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 →
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is mini-jev safe to install? View the security audit →
mini-Jev · read the letter What a Jev-style interface looks like on a frozen model: classify against a schema that arrives with the request by reading next-token logits, not by generating JSON. Measured on Qwen3-4B. TypeSafe's Jev is trained for typed decisions without open generation. mini-Jev asks how much of that interface an ordinary frozen model already provides, and measures it against today's path, grammar-constrained JSON. A JSON schema arrives with the request. Today the model writes a JSON object under a grammar, token by token. This project measures the alternative for closed-choice fields: turn each field into a lettered multiple-choice question, run one forward pass, and read the model's scores for the option letters at the answer position. No token is generated. Strings and numbers are still generated. Everything here runs on (bf16, greedy) with xgrammar for constrained generation and CLINC150 as the task. The experiment was preregistered (, amendments v1.1–v1.3) and every number below is recomputed from the stored run records. Results in one table No. Intent field, 6750 paired observations on 450 texts: JSON 0.909, letters 0.907, Δ −0.22 pp, 95 % CI [−1.44, +1.04]
| Stars | 58 |
| Forks | 5 |
| Language | Python |
| Category | AI Tool |
| License | MIT |
| Quality Score | 56.5595116308614/100 |
| Open Issues | 2 |
| Last Updated | 2026-09-18 |
| Created | 2026-09-17 |
| Platforms | python |
| Est. Tokens | ~16k |
These tools work well together with mini-jev for enhanced workflows:
Looking for a mini-jev alternative? If you're comparing mini-jev with other ai tool tools, these 3 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Skip to content github / docs Code Issues 80 Pull requests 35 Discussions Actions Projects 2 Security Insights
Skill to talk to Claude about your projects over the phone
.NET MAUI skills for GitHub Copilot and Claude Code
Explore other popular ai tool tools:
mini-jev is mini-Jev: what a Jev-style typed-decision interface looks like on a frozen Qwen3-4B — read the option letter's logits instead of generating JSON. Preregistered experiment, results, teaching bench.. It is categorized as a AI Tool with 58 GitHub stars.
mini-jev is primarily written in Python.
You can find installation instructions and usage details in the mini-jev GitHub repository at github.com/r-ms/mini-jev. The project has 58 stars and 5 forks, indicating an active community.
mini-jev is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to mini-jev on Agent Skills Hub include redesigned-pancake, claude-code-voice-skill, maui-skills. 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: