SAFE, quality 58/100

Security audit verdict: SAFE · quality 58/100

Flagged: sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by lencx · Codex Skill · ★ 646

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

🔒 Is Minke safe to install? View the security audit →

About Minke

Minke A native desktop workspace for DeepSeek Harness English · 简体中文 Minke brings DeepSeek Harness to the desktop as a focused, local-first workspace for agentic work. Conversations, project files, terminals, web tools, and native desktop actions stay within reach—without fragmenting your workflow across multiple apps. [!IMPORTANT] Minke is under active development. Features, packaging, and the local data schema may change as the project evolves. Minke is an independent community project, not an official DeepSeek product. Highlights Since v0.2.0, Minke has ad

agentai-agentscodexcordisdeekseekdesktopdshdsh-pluginharnesslinux

Quick Facts

Stars646
Forks69
LanguageTypeScript
CategoryCodex Skill
LicenseApache-2.0
Quality Score57.7839213290289/100
Open Issues3
Last Updated2026-09-16
Created2026-08-15
Platformscodex, node
Est. Tokens~17k

Compatible Skills

These tools work well together with Minke for enhanced workflows:

  • pilot-harness — semantic(0.63)+complementary+same_lang+similar_pop+shared_platform (72%)
  • dsh-desktop-hub — semantic(0.57)+complementary+same_lang+similar_pop+shared_platform (70%)
  • modsearch — semantic(0.41)+complementary+rare_topics+same_lang+similar_pop+shared_platform (69%)
  • modlens — semantic(0.40)+complementary+rare_topics+same_lang+similar_pop+shared_platform (68%)
  • awesome-deepseek-harness — semantic(0.49)+complementary+same_lang+similar_pop+shared_platform (67%)

Minke alternative? Top 6 similar tools

Looking for a Minke alternative? If you're comparing Minke 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.

  • memsearch by zilliztech · ⭐ 2.6k

    A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown a

  • token-monitor by Javis603 · ⭐ 2.2k

    Local-first desktop widget for tracking token usage, costs, and limits across 37+ AI coding tools—including Cl

  • wesight by freestylefly · ⭐ 924

    Open-source desktop AI agent workspace with one-click Claude Code, Codex, OpenClaw, Hermes Agent setup and cus

  • modsearch by liustack · ⭐ 482

    🥇 The strongest free web search plugin for DeepSeek Harness, and the search bridge for every model without na

  • cetus by drewnekota · ⭐ 146

    One macOS app for Claude Code, Codex, and every agent runtime you use — scheduled runs, global hotkey launcher

  • Vibe-Skills by foryourhealth111-pixel · ⭐ 3.1k

    Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on Skills

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is Minke?

Minke is 🐳 DeepSeek Harness Desktop. It is categorized as a Codex Skill with 646 GitHub stars.

What programming language is Minke written in?

Minke is primarily written in TypeScript. It covers topics such as agent, ai-agents, codex.

How do I install or use Minke?

You can find installation instructions and usage details in the Minke GitHub repository at github.com/lencx/Minke. The project has 646 stars and 69 forks, indicating an active community.

What license does Minke use?

Minke 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 Minke?

The top alternatives to Minke on Agent Skills Hub include memsearch, token-monitor, wesight. 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