stingray
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
noul: read in the code by a model, not yet by a person 由模型在代码里读到，尚无人复核
a model read the call site; no person yet 模型读过调用点，尚无人复核 · · Cited file / 引用的文件: hooks/stingray.sh
Summary · 摘要
Claude Code Stop hook that catches turns that stop half-done: Jev judges whether the turn did nothing, declared an action its tool calls do not back, promised to watch work that is not running, or answered in the wrong language, and the hook blocks the stop with a fixed nudge.written by a model
Claude Code 的 Stop 钩子，拦截做到一半就停下的轮次：由 Jev 判断这一轮是否什么都没做、宣称了工具调用无法佐证的操作、承诺监看并未运行的工作，或用错了回复语言，钩子随后以一段固定提示阻止停止。模型撰写机翻
Notes · 备注
Every check is off until a switch is set, and a shadow mode only logs. Background tasks, crons and pending handoffs are counted in code; Jev judges only the promise. The wordings are tuned on labelled fixtures, with the scores in the script's comments. Row drafted from the discovery queue (issue #14) by an AI assistant that read the README and the cited file on 2026-11-04; a maintainer has not yet read the call site.
在设置开关之前所有检查都不运行，影子模式只记录不拦截。后台任务、定时任务和等待回复的交接由代码计数，Jev 只判断承诺本身。问题措辞在带标签的测试样例上调过，分数记在脚本注释里。本条目由 AI 助手根据发现队列（issue #14）起草，于 2026-11-04 阅读了 README 和所引文件；维护者尚未亲自阅读调用点。
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/stingray.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
latitude-llm
Open-source observability for AI agents that flags where agents fail in their traces. A shadow provider asks Jev one noul per flagger dimension, at most 11 per call; the cited file does not show whether those answers change any flag, and the README does not mention Jev.
reticle
Checks an agent's "done" by driving the running app and returning pass, fail or cannot tell. Its benchmark harness asks Jev, in one call on captured evidence, five nouls (did the intended consequence happen, is the capture clean, did the app error), a pass/fail/unknown choice and a severity score.
celesto
Secure and persistent computer for AI agents -- build your own Grokbot, and Muse.
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.
abide
Hooks into Claude Code, Codex, OpenCode and Pi and, on every edit or turn, asks Jev one yes-or-no question per rule in AGENTS.md or CLAUDE.md, showing only the rule and the diff; a broken rule goes back to the agent to fix. On 93 replayed sessions Jev flagged 39 edits; a reviewer confirmed 10.