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/ericwang915/pythonclaw/scrapernpx skills add ericwang915/PythonClaw --skill scrapergit clone --depth 1 https://github.com/ericwang915/PythonClawWhat 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 | $0.00047 | $0.00253 |
| Opus 5 | $0.00023 | $0.00127 |
| Sonnet 5 | $0.00009 | $0.00051 |
| Haiku 4.5 | $0.00005 | $0.00025 |
Grade A, and why
web_scraper 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 2d 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.
What it actually says
Instructions
Scrape and extract readable content from any web page.
Prerequisites
Install dependencies: pip install requests beautifulsoup4
Usage
python {skill_path}/scrape.py URL [--format text|json|links|headings]
Formats:
text(default) — cleaned readable textjson— structured JSON with title, text, links, headingslinks— all links on the pageheadings— all headings (h1–h6)
Examples
- "Read the content of https://example.com"
- "Extract all links from https://news.ycombinator.com"
- "What does this page say? https://some-article.com/post"
Resources
| File | Description |
|---|---|
scrape.py |
Generic web page scraper |
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.
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.
- 2d ago First seen · 41 lines · 47 tokens per session scan A f370259808a5
web_scraper is a skill published in the GitHub repository ericwang915/PythonClaw (41 stars, last pushed 24d ago), licensed MIT. It adds 47 tokens to every session and 253 once invoked, about $0.0002 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.
Other skills, from other repositories
browser-pilot
增强版浏览器自动化。基于 Playwright 实现完整浏览器操作，包括基础导航、截图、点击、表单填写、内容提取、文件上传/下载、多标签页管理。支持反检测和高级自动化。.
web-scraper
增强版网页抓取功能。支持会话管理、多模式提取（CSS/XPath/正则）、并发抓取、反爬虫增强。提供完整的命令行接口。.
cloud-screencast
Record a clean product demo video of a web app on a disposable cloud VM — provision a GCE instance, install Xvfb + Chrome + ffmpeg + real fonts, deploy the app, drive the UI deterministically with Playwright over CDP while x11grab records, then cut the raw take into a social-ready clip with speed ramps and burned-in…
test-runner
Write and run tests across languages and frameworks.
save-as-pdf
Reformat the current HTML design into a paginated, paper-ready PDF. The "Instant" export already gives the user a PDF at the design's native pixel size — this path is for when they want real pages.
talking-head-recut
Package an existing talking-head / interview / podcast video with timed, designed GRAPHIC OVERLAY cards — kinetic titles, lower-thirds, data callouts, quotes, side panels, picture-in-picture — synced to the transcript, on a 16:9 / 9:16 / 4:5 canvas of your choice; the clip plays untouched underneath. Trigger on…