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 architectds · Codex Skill · ★ 115
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is modeldock safe to install? View the security audit →
Model Dock For Codex ModelDock makes the AI tools you already own work together. Keep working in Codex. Use Grok, DeepSeek, Qwen, and other models you choose alongside web search, image understanding, voice, memory, and video - without manually moving prompts, files, or results between apps. Work in one place. Get things done everywhere. A thin local Responses bridge for OpenCode Go, DeepSeek, and local engines - Ollama, llama.cpp, and vLLM are detected on loopback, and any other OpenAI-compatible endpoint can be added by URL - with native GPT passthrough and live token, latency, and trace observability. ModelDock currently connects models and capabilities inside a Codex task. The next step is Connectors: user-authorized local tools that run through their own official CLIs, work in an isolated job, and return a result and reviewable diff to the task. Connectors are planned; they are not part of the current release. English · 中文 · 日本語 <img src="assets/memory-banner.png" alt="Three-tier memory: project, global, expert - reward 50% to 80%, time 4h15m to 2h24m" width="70%"
| Stars | 115 |
| Forks | 14 |
| Language | JavaScript |
| Category | Codex Skill |
| Quality Score | 41.4735828044406/100 |
| Last Updated | 2026-08-21 |
| Created | 2026-07-19 |
| Platforms | browser, codex, node |
| Est. Tokens | ~13k |
These tools work well together with modeldock for enhanced workflows:
Looking for a modeldock alternative? If you're comparing modeldock with other codex skill tools, these 2 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Skills for agentic development on Solana
A Codex/Claude skill that maintains per-repo operating theory documents.
Explore other popular codex skill tools:
modeldock is Keep everything in Codex - and add DeepSeek. Give DeepSeek eyes, ears, a voice, a web search, a memory, and the content-to-video skill. ModelDock focuses on one thing: making DeepSeek work natively in. It is categorized as a Codex Skill with 115 GitHub stars.
modeldock is primarily written in JavaScript.
You can find installation instructions and usage details in the modeldock GitHub repository at github.com/architectds/modeldock. The project has 115 stars and 14 forks, indicating an active community.
The top alternatives to modeldock on Agent Skills Hub include solana-dev-skill, 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: