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 mostafa-drz/claude-skills --skill capture-screensgit clone --depth 1 https://github.com/mostafa-drz/claude-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/mostafa-drz/claude-skills/capture-screens)<a href="https://agentmods.dev/skills/mostafa-drz/claude-skills/capture-screens"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/capture-screens/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/mostafa-drz/claude-skills/capture-screens"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/capture-screens.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 | $0.00101 | $0.02748 |
| Opus 5 | $0.00051 | $0.01374 |
| Sonnet 5 | $0.00020 | $0.00550 |
| Haiku 4.5 | $0.00010 | $0.00275 |
Grade A, and why
capture-screens 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 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.
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 — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preferences
On startup, use Read to load ~/.claude/skills/capture-screens/preferences.md. If missing, use defaults below.
Defaults:
url:http://localhost:3000output:screenshotsviewport:1440x900highlight: truehighlight-color:#FF4B4Bwait-ms:800
Context
On startup, use Bash to detect the current working directory. Use this for default output path resolution.
Command routing
Check $ARGUMENTS:
help→ show help, stopconfig→ run config flow, stopreset→ delete preferences file, confirm, stop- anything else → run the skill
Help
capture-screens — Automated contextual screenshot capture via Playwright
Usage:
/capture-screens [context] Interactive — prompts for missing inputs
/capture-screens [context] --url <url> App URL to capture
/capture-screens [context] --features <f1,f2,...> Comma-separated routes or feature names
/capture-screens [context] --output <dir> Output directory (default: screenshots/)
/capture-screens [context] --no-highlight Skip CSS highlight injection
/capture-screens [context] --viewport <WxH> Viewport size (default: 1440x900)
/capture-screens [context] --auth <instructions> How to authenticate, e.g. "login as [email protected] / pass123"
/capture-screens [context] --inject-js <file> Path to a JS file to evaluate before capturing (e.g. to seed state)
/capture-screens config Set persistent preferences
/capture-screens reset Clear preferences
/capture-screens help This help
Context argument:
Free-text description of what you're capturing. Used to generate semantic
filenames and manifest descriptions. Example:
"Checkout flow — cart summary, shipping form, payment step, confirmation"
Examples:
/capture-screens "Settings page — profile tab, notifications, billing"
/capture-screens "Onboarding flow" --url https://staging.myapp.com --auth "skip login, go to /onboarding"
/capture-screens "Admin dashboard" --url http://localhost:3000 --no-highlight --output docs/screenshots
/capture-screens "Product tour" --inject-js seed-demo-state.js
Output:
{output}/ ← semantically-named PNGs
{output}/manifest.json ← filename → description map (for downstream skills)
{output}/capture-report.md ← human-readable summary with descriptions
Current preferences:
(shown from preferences.md)
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 · 284 lines · 101 tokens per session scan A 5cbf73c57c0d
capture-screens is a skill published in the GitHub repository mostafa-drz/claude-skills (4 stars, last pushed today), licensed MIT. It adds 101 tokens to every session and 2,748 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
shipkit-qa-visual
Visual QA using Playwright as a browser automation library. --setup installs Playwright and creates ui-goals.json; default mode writes inline scripts to navigate, screenshot, and report against goals.
playwright-pro
Production-grade Playwright testing skill for E2E suites, flaky test diagnosis, browser automation, migration from Cypress/Selenium, CI integration, visual checks, and regression validation.
browser-qa-delivery
Validate a Design Studio HTML artifact in the sandbox browser, fix rendering and runtime defects, then deliver exactly the tested file.
ag-testar-e2e
QA Playwright automatizado: navega como usuario, captura console/rede/UI quebrada e gera relatorio para fluxos criticos e regressao.
ag-testar-e2e-batch
Suite E2E completa com pre-flight de infra, batches de 10-20 testes, auto-fix de falhas (seletores/mocks/timing), retry ate 3 ciclos, progresso em /tmp/e2e-progress.md.
ag-referencia-playwright
Patterns canonicos Playwright 2026 — Chromium isolado, web-first assertions, locators semanticos, persistent context. Carregar antes de QAT/E2E/browser test.