search1api

A live web research tool for searching the internet, retrieving pages, finding news and sitemaps, and discovering links.

In plain words
What is it for?
Use it to search topics, read or summarize URLs, check news, explore websites, discover sitemaps, and find trending subjects.
Why use it?
It gives a coding agent a way to obtain current information and turn a website into a reusable agent skill.

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/superagents-lab/search1api-cli/search1api
Any agent
npx skills add superagents-lab/search1api-cli --skill search1api
Clone the repo
git clone --depth 1 https://github.com/superagents-lab/search1api-cli

Made for: Claude Code, Codex.

Per session 209 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,037 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00209 $0.04037
Opus 5 $0.00105 $0.02018
Sonnet 5 $0.00042 $0.00807
Haiku 4.5 $0.00021 $0.00404

Measured yesterday against content hash d991691275e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

search1api scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://cli.search1api.com/install.sh | bash

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://cli.search1api.com/install.sh | bash
skills/search1api/SKILL.md · 369 lines

How it starts

The opening of the file, as written. The whole thing — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Search1API

Live web research through the bundled Search1API MCP server or the s1 command-line tool.

Choose the available transport

  1. Prefer the connected Search1API MCP tools. They may be namespaced by the host, but their final tool names are search, fetch, news, crawl, sitemap, and trending.
  2. If the MCP tools are unavailable, check whether s1 is installed and use the matching CLI command.
  3. If neither transport is available, ask the user to connect the bundled MCP server or install the CLI:
curl -fsSL https://cli.search1api.com/install.sh | bash

Or via npm:

npm install -g search1api-cli

Do not install software or switch transports when a working Search1API tool is already available. To update an existing CLI install, the user can run s1 update. Only suggest this when a command fails in a version-related way.

The remote MCP server handles authentication through the host's connection flow. If the host reports that authentication is required, ask the user to connect or re-authenticate Search1API.

For CLI authentication, prefer browser login:

s1 login

Manual fallback:

s1 config set-key <your-api-key>

You can also set the environment variable SEARCH1API_KEY.

If a CLI command fails with "command not found" or an auth error, remind the user to install s1 and run s1 login before retrying.

When to use

User intent MCP tool CLI fallback
Shares a URL / link → read and summarize crawl s1 crawl <url>
Wants to search the web search s1 search "<query>"
Wants the full page behind a search result fetch with its result id s1 crawl <url>
Wants news news s1 news "<query>"
Wants to explore a site's links sitemap s1 sitemap <url>
Wants trending topics trending s1 trending <service>
Wants to check remaining credits Not exposed s1 balance
Wants an agent to keep a URL for later use Not exposed s1 learn <url>

Read the full file on GitHub · 369 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 369 lines · 209 tokens per session scan C d991691275e2

Subscribe to this mod's changes

search1api is a skill published in the GitHub repository superagents-lab/search1api-cli (2 stars, last pushed 7d ago), licensed MIT. It adds 209 tokens to every session and 4,037 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). 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

frontmcp-auth-ui

Use when customizing, branding, or replacing the built-in FrontMCP OAuth pages (the login, consent, federated-select, incremental-authorization, and error pages) with your own React components. Covers the auth.ui slot-to-file map and auth.extras name-to-handler map on the auth config (no decorator, no class); the…

agentfront/frontmcp · 184 tokens

integrated-browser

Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under src/vs/platform/browserView and src/vs/workbench/contrib/browserView.

microsoft/vscode · 68 tokens

agent-host-e2e-tests

Use when writing, recording, updating, or troubleshooting the agent host end-to-end tests under src/vs/platform/agentHost/test/node/e2e (black-box tests that drive the whole agent host over the AHP protocol, using a CapiReplayProxy record/replay system for Claude/Copilot/Codex). Covers adding a cross-provider test…

microsoft/vscode · 104 tokens

schema-exploration

Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.

langchain-ai/deepagents · 57 tokens

lint-js

Lint JS/TS code only. Use before opening a PR when only JavaScript or TypeScript files were changed (no Rust).

denoland/deno · 29 tokens

nemoclaw-contributor-implement-issue

Implement an accepted NemoClaw GitHub issue in the current checkout. Use when a user asks to pick up an issue for implementation, implement or fix a named issue, or add the issue's tests. Confirm accepted scope, deliver the smallest independently valuable capability slice, and record validation and remaining gates…

NVIDIA/NemoClaw · 134 tokens