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-plugin-devgit 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-plugin-dev)<a href="https://agentmods.dev/skills/pingfanfan/hello-dsh/dsh-plugin-dev"><img src="https://agentmods.dev/badge/skills/pingfanfan/hello-dsh/dsh-plugin-dev/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-plugin-dev"><img src="https://agentmods.dev/badge/skills/pingfanfan/hello-dsh/dsh-plugin-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 160 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 | $0.00055 | $0.01758 |
| Opus 5.5 | $0.00022 | $0.00703 |
| Sonnet 5.5 | $0.00011 | $0.00352 |
| Haiku 4.5 | $0.00006 | $0.00176 |
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 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
给 DSH 写插件
插件是 TypeScript 模块,跑在 Cordis 之上。DSH 处于 developer preview,官方明确警告有破坏性变更,所以任何行为都要在当前版本上验证。
先问一句:这件事非要插件不可吗? 如果用自然语言就能说清楚要模型做什么,写技能(一个 Markdown 文件)成本低一个数量级,也不会被上游 API 变更打挂。需要执行代码、接外部服务、挂生命周期钩子的,才需要插件。
最小形态
import type { Context } from '@deepseek-ai/cordis'
export const name = 'my-plugin'
export const inject = ['tools']
export function apply(ctx: Context) {
// 在这里注册能力
}
加载方式是写一个 overlay:
- insert:
- id: my-plugin
name: '/absolute/path/to/my-plugin.ts'
dsh web --patch ./my-plugin/cordis.yml
路径必须是绝对路径,官方文档明确要求,相对路径不会被解析。
第一个致命陷阱:不要写 default export
这条有官方事故复盘(docs/postmortem/0001),值得完整理解。
export const name = 'acp'
export const inject = ['agents', 'sessions']
export function apply(ctx, config) { }
export default apply // ← 这一行会让插件彻底失效
Loader 的 unwrapExports 逻辑是 exports.default ?? exports,优先取默认导出。有 export default 时,它解析出来的是裸的 apply 函数,而 inject、name、Config 是挂在模块命名空间上的同级命名导出,取 .default 那一步把整个命名空间丢掉了。
Loader 于是用一个空的 inject 构建 fiber。插件在什么服务都没注入的环境里运行,第一次访问 ctx.xxx 时沿 fiber 树一路找到根,抛出 cannot get property "agents" without inject。
崩在加载时,不是请求处理时。
当时这个 bug 有 178 个绿色测试和 100% 行覆盖率,因为所有测试都是手动挂载插件的,绕过了真实 Loader 路径。
规则:命名空间插件只用命名导出,绝不加 default export。
第二个致命陷阱:!!js 只在 config 里有效
同样有官方复盘(docs/postmortem/0002)。
- insert:
- id: fs
name: '@deepseek-ai/dsh-tool-fs'
disabled: !!js ctx.mode !== 'full' # ← 永远为真
config:
root: !!js process.cwd() # ← 这里才有效
Cordis 只对插件的 config 做递归插值。disabled、isolate、intercept 这些配置项元数据是直接读取的,拿到的是表达式对象,而对象恒为 truthy。结果是插件在所有模式下永久禁用,且无任何诊断。
规则:条件组合用显式的 overlay 文件,不要在元数据字段上写表达式。
注册工具的两个实测坑
ctx.tools.register() 的参数形态跟直觉不一样,这两条是实际跑出来的报错:
一、必须用 defineTool() 包裹,且必须声明 output
tool "xxx" must declare output { schema, render, presentationMeta? }
output 里要有 schema(返回值的 JSON Schema)和 render(渲染函数)。
二、parameters 不是标准 JSON Schema,且 required 只能填 true
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 · 178 lines · 55 tokens per session scan A a1b20e5fdbf3
dsh-plugin-dev is a skill published in the GitHub repository pingfanfan/hello-dsh (101 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 1,758 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.