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 agentmods add skills/hackerfish/awesome-dsh-skills/dsh-plugin-devnpx skills add hackerFish/awesome-dsh-skills --skill dsh-plugin-devgit clone --depth 1 https://github.com/hackerFish/awesome-dsh-skillsWrote 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/hackerfish/awesome-dsh-skills/dsh-plugin-dev)<a href="https://agentmods.dev/skills/hackerfish/awesome-dsh-skills/dsh-plugin-dev"><img src="https://agentmods.dev/badge/skills/hackerfish/awesome-dsh-skills/dsh-plugin-dev.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00035 | $0.00591 |
| Opus 5 | $0.00017 | $0.00296 |
| Sonnet 5 | $0.00007 | $0.00118 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
dsh-plugin-dev 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 6d 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.
What it actually says
DSH 插件开发（依据官方包验证过的结构）
最小形态
插件 = 一个 npm 包 + dsh.bundle 声明（字段取自官方 @deepseek-ai/dsh-base 的真实清单）：
// package.json（节选）
{
"name": "my-dsh-plugin",
"version": "0.1.0",
"main": "lib/index.js",
"dsh": { "bundle": { "patch": "./cordis.patch.yml" } }
}
cordis.patch.yml 是往 profile 配置栈插入的行列表（结构取自官方 base 清单）：
- insert:
- id: my-plugin
name: 'my-dsh-plugin'
config: {}
规则：行按 id 定位，后写覆盖先写，且整行替换 config 而非合并；行顺序不代表加载顺序。
调试循环
dsh plugin --profile web add /path/to/my-dsh-plugin --ignore-workspace-root-check
dsh --profile web --dump-config # 确认你的行进入配置
- 隔离测试：把
DSH_HOME指向临时目录，不污染真实环境 - 干净安装必须成功；改代码后重新 add 再验
- 冒烟：
dsh --profile headless "最小任务"确认不崩（需模型凭据）
发布与收录
npm publish（确保files包含cordis.patch.yml与构建产物）- GitHub 仓库打
dsh-plugintopic - README 写明开发/测试时的 DSH 版本（rc 期 API 在变）
- 向社区目录提收录 PR，描述自己写
注意
- 依赖能省则省；避免
postinstall/prepare脚本（会让用户安装变复杂） - 官方当前不接受外部 PR，生态贡献以插件与内容为主
- 细分主题走专门技能：client 半端见
dsh-plugin-client，UI 国际化见dsh-plugin-i18n，发布与生态收录见dsh-plugin-publish
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.
- 6d ago First seen · 57 lines · 35 tokens per session scan A 5095355de6ce
dsh-plugin-dev is a skill published in the GitHub repository hackerFish/awesome-dsh-skills (5 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 591 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
dsh-first-plugin
当需要从零做出并装上第一个 DSH 插件时使用——给出跑通的完整流程（写文件、写 overlay、加载、验证），以及实测会踩到的三个报错和它们的确切修法。.
dsh-plugin-dev
当需要给 DeepSeek Harness 写插件、调试插件没加载或没注入的问题、或理解 Cordis 的组件生命周期时使用——覆盖导出规则、依赖声明、可逆效应和加载路径陷阱。.
dsh-skill-dev
当需要给 DeepSeek Harness 写一个技能、调试技能没被发现的问题、或决定某个能力该做成技能还是插件时使用——覆盖 frontmatter 规则、发现路径、fail-closed 陷阱和自测方法。.
api-design
当需要设计接口、给模块加公开方法、定义数据结构或评估某个 API 该不该存在时使用——按"有几个真实调用方"来判断必要性，优先让错误用法无法编译。.
code-review-cn
当需要审查代码改动、pull request 或 diff 时使用——按正确性、生命周期、安全、测试强度的顺序给出中文审查意见，优先给出少数有依据的阻断项而不是一堆风格挑剔。.
dsh-onboarding
当用户第一次使用 DeepSeek Harness（DSH），或在启动、工作区、权限、技能发现环节卡住时使用——解释 DSH 的进程模型、目录约定和权限边界，并给出可自查的排错路径。.