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 agentmods add skills/serphouse/agent-skills/nodejsnpx skills add SERPHouse/agent-skills --skill nodejsgit clone --depth 1 https://github.com/SERPHouse/agent-skillsWhat 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 | $0.00028 | $0.02479 |
| Opus 5 | $0.00014 | $0.01239 |
| Sonnet 5 | $0.00006 | $0.00496 |
| Haiku 4.5 | $0.00003 | $0.00248 |
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.
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
});
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.
- yesterday First seen · 299 lines · 28 tokens per session scan A 23d0cfb8702d
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.
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…
remember
Harmonia remember - capture a single learning into the right memory tier. Use ONLY when explicitly invoked as /harmonia:remember.
recall
Harmonia recall - surface relevant past learnings for the current repo mid-session. Use ONLY when explicitly invoked as /harmonia:recall.
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?".
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.
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…