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 Elumenotion/GuideAnts --skill searxng-searchgit clone --depth 1 https://github.com/Elumenotion/GuideAntsWrote 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/elumenotion/guideants/searxng-search)<a href="https://agentmods.dev/skills/elumenotion/guideants/searxng-search"><img src="https://agentmods.dev/badge/skills/elumenotion/guideants/searxng-search/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/elumenotion/guideants/searxng-search"><img src="https://agentmods.dev/badge/skills/elumenotion/guideants/searxng-search.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 | $0.00079 | $0.01427 |
| Opus 5 | $0.00039 | $0.00714 |
| Sonnet 5 | $0.00016 | $0.00285 |
| Haiku 4.5 | $0.00008 | $0.00143 |
Grade A, and why
searxng-search 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 8d 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.
tools are wired to. Stdlib Python only (urllib): no pip installs, no API keys. This is a copy
92% identical to searxng-search — 236 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
searxng-search
Paths - fixed layout, do not probe or re-derive. The sandbox CWD is the
notebook's output directory. This skill's scripts live under
Skills/searxng-search/scripts/ relative to it, so run the commands in this
file exactly as written. Write every deliverable to the CWD with a bare
filename: never prefix an output path with Output/ - the CWD is the
output directory, so Output/... would create a nested Output/ folder.
Searches web text and images through the GuideAnts stack's own self-hosted SearXNG - the same instance the product's web-search / ReadWeb tools are wired to. Stdlib Python only (urllib): no pip installs, no API keys.
How the instance is wired (verified against this repo)
| Where | What |
|---|---|
docker/docker-compose.cuda.yml |
service searxng (container readweb-searxng), image guideants-searxng:latest, port 127.0.0.1:8091:8080 |
docker/build/searxng/Dockerfile |
custom image: SearXNG + Chromium + /browser/ render sidecar behind nginx :8080 |
docker/volumes/searxng/config/settings.yml |
formats: [json], limiter: false - the JSON API is open to local clients |
| sandbox reachability | http://host.docker.internal:8091 (the host-published port) |
--base-url or the SEARXNG_URL environment variable overrides the default,
so the skill also works against any other SearXNG instance (public or
self-hosted).
Dependencies
Python 3 standard library only. The only prerequisite is that the stack is up
and readweb-searxng is running.
What to run
Probe first (cheap; confirms the instance answers with JSON):
python3 Skills/searxng-search/scripts/searxng_tool.py probe
Web search:
python3 Skills/searxng-search/scripts/searxng_tool.py search "duck" --limit 10
python3 Skills/searxng-search/scripts/searxng_tool.py search "python async" --engines bing,duckduckgo --time-range week
python3 Skills/searxng-search/scripts/searxng_tool.py search "fastapi" --json # raw JSON for parsing
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.
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.
- 8d ago Changed · -97 lines · +29 tokens per session 4e45df200cae
- 12d ago First seen · 213 lines · 50 tokens per session scan A 3eecf1185abf
searxng-search is a skill published in the GitHub repository Elumenotion/GuideAnts (57 stars, last pushed 2d ago), licensed Apache-2.0. It adds 79 tokens to every session and 1,427 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 92% identical to searxng-search, differing in 236 lines, and is treated as a copy.
Other skills, from other repositories
stealth-browser-mcp
Use this skill when operating stealth-browser-mcp from an AI agent or MCP client for browser automation, page inspection, element interaction, screenshots, file uploads, CDP commands, network debugging, cookies/storage, stealth setup, or reliable multi-step browser workflows. It provides the correct tool order, state…
gemini-deep-research
Run Gemini Deep Research via browser automation. Persistent Chrome on CDP port 9222. Use when user asks to research a topic with.
agent-reach
A set of tools that lets an AI agent search and read information from websites, social networks, developer platforms, career sites, videos, podcasts, and RSS feeds.
amazon-photos-album-download
Download the original photo and video files from a public Amazon Photos shared album (an amazon.com/amazon.ca /photos/share/ link) via Amazon Drive's own JSON API, no login required. Drives headless Chrome with Playwright, lists the album nodes, and pulls size-verified originals. Use when you need a local copy of…
manage-apps-and-sounds-headless
Control the pushover.net web dashboard headlessly for things the HTTP API cannot do - log in, list applications, CREATE or DELETE Pushover applications (returning the new app's API token), and ADD or REMOVE custom notification sounds (with a sourcing+loudness pipeline for free MP3 jingles). Drives system Google Chrome…
cypress-ops
Cypress end-to-end and component testing operations - selector/retry-ability strategy, cy.intercept network stubbing, cy.session auth, component vs e2e, flake diagnosis, CI, Test Replay. Use for: cypress, e2e test, component test, cy.get, cy.intercept, cy.session, data-cy, data-test, retry-ability, flake, flaky test…