by ARahim3 · Codex Skill · ★ 698
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
brew install --cask mlx-dspark
pip install mlx-dspark # or: uv pip install mlx-dsparkTaken from the project's README on GitHub. Check the security audit before running it.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 698 |
| Forks | 60 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 65/100 |
| Open Issues | 20 |
| Last Updated | 2026-10-05 |
| Created | 2026-06-29 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~25k |
DeepSeek's DSpark and z-lab's DFlash speculative decoding — native on Apple Silicon via MLX. Lossless drafters (same output, just faster) for Gemma-4, Qwen3, LFM2.5, Muse-Glimmer, Ornith-1.0, Qwen3.6, Qwen3.8, Nemotron, and Bonsai targets — plus any matched DSpark / DFlash checkpoint.
These tools work well together with mlx-dspark for enhanced workflows:
Looking for a mlx-dspark alternative? If you're comparing mlx-dspark 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.
The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenC
Run a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16–64 GB App
Hit your Claude Code usage limit? Keep going free and offline on a local model. Claude Code Local runs on Appl
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swif
High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuou
Diablo II: Resurrected on iPhone, iPad, Apple silicon Mac, Android and HarmonyOS. Offline play with touch or a
Explore other popular codex skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: