dsh-web is a plugin ecosystem that adds a web interface and optional tools to DeepSeek Harness, an AI development environment. It is used to provide features such as task boards, mobile remote control, SSH operations, image understanding, file and code panels, Git views, agent presets, and interchangeable skins through independently loaded plugins. The catalogue skills are plugins and related workflows for extending and operating the DSH Web environment.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add zhu1090093659/dsh-web --skill dsh-web-pet-developergit clone --depth 1 https://github.com/zhu1090093659/dsh-webWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zhu1090093659/dsh-web/dsh-web-pet-developer)<a href="https://agentmods.dev/skills/zhu1090093659/dsh-web/dsh-web-pet-developer"><img src="https://agentmods.dev/badge/skills/zhu1090093659/dsh-web/dsh-web-pet-developer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zhu1090093659/dsh-web/dsh-web-pet-developer"><img src="https://agentmods.dev/badge/skills/zhu1090093659/dsh-web/dsh-web-pet-developer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00162 | $0.03223 |
| Opus 5 | $0.00081 | $0.01612 |
| Sonnet 5 | $0.00032 | $0.00645 |
| Haiku 4.5 | $0.00016 | $0.00322 |
Grade A, and why
dsh-web-pet-developer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
宠物开发者（dsh-pet 多宠物注册表）
本技能指导制作并接入一只宠物到 dsh-pet（GUI 右下角桌面宠物 + 设置页一级菜单「宠物」）。
宠物是注册表条目而不是代码：一只宠物 = 一个目录 + 一份 pet.json manifest + 一张图集
（可选 voice.json 语音包与状态装饰 decoration），新增宠物不需要改任何宿主或客户端代码。
契约按 pet-center 里程碑演进（issue #623）：M1 场景/动画语义、M2 manifest v2 结构校验、
M3 live2d、M4 voice pack（#677）、M5 状态装饰（#567）。
0. 宠物契约（硬性约束，违反会被跳过或拒绝）
契约的权威实现是 packages/dsh-pet/src/manifest-v2.ts（结构门，fail-closed）与
registry.ts（归一化，never-throw）；JSON Schema 孪生文件在
packages/dsh-pet/contracts/pet-manifest-v2.schema.json（文档与 CLI 用，仓库内以手写校验器为准）。
完整示例：packages/dsh-pet/assets/whale/pet.json（id whale-girl，v2 全量：frames/tracks
覆盖 + sequences + license）与 assets/whale-refined/pet.json（id whale-girl-refined，
最小 v2）。v1 manifest 兼容读取（附迁移提示）；v2 manifest fail-closed：未知顶层键、未知
renderer、缺失条件块与不安全路径都会拒绝该条目并给出结构化诊断。
- 顶层字段：
petManifestVersion=2、id（^[a-z0-9][a-z0-9-]*$小写 kebab）、displayName（≤ 80 字符）、description/version/author/homepage可选、license（v2 必填）、renderer（sprite2d|live2d）、sprite2d{}/live2d{}、sequences、remarks。 sprite2d块：spritesheetPath（安全相对路径：无..、无绝对路径、无反斜杠、 无协议 scheme，段字符^[A-Za-z0-9._-]+$，缺省spritesheet.webp）；cell缺省 192×208（上限 2048）；columns缺省 8（上限 32）；atlasRows缺省 9（v2 图集可声明 11 = 9 动画行 + 2 行 look 行）；frames每行用到的列数（9 个 1..columns 整数），缺省 hatch-pet 契约表[6, 8, 8, 4, 5, 8, 6, 6, 6]；tracks按动画覆盖durations（正数毫秒，按该行帧数循环补足）、loop、fallback；缺省全部循环，jumping与failed停在末帧后回idle。- 图集几何：8 列 × 9 行（v2 图集 11 行），行序固定：0 idle / 1 running-right / 2 running-left / 3 waving / 4 jumping / 5 failed / 6 waiting / 7 running / 8 review； 未用格子保持全透明。
sequences：按 ActivityPhase（idle / waiting / thinking / tool / review / done / failed） 覆盖场景轨道序列，每个序列至少 5 个动画，否则该序列丢弃（warning，宠物保留默认单轨）。remarks：交互俏皮话槽位覆盖（每行 ≤ 120 字符，每槽 ≤ 64 行），社区宠物可用它配音。voice.json（M4，#677）：宠物目录内可选语音包（状态文案池 + 悬浮面板 chrome），纯内容 warn-and-drop；全局覆盖放$DSH_HOME/pets/.voice.json（垫底于每个宠物包之下）。- live2d（M3）：
renderer: "live2d"+live2d{}块（model相对路径 .model3.json、scale(0,10]、translate、motions（idle 必填，未映射相位回退 idle）、expressions、hitAreas、lipSync）。model3.json 的引用闭包 = 资产路由的可服务集合；模型不可读或声明 不安全引用 → fail-closed 拒绝。Cubism Core 由用户自供 （$DSH_HOME/pets/.runtime/live2dcubismcore.min.js），插件永不打包或下载。 - 可选
previews/<name>.gif（文件名^[A-Za-z0-9._-]+$），经/pet/<id>/previews/<name>提供（README 动画预览表用它）。 - 资产大小上限（路由强制）：manifest 64 KiB / 图片 20 MiB / live2d 模型文件 32 MiB。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 123 lines · 162 tokens per session scan A 9323e331eea5
dsh-web-pet-developer is a skill published in the GitHub repository zhu1090093659/dsh-web (7,321 stars, last pushed today), licensed Apache-2.0. It adds 162 tokens to every session and 3,223 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
blender-motion-state-inspection
Use this skill when inspecting Blender characters, rigs, poses, animation retargeting, ground contact, facing direction, or model-vs-motion alignment where screenshots alone are not enough.
manage-taskboard
Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions. Use when an Agent must inspect project work, claim an eligible todo, record progress or blockers, verify an implementation, submit it for human review, or release its own claim; also use when a human asks how to accept…
industry-research-method
A Chinese-language method for researching an industry by mapping its supply chain, tracking policies and news, and writing sourced reports. It separates the chain into upstream inputs, midstream production, and downstream distribution or use.
company-research-method
A documented process for researching a company using supplied files and selected public sources. It produces a company overview with business details, sourced financial figures, and stated risks.
dsh-plugin-guide
Use when developing, reviewing, packaging, debugging, or answering questions about DeepSeek Harness (DSH) plugins — the plugin-based agent harness on vendored Cordis. Applies the official plugin-development constraints (plugin contract, cordis.yml layers, services/events/effects, tool DSL, bundles/profiles) backed by…
xiaohongshu-creator
A Xiaohongshu content-creation tool for generating and rewriting posts, creating and scoring titles, planning cover designs, and checking restricted words. Xiaohongshu is a Chinese social platform where users publish posts with text, images, and tags.