web-kit CLAUDE.md

web-kit CLAUDE.md is an instructions file for coding agents from huangyrcn/web-kit. It costs 1,085 tokens per session, scanned A, original, MIT.

Repository instructions for web-kit, a project that gives coding agents web search and browser-based page or file fetching.

In plain words
What is it for?
Use them when developing or maintaining web-kit's search and browser-fetch tools, Docker backend, environment settings, and related scripts.
Why use it?
They explain how the project is organised, how its scripts connect to the backend, and how to build or run it.

Instructions file

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 instructions/huangyrcn/web-kit/claude-md
Clone the repo
git clone --depth 1 https://github.com/huangyrcn/web-kit

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 web-kit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/huangyrcn/web-kit/claude-md.svg)](https://agentmods.dev/instructions/huangyrcn/web-kit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/huangyrcn/web-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/huangyrcn/web-kit/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,085 This file is loaded in full into every session.
When invoked 1,085 The same file — it is already loaded in full.
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 $0.01085 $0.01085
Opus 5 $0.00543 $0.00543
Sonnet 5 $0.00217 $0.00217
Haiku 4.5 $0.00109 $0.00109

Measured 4d ago against content hash dbaae26e7eb7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

web-kit CLAUDE.md 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 4d 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.

| `searxng-search` | `scripts/searxng-search` | `uv run --script` | `urllib.request` (stdlib) |
CLAUDE.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

web-kit is a Claude Code skill plugin that gives AI agents two lightweight web primitives: search (searxng-search) and browser fetch (browser-fetch, with page → markdown and file → raw download subcommands). A self-hosted single-container backend (Docker) powers both.

Architecture

The repo has two independent halves connected only by environment variables:

skills/
├── searxng-search/      (SearxNG metasearch CLI)         ─┐
└── browser-fetch/   (Chrome fetcher: page + file)    ─┘
       ↓ SEARXNG_URL, CDP_URL
backend/          (Docker: SearxNG + Chrome + search-proxy)
  • skill scripts run on the agent's host machine, call the backend over HTTP
  • backend runs in Docker: supervisord manages 9 processes (Xvfb, fluxbox, x11vnc, novnc, Chrome, socat CDP forward, search-proxy FastAPI, SearxNG, watchdog)

The search-proxy (backend/server.py) renders Google/DuckDuckGo SERPs via Chrome CDP using patchright (anti-detection Playwright fork). SearxNG proxies to this search-proxy for Google/DDG engines while using direct APIs for everything else.

Script Details

Skill Script Invocation Key dependency
searxng-search scripts/searxng-search uv run --script urllib.request (stdlib)
browser-fetch (page) scripts/page uv run --script crawl4ai (auto-installed by uv)
browser-fetch (file) scripts/file uv run --script websocket-client (auto-installed by uv)

All scripts use PEP 723 inline metadata with #!/usr/bin/env -S uv run --script shebangs. On Unix they can be executed directly; on Windows use uv run --script <path>.

The only external dependency is uv (for running scripts with auto-installed packages) and the backend service (SEARXNG_URL / CDP_URL).

Building & Running

Backend

cd backend
cp searxng-settings/settings.yml.example searxng-settings/settings.yml
docker compose up -d          # first build ~5-10 min
sleep 90                      # warm-up

Read the full file on GitHub · 91 lines

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. 4d ago First seen · 91 lines · 1,085 tokens per session scan A dbaae26e7eb7

Subscribe to this mod's changes

web-kit CLAUDE.md is an instructions file published in the GitHub repository huangyrcn/web-kit (5 stars, last pushed 2mo ago), licensed MIT. It adds 1,085 tokens to every session, about $0.0054 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 instructions, from other repositories