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 agentmods add skills/mishahanin/heading-os/playwrightnpx skills add mishahanin/heading-os --skill playwrightgit clone --depth 1 https://github.com/mishahanin/heading-osWrote 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/mishahanin/heading-os/playwright)<a href="https://agentmods.dev/skills/mishahanin/heading-os/playwright"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/playwright.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 | $0.00080 | $0.02583 |
| Opus 5 | $0.00040 | $0.01291 |
| Sonnet 5 | $0.00016 | $0.00517 |
| Haiku 4.5 | $0.00008 | $0.00258 |
Grade A, and why
playwright scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playwright Browser Automation
Browser automation and content extraction via Playwright (Python). Handles screenshots, scraping, form filling, PDF generation, YouTube content extraction, and website monitoring.
Prerequisites
Dependencies (already installed in this workspace):
pip install playwright youtube-transcript-api yt-dlp python-dotenv
python -m playwright install chromium
Script Location
.claude/skills/playwright/scripts/pw.py
Run from the workspace root. First anchor the shell: cd "$(git rev-parse --show-toplevel)". A prior skill can leave the shell in a subdirectory, which breaks the root-relative script path below. All commands follow this pattern:
python ".claude/skills/playwright/scripts/pw.py" <command> [args]
Quick Reference
| Command | Purpose | Example |
|---|---|---|
screenshot |
Capture page screenshot | pw.py screenshot "https://example.com" |
extract |
Extract text/data via selectors | pw.py extract "https://example.com" -s "h1" -f json |
fill |
Fill form fields | pw.py fill "https://url" --fields '{"#email": "[email protected]"}' |
click |
Click element, capture result | pw.py click "https://url" -s "button.submit" |
pdf |
Generate PDF from web page | pw.py pdf "https://example.com" |
youtube |
Extract video content + transcript | pw.py youtube "https://youtu.be/VIDEO_ID" |
batch-screenshots |
Screenshot multiple URLs | pw.py batch-screenshots "url1,url2,url3" |
monitor |
Check URL status | pw.py monitor "https://odun.one" |
execute |
Run custom Playwright script | pw.py execute "/tmp/my_script.py" |
YouTube Content Extraction
The most direct way to understand YouTube video content. Extracts title, description, chapters, and full transcript without needing a browser -- uses YouTube's caption APIs directly.
# Get full video content in markdown (default)
python ".claude/skills/playwright/scripts/pw.py" youtube "https://youtu.be/VIDEO_ID"
# Save to file
python ".claude/skills/playwright/scripts/pw.py" youtube "https://youtu.be/VIDEO_ID" -o "$OUTPUTS_DIR/browser/video.md"
# JSON format for structured processing
python ".claude/skills/playwright/scripts/pw.py" youtube "VIDEO_ID" -f json
What ships with it
4 files 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.
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.
- 2d ago First seen · 221 lines · 80 tokens per session scan A 6215ea659e91
playwright is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed today), licensed Apache-2.0. It adds 80 tokens to every session and 2,583 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
shogun-screenshot
スクリーンショットの取得・加工を行う。ローカルスクショから最新画像を取得、 PlaywrightでWebページをキャプチャ、画像のトリミング・リサイズ、機微情報を黒塗りマスキング。 記事執筆、レポート作成、UI確認、画像加工時に起動。 「スクショ」「スクリーンショット」「画面キャプチャ」「最新のスクショ」「画像加工」「トリミング」「マスク」「写メ」「写メ撮った」「スクショ撮った」で起動。 Do NOT use for: 画像生成（shogun-imagegenを使え）。.
har-derived-api-client
Record a site's XHR into a HAR, derive an HTTP client.
e2e-testing
Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies. Use when writing Playwright tests, structuring page objects, or fixing flaky E2E runs in CI.
scrapling
Scrape sites with stealth browsing and Cloudflare bypass.
dogfood
Exploratory QA of web apps: find bugs, evidence, reports.
blocked-page-recovery
Use when a fetch fails: 403/429, paywall, WAF, bot wall.