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 microlinkhq/mcp --skill capture-web-screenshotgit clone --depth 1 https://github.com/microlinkhq/mcpWrote 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/microlinkhq/mcp/capture-web-screenshot)<a href="https://agentmods.dev/skills/microlinkhq/mcp/capture-web-screenshot"><img src="https://agentmods.dev/badge/skills/microlinkhq/mcp/capture-web-screenshot/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/microlinkhq/mcp/capture-web-screenshot"><img src="https://agentmods.dev/badge/skills/microlinkhq/mcp/capture-web-screenshot.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 | $0.00104 | $0.01234 |
| Opus 5.5 | $0.00042 | $0.00494 |
| Sonnet 5.5 | $0.00021 | $0.00247 |
| Haiku 4.5 | $0.00010 | $0.00123 |
Grade A, and why
capture-web-screenshot 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 2mo 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.
Capture web screenshots & PDFs
Turn any public URL into an image or PDF hosted on a permanent CDN URL. Use the
microlink_screenshot and microlink_pdf MCP tools.
Pick the tool
| Goal | Tool | Result field |
|---|---|---|
| Image of a page (PNG/JPEG) | microlink_screenshot |
microlink.data.screenshot.url |
| Printable/paginated document | microlink_pdf |
microlink.data.pdf.url |
| Image plus metadata/palette in one call | microlink_extract with screenshot: true |
microlink.data.screenshot.url |
The response is structuredContent. Read the asset URL from
microlink.data.<feature>.url, and check microlink.status === "success" first.
Screenshot recipes
Give each request a url plus a screenshot value. Pass screenshot: true for
defaults, or an object to configure it. screenshot: {} behaves like true.
- Full page (entire scroll height):
{ "url": "...", "screenshot": { "fullPage": true } } - Single element (crop to a selector):
{ "screenshot": { "element": "#hero" } } - JPEG for smaller files:
{ "screenshot": { "type": "jpeg" } }(default ispng) - Transparent background:
{ "screenshot": { "omitBackground": true } } - Marketing / OG image — wrap the page in browser chrome on a gradient:
{ "screenshot": { "overlay": { "browser": "dark", "background": "linear-gradient(45deg, #757abf, #8583be)" } } } - Code snippet page — syntax theme:
{ "screenshot": { "codeScheme": "dracula" } }
Control the browser before capturing
These parameters work on both screenshot and PDF:
device: emulate a device, e.g."iPhone 12","Pixel 5","Macbook Pro 16".viewport: custom size, e.g.{ "width": 1200, "height": 630 }(ideal OG ratio).colorScheme:"dark"or"light"to trigger the page's theme.click: CSS selector(s) to click first (dismiss a cookie banner, open a tab).scroll: CSS selector to scroll into view before shooting.styles/scripts: inject CSS/JS to hide clutter (e.g. hide a sticky nav).waitForSelector: wait until an element exists (good for lazy content).waitForTimeout: wait N ms extra for animations to settle.adblock: true: strip ads before capture.
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.
- 2mo ago First seen · 92 lines · 104 tokens per session scan A 62a92189bd6a
capture-web-screenshot is a skill published in the GitHub repository microlinkhq/mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 104 tokens to every session and 1,234 once invoked, about $0.0004 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 2026-08-31.
capture-web-screenshot compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| capture-web-screenshotmicrolinkhq/mcp | Skill | 0 | 4mo ago | MIT | A | 104 | Claude Code, Codex |
| chrome-devtools-cliChromeDevTools/chrome-devtools-mcp | Skill | 55k | today | Apache-2.0 | A | 31 | Claude Code |
| x-readerrunesleo/x-reader | Skill | 988 | 4d ago | MIT | A | 64 | Claude Code |
| jmcomichect0x7/jmcomic-ai | Skill | 125 | 3d ago | MIT | A | 124 | Claude Code, Codex |
| x-twitter-scraperXquik-dev/x-twitter-scraper | Skill | 227 | today | MIT | A | 162 | Claude Code |
| apitapn1byn1kt/apitap | Skill | 131 | 17d ago | Apache-2.0 | A | 0 | Claude Code, Codex |
| x-use-inboxihuzaifashoukat/x-use | Skill | 181 | 4d ago | MIT | A | 64 | Claude Code |