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 imsai-sh/awesome-deepseek-harness-plugins --skill submit-dsh-plugingit clone --depth 1 https://github.com/imsai-sh/awesome-deepseek-harness-pluginsWrote 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/imsai-sh/awesome-deepseek-harness-plugins/submit-dsh-plugin)<a href="https://agentmods.dev/skills/imsai-sh/awesome-deepseek-harness-plugins/submit-dsh-plugin"><img src="https://agentmods.dev/badge/skills/imsai-sh/awesome-deepseek-harness-plugins/submit-dsh-plugin/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/imsai-sh/awesome-deepseek-harness-plugins/submit-dsh-plugin"><img src="https://agentmods.dev/badge/skills/imsai-sh/awesome-deepseek-harness-plugins/submit-dsh-plugin.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 | $0.00103 | $0.02673 |
| Opus 5 | $0.00051 | $0.01337 |
| Sonnet 5 | $0.00021 | $0.00535 |
| Haiku 4.5 | $0.00010 | $0.00267 |
Grade A, and why
submit-dsh-plugin 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 10d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
提交 DSH 插件
从插件作者的仓库准备一份聚焦的目录收录 PR。始终把 catalog/plugins/*.json 视为贡献者唯一可以编辑的目录源数据。
安全与范围
- 不得在插件提交 PR 中编辑
README.md、catalog/README.md、工作流或脚本。两个 README 是 bot 生成的目录投影，合并后由 CI 自动刷新。 - 不得仅为了检查插件而安装依赖、运行生命周期脚本、构建或执行插件代码。运行作者代码前必须先征得同意。
- 保留所有无关的本地改动。如果目录仓库工作区不干净，应停止操作；除非用户指定一个干净 worktree，或明确界定现有改动的范围。
- 将“准备”或“起草”理解为仅做本地修改。只有用户明确要求“提交”“推送”或“创建 PR”时，才视为已授权在展示准确目标后执行 fork、push 和创建 PR。
- 不得手动合并 PR，也不得修改生成投影。合规的非草稿新增类目录 PR 会在可信静态审查通过后自动合并；修改或删除既有条目的 PR 即使静态审查通过也不会自动合并，必须等待目录仓库维护者人工审核后手动合并。合并进入
main后，CI 自动把目录条目同步到网站数据库（D1）并重新生成两个 README，即自动同步，无任何维护者手工步骤。
1. 明确提交信息
确定以下内容：
- 插件 ID：仓库级插件为
owner/repository；monorepo 子包插件为owner/repository/sub/dir，前两段之后的路径段指向仓库内的子目录 - 插件名称：仓库级插件通常与仓库名一致，子目录 ID 默认取最后一个路径段（子包目录名）
- 一个主要目录分类
- 客观的英文与中文简介
- 作者实际执行的测试命令和结果
ID 各段仅限 A-Za-z0-9_.- 字符，路径段不得是 . 或 ..，总长不超过 201 字符。无论 ID 是否携带路径，条目的 repository 字段始终是由前两段推导的仓库根 URL https://github.com/owner/repository。ID 的路径段锁定插件源码位置：子目录 ID 的 <sub/dir>/package.json 必须恰好是插件的 manifest。安装入口只来自发布到 npm 的包（1024 Store 仅提供 npm 安装），目录条目本身只记录源码仓库。
目录仓库固定使用 https://github.com/imsai-sh/awesome-deepseek-harness-plugins。创建文件前，读取其当前 checkout 中的 CONTRIBUTING.md 和 catalog/categories.json；如果线上仓库规范与本 Skill 不同，以线上规范为准。
选择分类或编写 PR 时，读取 references/submission-reference.md。
2. 检查插件仓库
先完成只读检查：
- 确认仓库公开且存在默认分支。
- 确认仓库包含
dsh-pluginGitHub topic。如果缺少 topic、用户拥有该仓库且已授权外部写入，才可执行gh repo edit owner/repository --add-topic dsh-plugin。topic 作用于仓库本身：gh repo edit的参数只取 ID 的前两段owner/repository，子目录 ID 的路径段不参与。 - 定位插件的 manifest：两段 ID 可使用根目录或任意嵌套的
package.json（排除node_modules）；子目录 ID 则必须在<sub/dir>/package.json恰好找到 manifest——ID 的路径就是插件在仓库中的位置，仓库里其他位置的 manifest 不算数。 - 确认其中声明了非空字符串
dsh.bundle.patch。 - 相对于声明该字段的
package.json解析补丁路径；拒绝绝对路径、反斜杠以及跳出仓库的路径。 - 确认 manifest 和引用的补丁都存在于 GitHub 默认分支，而不只是尚未推送的本地提交。
- 向作者说明安装可用性：1024 Store 只提供 npm 安装，不再提供 GitHub 源码安装。
网站会自动探测 manifest 中声明的 npm 包名；只要 npm 上的 latest manifest 声明
dsh.bundle，插件即可安装（repository回链缺失或不一致不影响验证）。 未发布 npm 包不影响收录：插件照常收录，以浏览模式展示（有仓库链接，无安装命令），PR 评论会提示作者发布 npm 包后目录自动检测、无需追加 PR。 - 记录作者实际执行的兼容性测试。如果尚未测试，应停止并要求作者先测试；目录自动审查不会执行第三方代码。
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 134 lines · 103 tokens per session scan A fad2bd20b373
submit-dsh-plugin is a skill published in the GitHub repository imsai-sh/awesome-deepseek-harness-plugins (225 stars, last pushed yesterday), licensed MIT. It adds 103 tokens to every session and 2,673 once invoked, about $0.0005 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
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…
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
auto-research-loop
A bounded research workflow that repeats four steps: planning, searching, reading, and combining findings. It records each step and its sources so the work can resume after an interruption.
code-review
A structured code-review workflow for examining one fixed code change. It checks correctness, security, tests, and maintainability in that order.
dsh-plugin-schemes
A set of rules for choosing the right kind of DeepSeek Harness extension before building it. It explains the differences between bundles, local patches, agent presets, skills, and temporary runtime plugins.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.