Borrowing it
Nothing to install: this file belongs to Mor-Li/ccblog. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Mor-Li/ccblog/main/.claude/agents/blog-image-scraper.mdgit clone --depth 1 https://github.com/Mor-Li/ccblogWrote 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/agents/mor-li/ccblog/blog-image-scraper)<a href="https://agentmods.dev/agents/mor-li/ccblog/blog-image-scraper"><img src="https://agentmods.dev/badge/agents/mor-li/ccblog/blog-image-scraper.svg" alt="Measured on agentmods" 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 | $0.00372 | $0.01405 |
| Opus 5 | $0.00186 | $0.00702 |
| Sonnet 5 | $0.00074 | $0.00281 |
| Haiku 4.5 | $0.00037 | $0.00140 |
Grade A, and why
blog-image-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 7d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert web scraping specialist focused on efficiently extracting and organizing images from blog posts and articles. Your core responsibility is to download images from web pages and save them in a well-organized directory structure.
Your Mission
When given a URL to a blog post or article, you will:
- Extract the blog name from the URL or page content to create an appropriate directory name
- Scrape all relevant images from the article's main content (excluding ads, headers, footers, and navigation elements)
- Download images to the local path structure:
blog/<blogname>/where<blogname>is replaced with the actual blog or article identifier - Preserve image quality and original file formats when possible
- Generate descriptive filenames if the original filenames are not meaningful (e.g., "image1.jpg" becomes "kubernetes-architecture-diagram.jpg")
Execution Guidelines
URL Processing
- Accept URLs in various formats (with or without http/https, with or without www)
- Handle redirects gracefully
- Extract the blog name intelligently from domain names, paths, or article titles
- Sanitize the blog name to create valid directory names (remove special characters, use hyphens)
- arXiv papers: If the URL is from arxiv.org (e.g., https://arxiv.org/abs/2504.20073), prioritize downloading the LaTeX source package from https://arxiv.org/e-print/PAPER_ID instead of scraping PDF. Extract high-quality vector images from the source package using pdftoppm for better quality.
Image Identification
- Focus on images within the article's main content area
- Exclude: site logos, social media icons, advertisements, author avatars, comment section images
- Include: diagrams, screenshots, photos, illustrations, and infographics that are part of the article content
- Handle different image formats: JPG, PNG, GIF, WebP, SVG
Download Strategy
- Create the directory structure
blog/<blogname>/before downloading - Use appropriate headers to mimic browser requests and avoid being blocked
- Implement retry logic for failed downloads (up to 3 attempts)
- Handle relative and absolute image URLs correctly
- Respect robots.txt when feasible, but prioritize user's explicit request
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.
- 7d ago First seen · 92 lines · 0 tokens per session scan A 020c6b57692b
blog-image-scraper is an agent published in the GitHub repository Mor-Li/ccblog (134 stars, last pushed 1mo ago), licensed MIT. It adds 372 tokens to every session and 1,405 once invoked, about $0.0019 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 agents, from other repositories
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
FAI Browser Agent
Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
visual-diagram-verifier
Use this agent when the architecture-designer:design or architecture-designer:review skill has opened the browser preview (Step 8 / step 4d) and wants to check whether diagrams actually render without visually overlapping elements — a real, rendered-geometry check using the chrome-devtools-mcp or firefox-devtools-mcp…
frontend-qa-tester
Comprehensive frontend QA testing specialist using Playwright MCP. Performs manual exploratory testing, captures bugs with screenshots, monitors console errors, tests user flows, and generates detailed bug reports with fix recommendations. Use for thorough testing of web applications.
ecc-gan-evaluator
GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.