Claude Code 安全钩子用本地小模型 + Jev 每晚做 600 次放行判断
作者把 allow/ask/deny 判断交给本地 1.5GB 模型（约 18ms、零 token 成本），模糊情况再路由给 Jev 或人工，命令不出本机，切换只需改配置。
jev + claude code... i honestly don't get why every agent setup isn't running this yet. my safety hook makes ~600 decisions a night. now a 1.5 GB model makes them on my mac in ~18 ms each, $0 in tokens, and the commands never leave the disk. → plain code rules catch the obvious commands before any model is called → narrow allow / ask / deny calls go to the local model → fuzzy ones get routed to jev or to me → moving a question between local and jev is a config change, not a rewrite claude does the hard reasoning. the local model picks allow, ask or deny. the hook enforces it. i break down the gate, the router and the real bill in the article below:
这条是引用着另一条写的：x.com/asteri_eth/status/2104901781725598103