Jev 接管 agent 栈：9 个可抄的开源项目
列出用 Jev 做的 Opus 努力度路由、Stop 钩子证据校验、技能路由、Codex 子代理路由、提交信息校验、恶意代码扫描、语义 grep、MCP 搜索评分等 9 个项目。
Jev is quietly taking over the agent stack. If you already have a Jev API key and don't know what to build first, steal this checklist: 1. jev-opus Runs Claude Code on Opus 5.5 and asks Jev before every call how much effort the next step needs: low, medium or high. Code enforces the floors and ceilings, and the prompt cache stays intact. https://github.com/WXK-AI/jev-opus 2. jev-belay A Claude Code Stop hook that won't trust "done" without evidence. If files changed and nothing passed since, one Jev call checks the transcript before the agent is allowed to stop. https://github.com/valentynkit/jev-belay 3. jev-skill-router On every prompt, Jev picks one skill from everything you have installed, or none. It starts in shadow mode and only logs, so you see its picks before you trust them. https://github.com/shimo4228/jev-skill-router 4. codex-jev-router Jev picks the model and reasoning effort for each Codex subagent. When Jev is unsure, it falls back to Sol. https://github.com/suenot/codex-jev-router 5. jev-commit A pre-commit hook. One Jev call checks whether your commit message actually matches the staged diff and flags debug leftovers and unmentioned work. https://github.com/valentynkit/jev-commit 6. is-malicious Scans source, config, build and CI files with Jev and points at the suspicious lines before the code ever runs. https://github.com/luantak/is-malicious 7. jegrep Semantic grep in Rust. Jev scores your files with probabilities, no embedding index and no background daemon. https://github.com/can1357/jegrep 8. jev-scout An MCP server that scores every search query, result and fetched page your agent touches for relevance and credibility, with a live decision dashboard. https://github.com/kierandotai/jev-scout 9. hunch Probabilistic control flow for Ruby. if Hunch.likely?("fraudulent", given: order) branches on a typed Jev answer. https://github.com/carldaws/hunch 10. pytest-jev Write plain-English claims about your output, and the test passes only when Jev clears every claim above 0.8. https://github.com/allebee/pytest-jev Copy any of these Jev builds, then read the full Jev setup below ↓
这条是引用着另一条写的：x.com/hanakoxbt/status/2101709924828934222