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 site-shot/site-shot-mcp --skill website-screenshotsgit clone --depth 1 https://github.com/site-shot/site-shot-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/site-shot/site-shot-mcp/website-screenshots)<a href="https://agentmods.dev/skills/site-shot/site-shot-mcp/website-screenshots"><img src="https://agentmods.dev/badge/skills/site-shot/site-shot-mcp/website-screenshots/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/site-shot/site-shot-mcp/website-screenshots"><img src="https://agentmods.dev/badge/skills/site-shot/site-shot-mcp/website-screenshots.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 | $0.00050 | $0.01786 |
| Opus 5.5 | $0.00020 | $0.00714 |
| Sonnet 5.5 | $0.00010 | $0.00357 |
| Haiku 4.5 | $0.00005 | $0.00179 |
Grade A, and why
website-screenshots 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 6d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Website screenshots with Site-Shot
Site-Shot renders a public URL in a real Chromium browser on Site-Shot's own infrastructure and returns the image. Reach for it when someone needs to see a page: a layout check, a before/after comparison, or how the same URL renders from another country.
The image comes back into this conversation and nowhere else: Site-Shot does not save it as a file or give a link to it. If someone wants to keep a copy, tell them that plainly rather than implying it has been archived.
Before the first capture
The API key needs either the free plan — 100 captures a month on a confirmed account, no card
needed — or a paid plan (from $5/mo for 2,000). Free-plan captures come from the default location or
the US; other countries need a paid plan, and a request for one is refused but still counts toward
the month. Once the free plan's 100 are spent, the API answers 403 until it renews. Captures use
that account's API allowance and limits.
The key reaches the server as SITESHOT_API_KEY, and how it gets there depends on how the server
was installed, not on this skill:
- With the Site-Shot plugin for Claude Code, it is a required plugin setting the person fills in
themselves with
/plugin configure site-shot@site-shot. - Anywhere else (the Codex plugin, a Tessl install, a hand-written MCP config), it is the
SITESHOT_API_KEYvariable in the environment the agent was started from. Codex passes it on only when the server entry lists it asenv_vars = ["SITESHOT_API_KEY"]; anenvtable holding the text${SITESHOT_API_KEY}reaches the server literally. Setup steps: https://github.com/site-shot/site-shot-mcp#codex-cli-plugin
So there is never a reason to ask anyone for the key in conversation, to read it out of a file, or to go hunting for one. If the setup is incomplete — the capture tools are not available, or a call comes back saying the key is missing — stop and say which host-side step is still outstanding, naming the right one for the host you are running in. Do not sign anyone up or buy anything on their behalf.
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.
- 6d ago Changed · +41 lines · -2 tokens per session b08a1d7b1673
- 13d ago Changed · +2 lines 8ba2d5dd3f04
- 15d ago Changed · +2 lines 50c28a56e25b
- 1mo ago First seen · 81 lines · 52 tokens per session scan A 9bc744a1a4f6
website-screenshots is a skill published in the GitHub repository site-shot/site-shot-mcp (3 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 1,786 once invoked, about $0.0002 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 2026-09-20.
website-screenshots compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| website-screenshotssite-shot/site-shot-mcp | Skill | 3 | yesterday | MIT | A | 50 | Cursor |
| x-use-inboxihuzaifashoukat/x-use | Skill | 183 | yesterday | MIT | A | 64 | Claude Code |
| x-useihuzaifashoukat/x-use | Skill | 183 | yesterday | MIT | B | 98 | Claude Code, Codex |
| cliTacosyHorchata/Pilot | Skill | 32 | 4mo ago | MIT | A | 0 | Claude Code, Codex |
| scan-urlkiruxich/legitAgent | Skill | 2 | 2mo ago | MIT | A | 42 | Cursor |
| amazon-bestseller-listingbrowser-act/skills | Skill | 6.4k | 10d ago | MIT | A | 300 | Claude Code, Codex |
| amazon-search-listingbrowser-act/skills | Skill | 6.4k | 10d ago | MIT | A | 341 | Claude Code, Codex |