by kerpopule · Codex Skill · ★ 1.2k
Hermes Jev Skills Give your agent a fast, cheap second brain for the small decisions. Your agent burns frontier-model tokens on things that are not thinking: which model should answer this turn, which of 377 skills to load, which retrieved passages matter, which turns survive a summary, which button comes next. Those are decisions, not prose. Hand them to something that costs a fraction of a cent and answers in about 0.4 seconds, and let the expensive model do the writing. That is what Jev is. It is TypeSafe's decision model. It never writes text.
| Stars | 1,153 |
| Forks | 117 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 35/100 |
| Open Issues | 2 |
| Last Updated | 2026-10-23 |
| Created | 2026-09-18 |
| Platforms | browser, claude-code, codex, python |
| Est. Tokens | ~36k |
These tools work well together with hermes-jev-skills for enhanced workflows:
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 1.2k 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 1.2k stars and 117 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.