Aik358/dsh-anchored-monitor
DeepSeek Harness的实时思维链锚定监控与干预插件:三频段(规范/混合/反应)指纹检测、L1提示/L2重置/L3重启干预、液态玻璃网页叠加层+变阻器条、独立监控进程及JSONL实验日志。
Project Overview项目介绍
This is a native DSH plugin built exclusively for DeepSeek Harness, designed to monitor the reasoning trajectory of DeepSeek V4 Pro in real time. It scores every reasoning block based on keyword fingerprints for “we”-style focused reasoning versus “let me”-style scattered reasoning, sorts results into three focus bands, and displays a real-time thinking efficiency gauge in the corner of your DSH interface. By default, it operates in visualization-only mode, but you can enable automatic intervention that pulls the model back when it drifts into low-focus scattered mode.
The plugin works with any DSH preset that follows anchored discipline, including the official Minimal preset, Liang-god Mode, and other derivatives built on the anchoring idea. You do not need to modify your existing preset to use it, because the plugin reads reasoning event logs from local DSH sessions directly to calculate its scores. If you enable intervention mode, it will automatically push the model back on track when it drifts into the scattered low-efficiency focus band.
This plugin is released under the open-source MIT license, and requires Node.js version 22.19.0 or higher to run. The automatic intervention feature is recommended only for DeepSeek V4 Pro 0813; for all other models, users should keep the plugin in monitor-only mode as a live gauge. If your starting prompt is not properly anchored, the plugin will incorrectly trigger continuous interventions, so it should only be used with presets that follow the anchoring standard.
这是一个专为DeepSeek Harness开发的原生插件,用于实时监控DeepSeek V4 Pro的推理轨迹。它会根据每个推理块中「we」类(聚焦模式)和「let me」类(发散模式)关键词指纹打分,划分三个专注度区间,并在界面角落显示实时思考效率仪表盘。默认仅做可视化,也可设置为模型漂移到低专注模式时自动干预。
适用于使用锚定预设(比如基于最小人设、梁神模式开发的各类预设)的DSH用户,用来监控推理过程是否偏离预设的锚定轨迹。使用时无需额外修改预设,插件会自动读取本地会话中的推理事件日志完成打分,开启干预后,当模型掉入发散低效率区间时会自动拉回正轨。
插件遵循MIT许可免费开源,要求Node.js版本不低于22.19.0,干预功能推荐仅对DeepSeek V4 Pro 0813版本开启,其他模型建议仅开启监控功能。如果会话一开始就没有锚定,插件会持续误触发干预,因此仅推荐搭配遵循锚定规范的预设使用。
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】,检查通过再动手。
插件:dsh-anchored-monitor(Aik358/dsh-anchored-monitor)
仓库:https://github.com/Aik358/dsh-anchored-monitor
本站详情页:https://www.yhbd.top/plugins/aik358-dsh-anchored-monitor/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 10 · 最近提交 2026-09-05 · 主语言 JavaScript
按下面顺序执行,每步先把结论告诉我,再进入下一步:
【1 兼容性检查】
① 我这边:DSH 版本、Node 版本、操作系统、当前 profile(web / desktop)。
② 读它的 README、package.json、插件 manifest,列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对,结论只写「满足 / 不满足 / 未知」三种;不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突:命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。
【2 安全性检查】
① 仓库可信度:和上面「本站登记」是否一致;star / fork 数、创建时间、最近提交,是否归档或长期停更。
② 安装脚本:逐行看 package.json 的 preinstall / install / postinstall,以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名,立刻停下来告诉我,不要继续装。
③ 依赖:列出新增依赖,标出无人维护、或与知名包拼写近似的可疑包(typosquatting)。
④ 权限与副作用:它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限(filesystem / network / shell / clipboard 等),以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限,或权限明显超出功能所需,先停下来问我。
【3 安装】
上面两步没有「不满足」和「高危项」时才执行;用官方推荐方式安装,不要自行提权。
【4 汇报】
用表格输出:检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜,也不要替我决定。
Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH:它会先核对兼容性与安全性(逐条给「满足 / 不满足 / 未知」),确认没问题再安装,有高危项会停下来问你。框内可滚动,复制到的是完整提示词;安装命令不一定准确,发给 DSH 更稳。
- 10 stars - an early-stage project星标 10,属于早期项目
DSH walks through these 9 checksDSH 会逐条核对这 9 项
Compatibility兼容性
- DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
- External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
- Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册
Security安全性
- Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
- Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
- curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
- Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
- Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
- Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式
Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。
Or use CLI install (for developers)或使用命令行安装(适合开发者)
CLI Install命令行安装
dsh plugin --profile web add @a9i5k4/dsh-anchored-monitor
把 Aik358/dsh-anchored-monitor 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
dsh-anchored-monitor
English | 简体中文
In one sentence (一句话说清): it's a whip for DeepSeek V4 Pro. When the model falls from the focused, high-capability mode ("We need…" / "I will…") into the scattered, low-focus mode ("let me…"), the whip cracks — and pulls it back. 这是给 DeepSeek V4 Pro 加的一根鞭子——当它从「We need / I will」的高专注、高能力模式, 跌落到「let me」的发散、低专注、低效率模式时,就抽它一鞭,让它改回去。
Real-time chain-of-thought anchoring monitor & intervention for DeepSeek Harness. Watch the we / let's / let me fingerprint of every reasoning block, stay in the spec band, and pull the model back automatically when the trajectory drifts.

What it is, in one line
Don't touch a thing and it's simply a live gauge of how hard your model is thinking right now. Thinking intensity, three-band state and the ECG-style curve, tucked into the corner of your screen — a real-time visualization of your model's thinking efficiency / capability intensity.
- Visualization first (default — no intervention until you want it): a real-time thinking-efficiency / capability-intensity gauge.
- Intervention when you need the whip: only cracks when the trajectory drifts into the scattered "let me" band — and it auto-continues the task.
- 「滑动变祖器」meme skin: flip the gauge into a Liang-o-meter that live-queries DeepSeek V4 Pro's "梁系强度" (from focused-humble to emperor-slacking) while it runs.
Open the settings page and you can tune every parameter — and one-click Reset to defaults if you ever change too much.
Which mode does it pair with?
You don't need to force-install dsh-anchored-standard.
The monitor never checks a preset's name. It reads every session's reasoning
blocks (~/.dsh/sessions/*/events.jsonl) and scores them purely by the
we / let's / let me fingerprint (spec band < 0.2, mixed 0.2–0.5, react ≥ 0.5).
So any preset that implements the anchored-standard discipline — anchor the
first turn with the Minimal persona (46-character persona + bash/str_replace_editor),
then plan in a collective "we" style without "let me" — pairs with this plugin.
Renamed / derivative presets work too: 梁神模式 (Liang-god Mode), liangshen,
and any other preset built on the same anchoring idea. The L2 reset payload is
fully self-contained (the Minimal 46-character persona + the dual tools ship in
this plugin's own config), so nothing is imported from another repo at runtime.
Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要,完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →
gjj-star/dsh-conversation-navigator
masknull/dsh-qoder-connect
HuanLinOTO/dsh-plugin-ya-workspace-sidebar
EugeneVl/dsh_session_folders
lw-storm/dsh-plugin-masterprompt
Yiheng-guo/dsh-boot-animation-pro
taoser258/dsh-client-ui-skin-qingxiao