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 kerpopule · Codex Skill · ★ 158
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is hermes-jev-skills safe to install? View the security audit →
Hermes Jev Skills Give your agent a fast, cheap second brain for the small decisions. Jev is TypeSafe's decision model. It does not write text. You hand it a state and typed questions (pick one, score this, yes or no) and it answers in about 0.4 seconds for a tiny fraction of a cent, with a calibrated confidence. This repo puts that to work on the decisions an agent makes all day, so your expensive model only does the thinking and writing. Plus a model routing dashboard (): every profile's models on one page, an on/shadow/off switch for Jev routing, and a live view of where each turn is being sent. See router-dashboard. Built for Hermes. The ski
| Stars | 158 |
| Forks | 9 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 67.0196691056989/100 |
| Open Issues | 3 |
| Last Updated | 2026-09-20 |
| Created | 2026-09-18 |
| Platforms | browser, claude-code, codex, python |
| Est. Tokens | ~15k |
Looking for a hermes-jev-skills alternative? If you're comparing hermes-jev-skills with other codex skill tools, these 4 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agen
Generate and evaluate agent skills for code agents like Claude Code, Open Code, OpenAI Codex
开源了Codex Skills等集合，大部分是自己实际需要搞得，需要的自取。欢迎star
Skills for agentic development on Solana
Explore other popular codex skill tools:
hermes-jev-skills is Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex). It is categorized as a Codex Skill with 158 GitHub stars.
hermes-jev-skills is primarily written in Python.
You can find installation instructions and usage details in the hermes-jev-skills GitHub repository at github.com/kerpopule/hermes-jev-skills. The project has 158 stars and 9 forks, indicating an active community.
hermes-jev-skills is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to hermes-jev-skills on Agent Skills Hub include ai-maestro, upskill, 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: