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 SERPHouse/agent-skills --skill apigit clone --depth 1 https://github.com/SERPHouse/agent-skillsWrote 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/serphouse/agent-skills/api)<a href="https://agentmods.dev/skills/serphouse/agent-skills/api"><img src="https://agentmods.dev/badge/skills/serphouse/agent-skills/api/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/serphouse/agent-skills/api"><img src="https://agentmods.dev/badge/skills/serphouse/agent-skills/api.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00028 | $0.02355 |
| Opus 5.5 | $0.00011 | $0.00942 |
| Sonnet 5.5 | $0.00006 | $0.00471 |
| Haiku 4.5 | $0.00003 | $0.00235 |
Grade A, and why
serphouse-api scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
description: Teach AI agents to call SERPHouse REST APIs with curl for web search, SERP data, and SEO intelligence How it starts
The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SERPHouse API Skill
This skill equips the agent to search the web and scrape SERP data via the SERPHouse API. The agent can search Google, Bing, Yahoo — web, news, images, shopping, jobs, forums, local, video, and more.
How to Use
- On first invocation, the user must provide a
SERPHOUSE_API_KEY. The agent will store and reuse it for subsequent searches. - The agent uses
curlto call SERPHouse endpoints unless the codebase provides a dedicated client. - Always prefer
curlexamples when showing the user how to use an endpoint — include the full command withapi_token=<KEY>orAuthorization: Bearer <KEY>.
Authentication
Pass your API key in one of two ways:
- Header:
Authorization: Bearer <KEY> - Query param:
api_token=<KEY>
Base URL: https://api.serphouse.com
curl Examples for Every Endpoint
1. SERP API (General)
Live GET search (realtime):
curl "https://api.serphouse.com/serp/live?q=best+coding+courses&serp_type=web&api_token=$SERPHOUSE_API_KEY"
Live POST search:
curl -X POST https://api.serphouse.com/serp/live \
-H "Authorization: Bearer $SERPHOUSE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"q":"best coding courses","domain":"google.com","lang":"en","device":"desktop","serp_type":"web"}'
Schedule batch tasks (up to 100):
curl -X POST https://api.serphouse.com/serp/schedule \
-H "Authorization: Bearer $SERPHOUSE_API_KEY" \
-H "Content-Type: application/json" \
-d '[{"q":"python tutorial","domain":"google.com","lang":"en","device":"desktop","serp_type":"web"}]'
Google Advanced (top 100 results):
curl -X POST https://api.serphouse.com/serp/google_advanced \
-H "Authorization: Bearer $SERPHOUSE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"q":"machine learning","domain":"google.com","lang":"en","device":"desktop","max_pages":5}'
Check task status:
curl "https://api.serphouse.com/serp/check?id=TASK_ID&api_token=$SERPHOUSE_API_KEY"
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 · 260 lines · 28 tokens per session scan A 7beca3833388
serphouse-api is a skill published in the GitHub repository SERPHouse/agent-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 2,355 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
managing-mcp-servers
Use when the user asks to add, change, remove, enable or disable an MCP server, or when an MCP tool is missing, needs sign-in, fails, or was blocked. ThinkRail runs pi in-process, so there is no pi command to call.
todos
Use when the user asks for a shared plan, a task needs at least three substantive execution steps, or a loose TODO is pending. Without an explicit plan request, not for one-shot answers or checks, or one- to two-step work that is not already in the list.
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
writing-specs
Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.
setting-up-a-project
Use when asked to set up, onboard, initialize, or spec a project with no spec graph, or when invoked by the app's Set-up-project card. Not for ordinary work in an already-specced project.
ai-ml-development
AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.