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 bug-ops/zeph --skill web-scrapegit clone --depth 1 https://github.com/bug-ops/zephWrote 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/bug-ops/zeph/web-scrape)<a href="https://agentmods.dev/skills/bug-ops/zeph/web-scrape"><img src="https://agentmods.dev/badge/skills/bug-ops/zeph/web-scrape/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/bug-ops/zeph/web-scrape"><img src="https://agentmods.dev/badge/skills/bug-ops/zeph/web-scrape.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00082 | $0.02764 |
| Opus 5.5 | $0.00033 | $0.01106 |
| Sonnet 5.5 | $0.00016 | $0.00553 |
| Haiku 4.5 | $0.00008 | $0.00276 |
Grade A, and why
web-scrape 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.
How it starts
The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Page Data Extraction
Extract structured data from web pages by specifying a URL, a CSS selector to target elements, and an extraction mode.
Command Format
{"url": "URL", "select": "CSS_SELECTOR", "extract": "MODE", "limit": N}
Parameters
| Parameter | Required | Description |
|---|---|---|
url |
Yes | Full URL of the page (use HTTPS) |
select |
Yes | CSS selector to target elements |
extract |
No | Extraction mode: text (default), html, or attr:NAME |
limit |
No | Maximum number of elements to return |
Extract Modes
| Mode | Description | Example Output |
|---|---|---|
text |
Inner text content, stripped of HTML tags | Hello World |
html |
Inner HTML markup | <strong>Hello</strong> World |
attr:href |
Value of the specified attribute | https://example.com |
attr:src |
Value of the src attribute |
/images/logo.png |
attr:class |
Value of the class attribute |
btn btn-primary |
attr:id |
Value of the id attribute |
main-content |
attr:data-* |
Value of any data attribute | 42 |
CSS Selector Reference
Basic Selectors
| Selector | Description | Example |
|---|---|---|
element |
All elements of that type | p, div, h1, table |
.class |
Elements with a specific class | .article, .btn-primary |
#id |
Element with a specific ID | #content, #main |
* |
All elements | * |
element.class |
Element with a specific class | div.container, p.intro |
element#id |
Element with a specific ID | div#header |
Attribute Selectors
| Selector | Description | Example |
|---|---|---|
[attr] |
Has the attribute | [href], [data-id] |
[attr=val] |
Attribute equals value exactly | [type="text"], [lang="en"] |
[attr~=val] |
Attribute contains word (space-separated) | [class~="active"] |
[attr|=val] |
Attribute starts with value or value followed by - |
[lang|="en"] |
[attr^=val] |
Attribute starts with value | [href^="https"] |
[attr$=val] |
Attribute ends with value | [href$=".pdf"] |
[attr*=val] |
Attribute contains value anywhere | [href*="example"] |
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 First seen · 292 lines · 82 tokens per session scan A dcdc65e0aae1
web-scrape is a skill published in the GitHub repository bug-ops/zeph (65 stars, last pushed 11d ago), licensed MIT. It adds 82 tokens to every session and 2,764 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
verify
Drive an engine app headlessly in a pty, record a video of the whole verification, and open a summary page (video + timeline + checks) with pixel open.
web-access
Use this skill for live web research, webpage fetching, login-state browsing, dynamic pages, social sites, and tasks that need current internet evidence.
computer-use
Desktop control that picks the right interface per step — app scripting (AppleScript/JXA), accessibility-first observation and actions, pixel fallback, screenshots, zoom, screen recording, and switching between registered computers. Qualified on macOS; Windows, Linux and HarmonyOS backends are experimental.
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
harbor-daytona
Use Harbor's Daytona sandbox platform for computer use — creating sandboxes, taking screenshots, sending mouse/keyboard input, and building agent loops. Use when the user wants to interact with a GUI, automate a desktop, do computer use, control a browser visually, or run Claude computer use against a Daytona sandbox.
web-scraping
Fetches web pages and extracts structured data using mq's toolchain (mq-crawl for fetching/crawling/JS rendering, mq for HTML-to-Markdown selector-based extraction, http() for in-query requests). Use when the user wants to scrape a URL, pull structured data out of a webpage, crawl a site, or turn HTML into…