A tool for rendering a local website and capturing full-page screenshots on desktop and mobile.

Use it to build and serve the project's landing page or audit report, then save screenshots for visual checking.

It lets developers inspect the built result visually, including layouts that change as the page scrolls.

How zernie/vigiles configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to zernie/vigiles. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/zernie/vigiles/main/.claude/skills/screenshot/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/zernie/vigiles

Made for: Claude Code.

Or install vigiles, the plugin that ships this one along with the rest of its 26 skills, 4 hooks, 2 plugins.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/zernie/vigiles/screenshot/github.svg)](https://agentmods.dev/skills/zernie/vigiles/screenshot)

Your own site

<a href="https://agentmods.dev/skills/zernie/vigiles/screenshot"><img src="https://agentmods.dev/badge/skills/zernie/vigiles/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/zernie/vigiles/screenshot"><img src="https://agentmods.dev/badge/skills/zernie/vigiles/screenshot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 828 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00083	$0.00828
Opus 5	$0.00042	$0.00414
Sonnet 5	$0.00017	$0.00166
Haiku 4.5	$0.00008	$0.00083

Measured 9d ago against content hash f0b45e604c8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

screenshot 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/shot.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

sleep 1 && curl -s -o /dev/null -w "%{http_code}\n" http://localhost:8899/ # expect 200

.claude/skills/screenshot/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

screenshot — render a local page and capture it

Contributor dev skill. Drives the container's pre-installed Chromium (no playwright install, no browser download) via playwright-core to full-page-screenshot a locally-served page. Built from the hard-won gotchas of doing this by hand (see below).

When to use

"screenshot the landing page / site", "how does the report look", "render site/ and show me".
Verifying a UI change in site/ (the landing) or report/ (the audit report) before committing.

Procedure

Build the target (if it's a Vite app, you need dist/):
- Landing: cd site && npm install && npm run build → site/dist/
- Report: it builds with the root npm run build → dist/audit-report.template.html

Serve it on a port (relative asset refs need the dir as web root):

cd site/dist && python3 -m http.server 8899 >/tmp/httpd.log 2>&1 &
sleep 1 && curl -s -o /dev/null -w "%{http_code}\n" http://localhost:8899/   # expect 200

Ensure the driver (no browser download — uses PLAYWRIGHT_BROWSERS_PATH):

node -e "require.resolve('playwright-core')" 2>/dev/null || npm install --no-save playwright-core

Shoot with the bundled script → writes <outDir>/<name>-desktop.png + -mobile.png:
```
node .claude/skills/screenshot/scripts/shot.mjs http://localhost:8899/ "$SCRATCHPAD" landing
```
Override viewports with SHOT_WIDTHS="1440x900,768x1024,390x844".
Look before sending: Read the desktop PNG to sanity-check it rendered, THEN SendUserFile (display: render) so the user sees it. Send to the scratchpad dir, not the repo.

Gotchas this skill encodes (don't relearn them)

Scroll-reveal = blank cards. Sections that fade in on scroll (opacity-0 + IntersectionObserver) are captured INVISIBLE by a naive fullPage screenshot — the hero renders, everything below the fold is blank. The script scrolls top→bottom to trigger the reveals, then returns to top before shooting. If cards are blank, this is why.
Chromium is pre-installed at /opt/pw-browsers/chromium-*/chrome-linux/chrome; pass it as executablePath + --no-sandbox. NEVER run playwright install (blocked; wastes time).
CJS-from-ESM import: playwright-core's entry is CJS, and a script run from the scratchpad can't resolve the repo's node_modules by a bare import — use createRequire(cwd + '/package.json') (the script does this).
Mobile uploads sometimes 400 on SendUserFile — retry once, or send desktop alone.

Read the full file on GitHub · 55 lines

Files

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.

scripts/shot.mjs 2.6 KB runs code

Changes

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.

9d ago First seen · 55 lines · 83 tokens per session scan A f0b45e604c8a

Subscribe to this mod's changes

screenshot is a skill published in the GitHub repository zernie/vigiles (15 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 828 once invoked, about $0.0004 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 2026-08-30.

Browser automation Claude Code agentic-coding ai-agents anthropic claude cli

web-scraper

Scrape, crawl, and extract data from websites. Use when users ask to scrape web pages, extract content, crawl websites, or collect data from the internet.

shobcoder/shob · 38 tokens

browser-doctor

Read-only health check on browser-control setup. Verifies browser binary, Playwright MCP Bridge extension presence, token file mode/contents, AIWG MCP registration, provider config injection, and optional workspace allow-list. Outputs pass/fail per check with remediation commands.

jmagly/aiwg · 56 tokens

web-access

A method for handling difficult web tasks across search, page fetching, and a real browser. It covers sites that need login sessions, dynamic pages, anti-bot handling, or exploration before their structure is understood.

open-octo/octo-agent · 139 tokens

browser-reset

Reconfigure the browser-control wiring. Rotate the Playwright MCP Bridge token, switch the target browser, or fully tear down the AIWG registration and provider injection. Walks the user through extension UI regeneration where needed; respects human-authorization gates for destructive operations.

jmagly/aiwg · 55 tokens

browser-setup

Interactive wizard that wires up @playwright/mcp end-to-end — detects the user's browsers, walks through Playwright MCP Bridge extension install, captures the per-install token, registers the MCP server in the AIWG registry with --extension and the env block, injects into the active provider's config, and verifies the…

jmagly/aiwg · 69 tokens

c-browser

Headless browser automation — navigate pages, click elements, fill forms, take screenshots, scrape content using agent-browser or playwright-cli.

daxaur/openpaw · 29 tokens

vigiles: Skill for Claude Code