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 huangyrcn/web-kit --skill searxng-searchgit clone --depth 1 https://github.com/huangyrcn/web-kitWrote 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/huangyrcn/web-kit/searxng-search)<a href="https://agentmods.dev/skills/huangyrcn/web-kit/searxng-search"><img src="https://agentmods.dev/badge/skills/huangyrcn/web-kit/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/huangyrcn/web-kit/searxng-search"><img src="https://agentmods.dev/badge/skills/huangyrcn/web-kit/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 | $0.00147 | $0.01841 |
| Opus 5 | $0.00073 | $0.00920 |
| Sonnet 5 | $0.00029 | $0.00368 |
| Haiku 4.5 | $0.00015 | $0.00184 |
Grade A, and why
searxng-search 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 10d 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.
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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
searxng-search
A web search skill that queries a SearxNG backend. It defaults to Google for
clear, broad web results. Part of a research workflow: find → read → synthesize.
Pair with browser-fetch to read the pages this skill finds.
Input
The primary input is a natural language query. Optional flags adjust scope:
| Flag | Meaning | Example |
|---|---|---|
| query | What to search for (required) | "knowledge graph multi-hop reasoning" |
-n |
Limit number of results | -n 5 |
-e |
Use one specific engine instead of Google | -e google_scholar |
-l |
Language preference | -l zh-CN |
-c |
Category | -c news |
-t |
Request timeout in seconds | -t 60 |
-u |
Output URLs only | -u |
-j |
Output JSON (structured, for scripting) | -j |
How to invoke
The script is bundled with this skill. Always invoke it via the script path
so it works regardless of whether searxng-search is on the user's PATH:
uv run --script ${SKILL_DIR}/scripts/searxng-search "query"
uv run --script ${SKILL_DIR}/scripts/searxng-search "query" -n 5
uv run --script ${SKILL_DIR}/scripts/searxng-search "query" -e google_scholar
uv run --script ${SKILL_DIR}/scripts/searxng-search "query" -c news -l zh-CN
Do not invoke the script directly (e.g. ${SKILL_DIR}/scripts/searxng-search ...) — the
file may not have execute permission after deployment. Always use uv run --script.
The only external dependency is uv (auto-installs inline Python deps on
first run) and a running SearxNG backend.
Environment
SEARXNG_URL — SearxNG endpoint (default: http://localhost:8082)
WEB_KIT_API_KEY — required; sent as the X-API-Key header to authenticate to the gateway.
Default behavior
If you do not specify any flags:
- Engine: Google
- Results: top 10
- Output: concise human-readable list with title, URL, snippet, and engine tag
- Errors: JSON to stdout with an
error_typefield (exit code 1)
Available engines
Engines are grouped by what they index. Choose at most one non-default engine per search. To compare sources, run separate searches.
What ships with it
3 files 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.
- 10d ago First seen · 178 lines · 147 tokens per session scan A 9bd3e07e23c7
searxng-search is a skill published in the GitHub repository huangyrcn/web-kit (5 stars, last pushed 2mo ago), licensed MIT. It adds 147 tokens to every session and 1,841 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…