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 thirdwatch-dev/scraping-skills --skill review-reputation-scrapinggit clone --depth 1 https://github.com/thirdwatch-dev/scraping-skillsWrote 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/thirdwatch-dev/scraping-skills/review-reputation-scraping)<a href="https://agentmods.dev/skills/thirdwatch-dev/scraping-skills/review-reputation-scraping"><img src="https://agentmods.dev/badge/skills/thirdwatch-dev/scraping-skills/review-reputation-scraping/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/thirdwatch-dev/scraping-skills/review-reputation-scraping"><img src="https://agentmods.dev/badge/skills/thirdwatch-dev/scraping-skills/review-reputation-scraping.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00095 | $0.00953 |
| Opus 5 | $0.00048 | $0.00477 |
| Sonnet 5 | $0.00019 | $0.00191 |
| Haiku 4.5 | $0.00010 | $0.00095 |
Grade A, and why
review-reputation-scraping scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST "https://api.apify.com/v2/acts/thirdwatch~trustpilot-reviews-scraper/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN" \ How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review & Reputation Scraping
Routing for getting review and ratings data off the web: review text, star ratings, TrustScore, pros/cons, verification status, and company replies. Useful for brand monitoring, voice-of-customer (VOC) analysis, competitive intelligence, and review mining for product/marketing research.
The reality on review sites
Review platforms are some of the most anti-bot-heavy targets on the web — the data is valuable and they protect it. G2, Capterra, and Yelp sit behind DataDome and Cloudflare and usually need a stealth browser to scrape reliably; plain HTTP gets you a challenge page. Trustpilot is gentler (server-rendered with embedded JSON), and Google Maps exposes an internal endpoint. The fields that matter for almost any analysis are the same across sites: review text, star rating, date, reviewer, verification status, and the company's reply. Aggregate signals (overall rating, review count, TrustScore) come for free on most listing pages.
Maintaining your own scraper here means re-solving the anti-bot challenge every time the vendor rotates it. Use a maintained scraper unless you have a reason not to.
Ready-made scrapers
| Target | Scraper | From | Notes |
|---|---|---|---|
| Trustpilot | Trustpilot Reviews Scraper | $0.005/result | full review text, TrustScore, company replies, 25+ fields |
| G2 | G2 Software Reviews Scraper | $0.008/result | software ratings, pros/cons, pricing |
| Capterra | Capterra Scraper | $0.008/result | software reviews, 800+ categories |
| Yelp | Yelp Business Scraper | $0.008/result | business reviews, hours, contact, coords |
| Google Maps | Google Maps Scraper | $0.002/result | business ratings + details by query/location |
| Shopify Reviews | Shopify Reviews Scraper | $0.002/result | total review count + avg rating across Judge.me/Yotpo/Loox/etc. |
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.
- 11d ago First seen · 56 lines · 95 tokens per session scan A 252c90757a61
review-reputation-scraping is a skill published in the GitHub repository thirdwatch-dev/scraping-skills (3 stars, last pushed 2mo ago), licensed MIT. It adds 95 tokens to every session and 953 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
ecommerce-full-pipeline
An e-commerce workflow assistant covering product discovery, 1688 product collection, listing on multiple platforms, promotional copy, and short-video creation. 1688 is a Chinese online wholesale marketplace.
pdf-table-extractor-brief
Produces a structured extraction plan and clean spreadsheet template for pulling tabular data out of a PDF document — identifying the table structure, defining column headers, flagging extraction pitfalls, and providing a ready-to-use template that ensures the data lands in a consistent, analysable format.
scraper-brief
Writes a clear, technical brief describing exactly what data needs to be collected from a website or set of web pages, how it should be structured, and what edge cases and legal/ethical considerations apply — for handoff to a developer or data team.
tinyfish-integration
Integrate TinyFish web toolkit (search, fetch, browser automation) into Hermes Agent.
mk:playwright-cli
Session-persistent browser automation via Playwright CLI — form filling, screenshots, data extraction, multi-step flows. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information across multiple requests. NOT for AI-driven…
cloud-browser-automation
Use cloud browser services (Browserbase) for Cloudflare bypass, JavaScript rendering, and stealth scraping when local tools fail.