What is web-kit CLAUDE.md?

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

Use them when developing or maintaining web-kit's search and browser-fetch tools, Docker backend, environment settings, and related scripts.

They explain how the project is organised, how its scripts connect to the backend, and how to build or run it.

How huangyrcn/web-kit configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to huangyrcn/web-kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/huangyrcn/web-kit/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/huangyrcn/web-kit

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/huangyrcn/web-kit/claude-md/github.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/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.

Your own site · 80×15

<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="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,069 This file is loaded in full into every session.

When invoked 1,069 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01069	$0.01069
Opus 5.5	$0.00428	$0.00428
Sonnet 5.5	$0.00214	$0.00214
Haiku 4.5	$0.00107	$0.00107

Measured 1mo ago against content hash 5814387c7355, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

web-kit CLAUDE.md 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 1mo 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.

CLAUDE.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code when working in this repository.

What this is

web-kit v2: a self-hosted web access service for agents. One backend container runs a real, logged-in Chrome and exposes one authenticated HTTP API (/v2/*). A stdlib-only CLI (webkit) is the client; the agent skill is generated from it.

src/webkit/             CLI (search / read / download / crawl / status / doctor / engines / config / skill)
backend/                Docker image: Caddy + webkit-api + Chrome + SearXNG + noVNC (supervisord)
backend/app/webkit_api/ FastAPI service (the API)
skills/web-kit/         SKILL.md + reference.md, generated by `webkit skill install --dir skills/web-kit` — do not edit by hand
tests/                  CLI tests (fake server) + live integration tests
backend/tests/          offline backend unit tests

Backend API (port 8082, Caddy-authenticated)

Route	Key	Purpose
`GET /v2/search`	X-API-Key	`profile` (ordered engine fallback) or `engine`; per-engine outcome report
`GET /v2/engines`	X-API-Key	engines, kinds (crawler/api), time-filter support, profiles
`POST /v2/page`	X-API-Key	read one URL (patchright render, crawl4ai conversion); PDFs → extracted text; `pdf` → the PDF the page links
`POST /v2/crawl`	X-API-Key	bounded synchronous deep crawl
`GET /v2/download`	X-API-Key	stream a file through Chrome (cookies apply); a paper page resolves to its PDF (`citation_pdf_url`), other pages are `not_a_file` unless `allow_html`
`GET /v2/status`, `/v2/version`	X-API-Key	browser, egress (TLS probe), engine health, versions
`GET /v2/admin/open`, `/v2/admin/ping`	X-Admin-Key	open a URL for a human via noVNC

Ports 6080 (noVNC, basic auth webkit / admin key) and 9223 (raw CDP, X-Admin-Key) are admin-only. SearXNG (127.0.0.1:8080) and /internal/* are never exposed.

Crawler engines (Chrome-rendered, serp.py): google, duckduckgo, google_scholar, semantic_scholar, arxiv. API engines go through SearXNG (searxng.py).

Read the full file on GitHub · 65 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.

1mo ago Changed · -26 lines · -16 tokens per session 5814387c7355
2mo 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 1mo ago), licensed MIT. It adds 1,069 tokens to every session, about $0.0043 per session on Opus 5.5. 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.

Browser automation

web-kit CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
web-kit CLAUDE.mdhuangyrcn/web-kit	Instructions file	5	1mo ago	MIT	A	1,069	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	280k	2d ago	MIT	A	4,325	Codex, OpenCode

web-kit: Instructions file for Claude Code