Flagged: environment access. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by bladedevoff · Claude Skill · ★ 61
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is stuntd safe to install? View the security audit →
stuntd: a local Jev-compatible proxy that learns your typed LLM decisions stuntd is a local, self-hosted proxy that records the typed decisions your app already makes and learns to answer them itself. It speaks the Jev System One protocol (, with , and questions) and the OpenAI Chat Completions API, distils each decision site into a small head on a frozen Laya encoder, and serves that answer locally with calibrated confidence, handing anything it is unsure about back to the provider. Try it in the browser: the Hugging Face Space puts zero-shot Laya and the heads stuntd trained side by side on three demos, no install. Three ways to run it: Local Jev. No key, no provider, no training. Point
| Stars | 61 |
| Forks | 1 |
| Language | Python |
| Category | Claude Skill |
| License | Apache-2.0 |
| Quality Score | 63.0017209154338/100 |
| Last Updated | 2026-10-03 |
| Created | 2026-09-23 |
| Platforms | claude-code, python |
| Est. Tokens | ~20k |
Looking for a stuntd alternative? If you're comparing stuntd with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Typed decisions with TypeSafe's Jev, the first System One model
🔥🔥 Papers, open reproductions and independent evaluations behind System One models and Jev.
Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisio
A curated list of Jev use cases, projects, SDKs, and resources. Jev is TypeSafe AI's System One model for fast
Jev / TypeSafe System One 中文精选列表：官方资料、SDK、爆款应用、Agent 工具、开源复现与独立评测，附中文上手指南，每日自动收录 GitHub 热门项目。
Meet JevEmbed — turn embeddings into decisions. Choose, score, and judge with your choice of embedding model.
Explore other popular claude skill tools:
stuntd is Local proxy that learns your app's typed LLM decisions and answers them with a Laya head. Jev and OpenAI compatible.. It is categorized as a Claude Skill with 61 GitHub stars.
stuntd is primarily written in Python. It covers topics such as claude-code, distillation, jev.
You can find installation instructions and usage details in the stuntd GitHub repository at github.com/bladedevoff/stuntd. The project has 61 stars and 1 forks, indicating an active community.
stuntd is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to stuntd on Agent Skills Hub include awesome-jev-typesafe, awesome-jev, open-alternative-jev. 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: