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 skills/bcefghj/webgrab/cursornpx skills add bcefghj/webgrab --skill cursorgit clone --depth 1 https://github.com/bcefghj/webgrabWhat 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 | $0.00000 | $0.00777 |
| Opus 5 | $0.00000 | $0.00388 |
| Sonnet 5 | $0.00000 | $0.00155 |
| Haiku 4.5 | $0.00000 | $0.00078 |
Grade A, and why
cursor 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 yesterday.
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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WebGrab - Web Content Download Skill
Description
Download videos, articles, danmaku, and comments from any website. Bypass copy protection. Supports Bilibili, Douyin, YouTube, and 1700+ sites.
Triggers
- User asks to download a video from a URL
- User asks to download an article or webpage
- User asks to extract danmaku/bullet comments from Bilibili
- User asks to download comments from Bilibili or Douyin
- User asks to bypass copy protection on a webpage
- User mentions "webgrab", "download video", "download article", "danmaku", "弹幕", "评论"
Prerequisites
The WebGrab MCP server must be configured. Add to your MCP config:
{
"mcpServers": {
"webgrab": {
"command": "webgrab-mcp",
"env": {
"BILIBILI_COOKIE": "optional - for higher quality",
"DOUYIN_COOKIE": "optional - for comment access"
}
}
}
}
Or install the CLI directly:
pip install webgrab
Instructions
Video Download
When the user provides a video URL from YouTube, Bilibili, Douyin, or any other site:
- Use the
download_videoMCP tool with the URL - Offer quality options: best, 1080p, 720p, 480p, audio-only
- Report the download result and file location
Bilibili Danmaku (弹幕)
When the user asks for danmaku from a Bilibili video:
- Use the
get_bilibili_danmakuMCP tool - Offer format options: json, csv, xml, ass (subtitle)
- Report the count and sample of danmaku
Bilibili Comments (评论)
When the user asks for comments from a Bilibili video:
- Use the
get_bilibili_commentsMCP tool - Include nested replies (楼中楼) by default
- Offer sort options: time or likes
Douyin Video
When the user provides a Douyin URL:
- Use the
get_douyin_videoMCP tool - This downloads the no-watermark version by default
Douyin Comments
When the user asks for Douyin comments:
- Use the
get_douyin_commentsMCP tool - Specify the limit parameter
Article/Webpage Download
When the user asks to save a webpage:
- Use the
download_articleMCP tool - Default format is Markdown, also supports html and text
- For quick inline extraction, use
extract_webpageinstead
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.
- yesterday First seen · 97 lines · 0 tokens per session scan A 44f7304ca722
cursor is a skill published in the GitHub repository bcefghj/webgrab (4 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 777 tokens. 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…