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 pingfanfan/hello-dsh --skill dsh-first-plugingit clone --depth 1 https://github.com/pingfanfan/hello-dshWrote 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/pingfanfan/hello-dsh/dsh-first-plugin)<a href="https://agentmods.dev/skills/pingfanfan/hello-dsh/dsh-first-plugin"><img src="https://agentmods.dev/badge/skills/pingfanfan/hello-dsh/dsh-first-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/pingfanfan/hello-dsh/dsh-first-plugin"><img src="https://agentmods.dev/badge/skills/pingfanfan/hello-dsh/dsh-first-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 23 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 85 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 94 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 171 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00060 | $0.01550 |
| Opus 5.5 | $0.00024 | $0.00620 |
| Sonnet 5.5 | $0.00012 | $0.00310 |
| Haiku 4.5 | $0.00006 | $0.00155 |
Grade A, and why
dsh-first-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 1mo 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
做出你的第一个 DSH 插件
这是一条实测跑通过的路径,不是从文档推的。下面每个报错都真实遇到过,修法也都验证过。
环境:DSH 0.1.0-rc.6,Node 20+。
先问一句:真的需要插件吗
如果你想做的事用自然语言就能说清楚(改变模型的判断标准、输出格式、工作流程),写技能,一个 Markdown 文件,五分钟搞定,也不会被上游 API 变更打挂。
只有需要注册新工具、接外部服务、挂生命周期钩子时才需要插件。
完整流程
一、装 DSH,确认能跑
npx @deepseek-ai/dsh --version
二、写插件
hello-plugin/src/hello.ts:
import type { Context } from '@deepseek-ai/cordis'
import { defineTool } from '@deepseek-ai/dsh-tools'
export const name = 'hello-plugin'
export const inject = ['tools']
export function apply(ctx: Context) {
ctx.tools.register(defineTool({
name: 'pingfan_hello',
description: '返回一句固定问候,用于验证第三方插件是否加载成功。',
parameters: {
who: { type: 'string', description: '要问候的对象' },
},
output: {
schema: {
type: 'object',
additionalProperties: false,
properties: {
greeting: { type: 'string', required: true },
},
},
render: (_args, value) => [{ type: 'text', text: value.greeting }],
},
execute(args) {
const who = args.who ?? 'world'
return Promise.resolve({ greeting: `HELLO to ${who}` })
},
}))
}
三、写 overlay
hello-plugin/cordis.yml:
- insert:
- id: hello
name: '/绝对/路径/hello-plugin/src/hello.ts'
路径必须是绝对路径。 生成方式:
cat > cordis.yml <<EOF
- insert:
- id: hello
name: '$(pwd)/src/hello.ts'
EOF
四、加载并验证
DEEPSEEK_API_KEY=sk-xxx npx @deepseek-ai/dsh --profile headless \
--patch ./cordis.yml "调用 pingfan_hello 工具,参数 who 填 test"
看到工具返回的内容就说明成功了。
Web UI 同理:
npx @deepseek-ai/dsh web --patch ./cordis.yml
实测踩到的三个报错
按遇到的顺序,都是真实报错原文。
报错一:must declare output { schema, render, presentationMeta? }
tool "pingfan_hello" must declare output { schema, render, presentationMeta? }
原因:工具注册必须声明 output,里面要有 schema(返回值的结构)和 render(怎么渲染给模型看)。只写 name/description/parameters 不够。
修法:补上 output 块,见上面的完整例子。
报错二:parameters.who.required must be true when present
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.
- 1mo ago First seen · 188 lines · 60 tokens per session scan A b264dc645971
dsh-first-plugin is a skill published in the GitHub repository pingfanfan/hello-dsh (102 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 1,550 once invoked, about $0.0002 per session on Opus 5.5. 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…
skill
Ten native DSH tools give a text-only agent eyes. Use these structured tools directly; do not shell out to the bundled Python scripts or reproduce their implementation. Vision API credentials and model settings are managed by the plugin, so tool calls do not receive credentials.
modsearch
Plug-in web search, X (Twitter) search, and page fetch for models without native web access. Use whenever the task needs current information, external facts, source links, posts from X, or the content of a specific URL, and the active model/harness has no native search or fetch tool. Runs the modsearch CLI to return…
submit-dsh-plugin
A submission checklist and workflow for adding a DeepSeek Harness plugin to the community’s public catalogue. It prepares the catalogue entry and checks the plugin’s repository, metadata, tests, and required files.
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.