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 agentmods add instructions/huangyrcn/web-kit/claude-mdgit 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/instructions/huangyrcn/web-kit/claude-md)<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>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 | $0.01085 | $0.01085 |
| Opus 5 | $0.00543 | $0.00543 |
| Sonnet 5 | $0.00217 | $0.00217 |
| Haiku 4.5 | $0.00109 | $0.00109 |
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) | 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
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.
- 4d ago First seen · 91 lines · 1,085 tokens per session scan A dbaae26e7eb7
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.
Other instructions, from other repositories
Browser4 CLAUDE.md
Claude Code instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
fix-quera AGENTS.md
Instructions for AlirezaKeshavarz83/fix-quera, covering agent guidance, project shape, visual style, quera page data findings and compatibility findings.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
sendblue-browser-use AGENTS.md
Instructions for sendblue-api/sendblue-browser-use, covering agents.md — sendblue-browser-use, what this repo is, setup, common commands and health (no auth).
sniff AGENTS.md
AGENTS.md instructions for Aboudjem/sniff, covering agents.md: sniff, what this repo is, how an agent should use sniff, handling the playwright setup gate and finding output schema.
browser_oxide AGENTS.md
AGENTS.md instructions for yfedoseev/browser_oxide, covering browseroxide — conventions for ai coding assistants, build & test, architecture, key conventions and where to read more.