DeepSeek Harness plugin

naked-fetch

DeepSeek Harness 插件:极简智能体浏览器(naked-fetch)→ web_fetch / web_search_bing 工具,自带引擎零外部依赖

Jump to install

Source facts

Repository
Kaeno-Tori/naked-fetch
Latest update
Aug 15, 2026
Category
Workflow & Automation
GitHub stars
0
Format
plugin
Package path
dsh
Catalog evidence
Upstream dsh.bundle evidence
Evidence path
dsh/package.json#dsh.bundle
Checked against
0.1.0-rc.8
Upstream check date
2026-08-21

This evidence comes from the upstream catalog. This site has not installed, run, or security-reviewed the plugin.

Install

Start with a prompt that asks an agent to review the GitHub repository and source. Switch to the command if you want to install it yourself.

Copy this prompt into DSH, Codex, or another agent and ask it to review the GitHub repository and source first.

Do not install or run any commands yet. Read this plugin's GitHub repository, README, and relevant source code. Then answer the questions below clearly and directly so I can decide whether it fits my needs:

1. What is this plugin, and what problem does it solve?
2. Who is it for, and what are its typical use cases?
3. How is it used after installation? Include one minimal example.
4. What known limitations or privacy, security, compatibility, or maintenance risks does it have?
5. Give a clear recommendation: recommend, conditionally recommend, or do not recommend, with reasons.

Distinguish statements documented by the repository, inferences from source code, and unknowns. If evidence is insufficient, say so explicitly. Do not guess or simply repeat the README.

GitHub: https://github.com/Kaeno-Tori/naked-fetch/tree/HEAD/dsh
Plugin: naked-fetch
Author: Kaeno-Tori

Check the source files

Read the README and other files from this plugin directory before installing.

File explorer2 files
README.mdSource · read only

naked-fetch-dsh — DeepSeek Harness 适配插件

把 [naked-fetch](../README.md)(极简智能体浏览器)注册为 DSH agent 的 naked_fetch / naked_search 两个工具。

引擎内嵌:本包自带全部代码(vendor/),npm i naked-fetch-dsh 即得,无外部依赖。

安装(两种方式)

方式 A:profile 安装(推荐,一次装好所有会话)

# 1. 安装 npm 包(含 naked-fetch 依赖)
npm i -g naked-fetch-dsh        # 或装到 DSH profile 的 node_modules

# 2. 把 bundle 加入 profile
#    编辑 ~/.dsh/profiles/<profile>/package.json:
#    "dsh": { "profile": { "bundles": [..., "naked-fetch-dsh"] } }

重启 dsh 后,所有会话的 agent 都能调用 naked_fetch / naked_search

方式 B:agent 自助(动态插件,单会话)

把你的 agent 指向下面的"自助安装"说明(或直接让它读本 README):

> 用 cordis_define(idPrefix: webt,code.host 为 examples/dsh-plugin.mjs 的函数体,把 WEB_TOOL 设为 naked-fetch 包 cli.js 的绝对路径(可在外部用 createRequire 解析 naked-fetch/package.json 得到)),然后 cordis_run。工具立即在当前会话可用;重启后需重装(动态插件不持久)。

工具

工具参数说明
naked_fetchurl*, timeout, raw, js, engine抓取 + AI 去噪提取;SPA 空壳自动渲染兜底(firefox→chromium,Via 模式)
naked_searchquery*, count, engine网页搜索(bing/baidu/ddg/google),无 API key

设计

  • 函数插件格式(name/inject/Config/apply),与 DSH 官方包同构
  • 注册走 ctx.tools.register(ToolDefinition),disposer 交给 ctx.effect(stop/update 自动撤销)
  • 执行走 ctx.subprocess spawn node naked-fetch cli.js --jsonexec.signal 绑定进程树终止)
  • config.webToolPath 可覆盖 cli.js 定位

打包发布

cd dsh
npm publish    # 依赖 naked-fetch 先发

Credits

由运行在 DeepSeek Harness 上的 AI agent 协作开发——本插件即"agent 给自己写插件"的产物。