DSH Marketplace

modsearch

liustack/modsearch

Web search bridge for text-only agents: ask the web or X, get structured JSON evidence (search, fetch, citations).

1336TypeScriptMITSource

Install

Add modsearch to DeepSeek Harness

via npm

Resolves a published tarball rather than cloning the repository, and installs without any extra setup. Swap `web` for your profile name if you run another one.

via GitHub · npm package

Installing from GitHub runs the project's build script, which pnpm blocks until you allowlist it — run the command once and pnpm prints the exact key to add under `allowBuilds` in ~/.dsh/profiles/web/pnpm-workspace.yaml.

What happened when we ran it

Installed cleanly when we ran it

Every command here is run in a throwaway container against a clean profile, and the result is whatever the harness recorded — not a guess from the source. Last run yesterday.

Due diligence

Before you install modsearch

  • Source of record: liustack/modsearch — present in the community registry that DSH's own plugin market installs from.
  • Licensed under MIT.
  • Detected: terminal surface. Read the source before granting these.
  • A listing here is not a security review. Plugins run with your agent's permissions.

The AI take

What it is — ModSearch provides web search, X search, and page fetching capabilities for text models in DeepSeek Harness.

Who it is for — When using DeepSeek-V4-Flash for tasks requiring up-to-date information, it supplements web search capabilities. If you use a model with native web access, it is not needed.

Watch out — Installation requires browser login for the default engine or free API keys from alternatives. Sandbox test passed: works in fresh profile and registered. The plugin executes shell commands. No obvious issues found.

The verdict — I would install it because of the free default engine and automatic failover support.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.

What modsearch does

Abstract diagram of scattered web signals converging into structured evidence cards.

modsearch is a DeepSeek Harness plugin that adds web, X, and single-page reading tools for text-only agents. It connects the harness’s built-in web_search to an engine chain, adds x_search and read_page, and returns structured JSON evidence with sources and citations. The available engines are Antigravity CLI, Tavily, Exa, Firecrawl, Grok Build, and the built-in local fetcher; configured engines fail over when one fails or exhausts its quota.

Configuration is stored in ~/.modsearch/config.json with mode 0600. API credentials can be set with modsearch config set tavily.apiKey, modsearch config set exa.apiKey, or modsearch config set firecrawl.apiKey, or supplied through TAVILY_API_KEY, EXA_API_KEY, and FIRECRAWL_API_KEY. The plugin can also use compatible endpoints through each engine’s baseURL setting.

It is intended for agents that need current web evidence, X search, or focused page extraction beyond the harness’s native search. It is a poor fit when existing web_search is sufficient, or when external engine setup is unacceptable: Antigravity CLI needs browser sign-in, X search needs Grok Build with SuperGrok or X Premium, and API engines require quotas or credentials. The terminal surface reaches the host terminal to install or run helper CLIs such as agy and grok, and to run the plugin’s configuration commands.

modsearch documentation

Configuration

modsearch uses an engine chain. The default channel is Antigravity CLI, which is free but requires browser sign-in. API credentials may be stored in ~/.modsearch/config.json with file mode 0600, or supplied through environment variables.

Engine Capability Configuration
Antigravity CLI Web search and page fetch Install agy and sign in
Tavily Web search tavily.apiKey; TAVILY_API_KEY
Exa Web search exa.apiKey; EXA_API_KEY
Firecrawl Web search and page fetch firecrawl.apiKey; FIRECRAWL_API_KEY
Grok Build X search Install grok and sign in
local Page fetch Built in

Each engine can be pointed at a compatible third-party or self-hosted service with its baseURL setting. Multiple configured engines are tried in order, with automatic failover.

Commands

The documented configuration form is modsearch config set <key> <value>, for example modsearch config set tavily.apiKey <key> or modsearch config set tavily.baseURL <url>. The CLI also provides configuration and health-check functions through its config and doctor commands.

How it behaves

The plugin connects the harness’s built-in web_search to the configured engine chain and supplies x_search for X and read_page for focused single-page reading. Results are returned as structured JSON evidence, including sources and citations. A search or fetch can be triggered through conversation when the agent needs current information or a URL read.

Requirements and limits

At least one search-capable engine is needed for web search. Antigravity CLI requires the agy installation and browser sign-in; Grok Build requires a SuperGrok or X Premium account. Tavily, Exa, and Firecrawl use their respective quotas or API-compatible endpoints. local provides page fetching only, so it does not replace a web-search engine.

Written from the project's own documentation and kept in sync with it. Where the two disagree, the source is authoritative — read the README on GitHub

Same category

Alternatives to modsearch

treg

superdesigndev

452

Tool catalog for agents: search ~2,600 external endpoints (SEO and SERP, backlinks, social, people and company enrichment, ad libraries, scraping) by the task you want done, read each one's parameters and per-call price, then call it with the credential injected server-side. Ships the skill plus an MCP row that stays disabled until TREG_TOKEN is set.

Installed cleanly when we ran it

GitHub sourcePythonyesterday

AI review

treg

What it is — The treg plugin provides DeepSeek Harness agents with a tool catalog to search and call approximately 2600 external endpoints by task.

Who it is for — When using a DeepSeek Harness agent to perform data collection tasks requiring external tools without managing multiple vendor accounts, this plugin is suitable. Developers who only use local CLIs or self-built skills can from another angle achieve the needed functionality through direct configuration.

Watch out — Sandbox test passed: installed in a fresh profile and registered into the profile by Harness. No obvious pits found. Source installation requires manually allowing the build script.

The verdict — I would install it because it enables a DeepSeek Harness agent to access external tools with one token and server-side credential injection.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Details
252

Chrome sidebar extension that lets DSH operate your browser directly, no vision capabilities required.

Installed cleanly when we ran it

GitHub sourceTypeScriptyesterday

AI review

dsh-browser

What it is — A Chrome sidebar extension that lets DSH operate your browser directly without vision capabilities.

Who it is for — When you want the model to operate in your actual browser to fill forms or navigate while preserving login state, you can use this plugin. It registers the DSH bundle in the web profile. If you only run DSH in terminal without browser control needs, you can skip this plugin.

Watch out — Installation requires manual approval of the build script from source. Sandbox testing passed, it registers in a fresh profile.

The verdict — I would install it because it enables model operation in a real browser session with preserved state.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Details

notes

zhaoolee

144

Export DSH conversations as Smartisan Notes-style PNGs, or create and update Markdown notes in a configured account-scoped workspace.

Installed cleanly when we ran it

GitHub sourceTypeScriptyesterday

AI review

notes

What it is — Export DSH conversations to Smartisan Notes-style PNGs or create and update Markdown notes in an account-scoped workspace.

Who it is for — Users who want to organize conversation records with DeepSeek Harness and export them as notes for sharing are suitable for installing this plugin. If you mainly handle static documents rather than conversation records, you can skip installing this plugin.

Watch out — Successfully registered in the profile after installation. No obvious issues found.

The verdict — I would install it because it allows direct export of conversations into notes with a simple trigger in the DSH dialogue.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Details

argo

taxueseek

98

Search built for agents: multilingual coverage across web, academic, code, shopping, finance, news, and encyclopedias.

Installs, but not as a profile layer

npm packagePython5d ago

AI review

argo

What it is — Argo is a multilingual search infrastructure for AI agents, delivering structured evidence candidates with credibility decomposition.

Who it is for — If you are developing AI agents using DeepSeek Harness to query topics like finance, sports, or movies requiring structured evidence support, it fits. If you seek only human-readable search summaries or link lists, you do not need it.

Watch out — Successfully installed via command, but treated as ordinary dependency without dsh.bundle so no profile layer added. No obvious issues found in sandbox testing.

The verdict — I would install it because it offers structured evidence for agents to reduce context bloat and costs, but as an ordinary dependency it will not add a profile layer and must be used as per its documentation.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Details
70

Undo/redo & rollback system for DSH: every config change is auto-snapshotted; undo/redo/restore to any version from the WebUI or the offline CLI/GUI tools (works even when DSH fails to boot).

Installed cleanly when we ran it

GitHub sourceJavaScriptyesterday

AI review

dsh-undo-plugin

What it is — Provide snapshot and rollback functionality for DeepSeek Harness configuration and plugin code, with one-click reversion to any version via WebUI, CLI or offline GUI.

Who it is for — When frequently adjusting profile settings or plugin code in the DeepSeek Harness WebUI, this is suitable. It is not appropriate for users running simple local scripts only, as the plugin targets DeepSeek Harness configuration management.

Watch out — Tested successfully after installation into a fresh profile with harness registration. Static check indicates shell command execution. No obvious issues found.

The verdict — I would install it, as it handles offline recovery when DeepSeek Harness fails to boot, without requiring additional dependencies.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Details

ru-marketplace-mcp

Vladimir-Human

64

Skills and optional MCP rows for ten Russian marketplaces: price comparison across Wildberries, Detsky Mir and Yandex Market, plus per-source search, product cards and reviews. The 13 skills load on install; both MCP rows stay disabled until RU_MARKETPLACE_MCP_DIR points at a local clone, which needs Python 3.12+ and uv.

No one-line install — this plugin lives inside a larger repository and publishes no npm package.

GitHub sourcePythonyesterday

AI review

ru-marketplace-mcp

What it is — ru-marketplace-mcp integrates Russian marketplace plugins for DeepSeek Harness.

Who it is for — If you need Russian marketplace product information in DeepSeek Harness, install this plugin. If you prefer plugins that work completely offline, you don't need to install this one.

Watch out — It requires Python 3.12+ and uv. Some features require your logged-in Chrome. No obvious pitfalls found.

The verdict — If I were you, I would install it because the sandbox has not been tested.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Details