A Python-based tool for turning a web page into readable text or Markdown. It can preserve links, images, tables, and page structure when extracting content from a URL.

Use it to fetch article, blog, documentation, or other web-page text for search, summarization, analysis, or further processing.

Web pages often contain menus, ads, and layout code that are difficult for programs to read. This removes that surrounding material so an agent can work with the main content.

web-extract — Skill by fuyuxiang

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 skills/fuyuxiang/echo-agent/web-extract

Any agent

npx skills add fuyuxiang/echo-agent --skill web-extract

Clone the repo

git clone --depth 1 https://github.com/fuyuxiang/echo-agent

Made for: Claude Code, Codex.

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 503 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5	$0.00026	$0.00503
Opus 5	$0.00013	$0.00251
Sonnet 5	$0.00005	$0.00101
Haiku 4.5	$0.00003	$0.00050

Measured 3d ago against content hash 917007a4d32d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

web-extract 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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/extract_url.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/research/web-extract/SKILL.md · 83 lines

What it actually says

Web Extract

Extract readable text/markdown from any URL. Uses trafilatura — the best Python content extraction library (handles news, blogs, docs reliably).

Quick Usage

pip install trafilatura httpx

import trafilatura

# Fetch and extract in one step
text = trafilatura.fetch_and_extract("https://example.com/article")
print(text)

# With more options
downloaded = trafilatura.fetch_url("https://example.com/article")
result = trafilatura.extract(downloaded, output_format="markdown", include_links=True)

Helper script

python3 scripts/extract_url.py "https://example.com/article"
python3 scripts/extract_url.py "https://example.com" --format markdown --links

Options

Parameter	Effect
`output_format="markdown"`	Markdown with headers
`include_links=True`	Preserve hyperlinks
`include_images=True`	Include image references
`include_tables=True`	Preserve table structure
`favor_recall=True`	Extract more (less precision)

Fallback: httpx + readability

For pages where trafilatura struggles:

import httpx
from readability import Document

resp = httpx.get(url, follow_redirects=True, timeout=15)
doc = Document(resp.text)
title = doc.title()
content = doc.summary()  # HTML, needs html2text for markdown

JavaScript-heavy sites

For SPAs or JS-rendered content, use playwright (optional):

from playwright.sync_api import sync_playwright

with sync_playwright() as p:
    browser = p.chromium.launch()
    page = browser.new_page()
    page.goto(url, wait_until="networkidle")
    html = page.content()
    browser.close()
# Then pass html to trafilatura.extract()

Rate Limits

Be respectful: add 1-2 second delays between requests to the same domain. Set a User-Agent: trafilatura.fetch_url(url, config=config) with custom config.

Files

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.

scripts/extract_url.py 1.1 KB runs code

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.

3d ago First seen · 83 lines · 26 tokens per session scan A 917007a4d32d

Subscribe to this mod's changes

web-extract is a skill published in the GitHub repository fuyuxiang/echo-agent (988 stars, last pushed 3d ago), licensed MIT. It adds 26 tokens to every session and 503 once invoked, about $0.0001 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 2026-08-30.

Research agent agent-memory

web-extract

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Web Extract

Quick Usage

Helper script

Options

Fallback: httpx + readability

JavaScript-heavy sites

Rate Limits

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

pptx

ai-style

curly-quote-sft

writing

kungfu-agent-onboarding

research