claude-code-templates: three Jev plugins
Project / 项目 · In the catalogue / 在目录中查看
What Jev decides here · Jev 在这里做什么决定
Safety gating (安全闸门), Model routing (模型路由), Tool selection (工具选择)
choice, score, noul: read in the code by a person 由人在代码里读到
a person read the call site 有人读过调用点 · · Cited file / 引用的文件: scripts/jev-spike.mjs
Summary · 摘要
Three independently installable Claude Code plugins — guardrails, model router and skill suggestion — each with its own hooks and tests.
三个可独立安装的 Claude Code 插件 —— 护栏、模型路由、技能推荐 —— 各自带 hook 和测试。
Notes · 备注
Its skill-suggestion plugin implements the official cookbook of the same name, including withholding the skill listing from the main model so the choice is actually made by Jev.
它的技能推荐插件实现了同名官方 cookbook，包括「不把技能清单给主模型看」这一步，从而让选择真正由 Jev 做出。
Launches · 发布记录
Not launched yet. 还没有发布过。 Launch it / 发布它 ↗ · How a product launches / 怎样发布一个产品
Makers · Maker
Made this? Confirm or correct its entry / 这是你做的？确认或更正条目 ↗
The same form takes the product's one line and a demo link, in its maker's own words. 同一个表单也可以补上产品的一句话和演示链接，用 Maker 自己的话。
Badge for its README · README 徽章
[](https://kydlikebtc.github.io/awesome-jev/products/claude-code-templates-jev.html)One line for the product's README, linked to this page. The picture says that it is listed; while it is on the launch board, that it is launching; after a week in the top three, its place. It is rebuilt with the site, so the line never needs changing. 放进产品 README 的一行，链接到本页。图片显示已收录；在发布榜上时显示正在发布；进过某周前三后显示名次。它随网站一起重建，这一行不用再改。
Also under this pattern · 同一模式的其他产品
sub2api: Jev as a moderation endpoint
Drops in as a moderation API by asking many parallel Noul questions in one request, one per hazard category, with an anti-injection prefix on every instruction.
@langchain/typesafe
The JavaScript counterpart of the LangChain integration, with the same classifier and middleware shapes.
DeepChat: agent tool-permission review
Reviews each tool call on three axes — risk level, whether the user authorised it, and an explicit prompt-injection pressure check.
agentgateway: Jev and OpenAI guardrail
Three yes-or-no questions (jailbreak, harmful content, secret disclosure) on each request and each response, rejected with HTTP 403 at a probability of 0.5 or more and blocked on any evaluation error; the gateway sends half the evaluations to Jev as Nouls and half to OpenAI.
atomic
Coding-agent runtime in which workflows are versioned TypeScript stages with executable checks, review gates and human approvals. Its AI package lists Jev from models.dev as a System One decision model on five providers, apart from the chat models; the README does not say where a workflow calls it.