searxng

searxng is a skill for Claude Code from pyros-projects/limitless. It costs 103 tokens per session (1,700 once invoked), scanned A, original, MIT.

Instructions for using SearXNG, a self-hosted search service that combines results from several search engines without tracking users.

In plain words
What is it for?
Search for current information, choose useful categories such as technology or science, restrict results by date, and retrieve structured search results.
Why use it?
They provide a repeatable way to search the web while narrowing results, handling poor matches, and limiting unnecessary queries.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the limitless plugin — 10 skills shipped together

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/pyros-projects/limitless/searxng
Any agent
npx skills add pyros-projects/limitless --skill searxng
Clone the repo
git clone --depth 1 https://github.com/pyros-projects/limitless

Made for: Claude Code.

Or install limitless, the plugin that ships this one along with the rest of its 10 skills.

Wrote 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.

agentmods badge for searxng

README.md
[![agentmods](https://agentmods.dev/badge/skills/pyros-projects/limitless/searxng.svg)](https://agentmods.dev/skills/pyros-projects/limitless/searxng)
Your own site
<a href="https://agentmods.dev/skills/pyros-projects/limitless/searxng"><img src="https://agentmods.dev/badge/skills/pyros-projects/limitless/searxng.svg" alt="Measured on agentmods" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,700 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 5.1 $0.00103 $0.01700
Opus 5 $0.00051 $0.00850
Sonnet 5 $0.00021 $0.00340
Haiku 4.5 $0.00010 $0.00170

Measured 5d ago against content hash 339cef6be33b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

searxng 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 5d 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.

curl -s "http://localhost:8888/search?q=test&format=json" | head -c 200
plugins/limitless/skills/searxng/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SearXNG is a self-hosted metasearch engine that aggregates results from 70+ search engines (Google, Bing, DuckDuckGo, etc.) without tracking or profiling. It provides a JSON API that works well for agent research loops.

Usage Posture

When using SearXNG for research:

  • Start with a focused query. Narrow beats broad. "rust async runtime comparison 2026" beats "rust async".
  • Fetch 5–10 results per query. More than 10 rarely adds signal. Use jq '.results[:5]' or [:10].
  • Use categories to cut noise. categories=it for tech, categories=news for recency, categories=science for academic sources.
  • Use time_range for freshness. time_range=week or time_range=month when recency matters. Omit it for evergreen topics.
  • Paginate only when the first page is promising but incomplete. Add pageno=2 if you see relevant results but need more.
  • Handle zero or poor results by reformulating. Try synonyms, drop qualifiers, or switch categories before concluding nothing exists.
  • Combine multiple targeted searches over one broad search. Two precise queries ("SearXNG docker setup" + "SearXNG JSON API") beat one vague query ("SearXNG").

Installation

Docker (recommended)

docker run -d \
  --name searxng \
  --restart always \
  -p 8888:8080 \
  searxng/searxng:latest

This runs SearXNG on http://localhost:8888. The --restart always flag ensures it starts on boot.

Docker Compose (alternative)

# docker-compose.yml
services:
  searxng:
    image: searxng/searxng:latest
    container_name: searxng
    ports:
      - "8888:8080"
    restart: always
docker compose up -d

Enable JSON Output

By default, SearXNG may not have JSON format enabled. To enable it:

# Find the settings file inside the container
docker exec searxng cat /etc/searxng/settings.yml | grep -A5 formats

# If json is not listed, override settings:
docker cp searxng:/etc/searxng/settings.yml ./settings.yml
# Edit settings.yml: under 'search:', add 'formats: [html, json, csv, rss]'
docker cp ./settings.yml searxng:/etc/searxng/settings.yml
docker restart searxng

Read the full file on GitHub · 182 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. 5d ago First seen · 182 lines · 103 tokens per session scan A 339cef6be33b

Subscribe to this mod's changes

searxng is a skill published in the GitHub repository pyros-projects/limitless (9 stars, last pushed 23d ago), licensed MIT. It adds 103 tokens to every session and 1,700 once invoked, about $0.0005 per session on Opus 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.

Related

Other skills, from other repositories

x402

Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — "just use it" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing…

browser-use/browser-use · 175 tokens

browser-use

Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.

browser-use/browser-use · 26 tokens

cloud

Documentation reference for using Browser Use Cloud — the hosted API and SDK for browser automation. Use this skill whenever the user needs help with the Cloud REST API (v2, v3, or v4), browser-use-sdk (Python or TypeScript), X-Browser-Use-API-Key authentication, cloud sessions, browser profiles, profile sync, CDP…

browser-use/browser-use · 177 tokens

opencli-browser

Use when an agent needs to drive a real Chrome window via opencli — inspect a page, fill forms, click through logged-in flows, or extract data ad-hoc. Covers the selector-first target contract, compound form fields, stale-ref handling, network capture, and the agent-native envelopes the CLI returns. Not for writing…

jackwener/OpenCLI · 80 tokens

opencli-adapter-author

Use when writing an OpenCLI adapter for a new site or adding a new command to an existing site. Guides end-to-end from first recon through field decoding, adapter coding, and verify. Replaces opencli-oneshot / opencli-explorer. For ad-hoc browser driving (no adapter), see opencli-browser instead; for a top-level…

jackwener/OpenCLI · 88 tokens

opencli-autofix

Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.

jackwener/OpenCLI · 61 tokens