serphouse-nodejs

A guide for using SERPHouse's official Node.js library to retrieve typed search-engine results. Node.js is a JavaScript runtime, and typed results describe the expected structure of the returned data.

In plain words
What is it for?
Write JavaScript or TypeScript code for Google, Bing, or Yahoo results and vertical searches such as jobs, local, videos, shopping, and autocomplete. It also covers raw HTML responses and API errors.
Why use it?
It gives coding agents documented patterns for setup, requests, locations, account checks, response formats, and errors. It is specific to SERPHouse rather than general web scraping.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/serphouse/agent-skills/nodejs
Any agent
npx skills add SERPHouse/agent-skills --skill nodejs
Clone the repo
git clone --depth 1 https://github.com/SERPHouse/agent-skills

Made for: Claude Code, Codex.

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,479 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00028 $0.02479
Opus 5 $0.00014 $0.01239
Sonnet 5 $0.00006 $0.00496
Haiku 4.5 $0.00003 $0.00248

Measured yesterday against content hash 23d0cfb8702d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

serphouse-nodejs 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 yesterday.

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.

skills/nodejs/SKILL.md · 299 lines

How it starts

The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@serphouse/serphouse-nodejs SDK Skill

This skill equips the agent to use the official SERPHouse Node.js SDK (@serphouse/serphouse-nodejs) for live SERP data — Google, Bing, Yahoo search results plus Jobs, Local, Videos, Shopping, Autocomplete, and more.

When to Use

Trigger when the user's project uses (or should use) @serphouse/serphouse-nodejs and needs help with:

Category Example prompts
Setup "Install serphouse-nodejs and set up the client"
Google SERP "Search Google for 'best CRM' from the US on desktop"
Bing/Yahoo SERP "Run a Bing news search for 'AI startups'"
Google Verticals "Find software engineer jobs on Google Jobs in SF" or "Get autocomplete suggestions for 'best saas'"
Location "Find the loc_id for Austin, Texas"
Account "Check my SERPHouse credit balance"
Error handling "Catch and log SERPHouse API errors"
TypeScript "Import the correct types for a Google search"
HTML responses "Get raw HTML instead of JSON"

Do not trigger for general web scraping or non-SERPHouse APIs.

Installation

npm install @serphouse/serphouse-nodejs

Requires Node.js 18+ (uses fetch natively). No runtime dependencies.

Quick Start

import { SERPHouse } from '@serphouse/serphouse-nodejs';

const client = new SERPHouse('YOUR_API_KEY');

// Namespaced style
const { results } = await client.google.search({
  q: 'Fresh Bagels',
  domain: 'google.com',
  lang: 'en',
  device: 'desktop',
  loc: 'New York,United States',
});

// Flat alias style (same result)
const { results } = await client.google_search({
  q: 'Fresh Bagels',
  domain: 'google.com',
  lang: 'en',
  device: 'desktop',
  loc: 'New York,United States',
});

CommonJS is also supported:

const { SERPHouse } = require('@serphouse/serphouse-nodejs');

Client Options

const client = new SERPHouse('API_KEY', {
  baseUrl: 'https://api.serphouse.com', // default
  timeout: 60000, // default, ms
});

Read the full file on GitHub · 299 lines

Changes

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.

  1. yesterday First seen · 299 lines · 28 tokens per session scan A 23d0cfb8702d

Subscribe to this mod's changes

serphouse-nodejs is a skill published in the GitHub repository SERPHouse/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 2,479 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

document

Workflow Phase 10 — orchestrator for documentation work. Surveys the diff, routes any page on a documentation surface through technical-writer, standalone technical reference through the documentation skill, tutorials through technical-tutorials, and all other prose body work (inline docs, README updates, user-facing…

friedbotstudio/baseline · 94 tokens

remember

Harmonia remember - capture a single learning into the right memory tier. Use ONLY when explicitly invoked as /harmonia:remember.

foliveira/harmonia · 29 tokens

recall

Harmonia recall - surface relevant past learnings for the current repo mid-session. Use ONLY when explicitly invoked as /harmonia:recall.

foliveira/harmonia · 33 tokens

explaining-code

Explains code with visual diagrams and analogies. Use when explaining how code works, teaching about a codebase, or when the user asks "how does this work?".

spacecake-labs/spacecake · 38 tokens

teach-impeccable

One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.

rwliebs/Dossier · 33 tokens

alego-doc-standards

Use when writing, moving, reviewing, or auditing documentation in the alego repo — choosing hierarchy and detail, separating tutorials from references, checking tutorial progression, trimming doc slop, responding to a verify-doc-budgets failure, or requests like "improve the docs", "audit the docs", "where should this…

singula-ai/alego · 82 tokens