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/ric03uec/clawrium/create-playwrightnpx skills add ric03uec/clawrium --skill create-playwrightgit clone --depth 1 https://github.com/ric03uec/clawriumWrote 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/ric03uec/clawrium/create-playwright)<a href="https://agentmods.dev/skills/ric03uec/clawrium/create-playwright"><img src="https://agentmods.dev/badge/skills/ric03uec/clawrium/create-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 | $0.00049 | $0.04910 |
| Opus 5 | $0.00024 | $0.02455 |
| Sonnet 5 | $0.00010 | $0.00982 |
| Haiku 4.5 | $0.00005 | $0.00491 |
Grade A, and why
create-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 4d 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 — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Demo Recording with Playwright — replay-first pipeline
Record browser demos using Playwright Python. Each demo lives in its own dated-slug folder docs/demos/YYYYMMDD-<slug>/ — the same parent as CLI demos produced by /create-vhs. The pipeline is replay-first: network responses are captured once via HAR on a live app, then a YAML spec drives driver generation, recording, and narration. Iteration is fast and timing is deterministic.
Pipeline
(one-time, slow)
scenes.yaml + live app --> outputs/*.har [HAR capture phase]
|
(instant) v
scenes.yaml + outputs/*.har --> pw_compile.py --> driver.py + cards/*.html + compiled.json
|
(~recording length) v
uv run driver.py --> recording.webm
|
(~5s, codec swap) v
ffmpeg -c:v libx264 ... --> recording.mp4
|
(~30s, cached per text) v
narrate.py compiled.json --> voice/*.mp3 + recording-narrated.mp4
|
(manual) v
upload to YouTube
pw_compile.py, the driver, and narrate.py are all idempotent. The slow step is the initial HAR capture; everything downstream re-runs in seconds.
Output Layout
| Path | Committed? | Purpose |
|---|---|---|
docs/demos/lib/pw_compile.py |
yes | scenes.yaml → driver.py + cards/*.html + compiled.json |
docs/demos/lib/pw_driver.py.j2 |
yes | Jinja template for the generated driver |
docs/demos/lib/cards/title.html.j2 |
yes | Title-card HTML template |
docs/demos/lib/cards/outro.html.j2 |
yes | Outro-card HTML template |
docs/demos/lib/narrate.py |
yes | Reused unchanged from /create-vhs |
docs/demos/lib/.env.example |
yes | Reused unchanged — ElevenLabs credentials template |
docs/demos/lib/.env |
no (gitignored) | Reused unchanged — real API key + voice/model IDs |
docs/demos/YYYYMMDD-<slug>/scenes.yaml |
yes | Single source of truth — scene structure, actions, narration |
docs/demos/YYYYMMDD-<slug>/outputs/NN-<slug>.har |
yes | Per-scene captured network responses (replayed by the driver) |
docs/demos/YYYYMMDD-<slug>/outputs/storage_state.json |
no (gitignored) | Auth/cookie state captured via playwright codegen; contains tokens |
docs/demos/YYYYMMDD-<slug>/driver.py |
yes | Generated by pw_compile.py; do not hand-edit |
docs/demos/YYYYMMDD-<slug>/cards/title.html |
yes | Generated by pw_compile.py |
docs/demos/YYYYMMDD-<slug>/cards/outro.html |
yes | Generated by pw_compile.py |
docs/demos/YYYYMMDD-<slug>/compiled.json |
yes | Generated by pw_compile.py; absolute narration timestamps |
docs/demos/YYYYMMDD-<slug>/voice/*.mp3 |
no (gitignored) | Per-beat TTS clips, cached by sha1(voice_id + text) |
docs/demos/YYYYMMDD-<slug>/recording.webm |
no (gitignored) | Direct Playwright video output |
docs/demos/YYYYMMDD-<slug>/recording.mp4 |
no (gitignored) | ffmpeg-transcoded H.264 |
docs/demos/YYYYMMDD-<slug>/recording-narrated.mp4 |
no (gitignored) | Final video with voiceover muxed in |
What ships with it
2 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.
- 4d ago First seen · 323 lines · 49 tokens per session scan A 1ef1741a1dae
create-playwright is a skill published in the GitHub repository ric03uec/clawrium (51 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 4,910 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
x402
Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — "just use it" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing…
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
scrapling-official
Scrape web pages using Scrapling with anti-bot bypass (like Cloudflare Turnstile), stealth headless browsing, spiders framework, adaptive scraping, and JavaScript rendering. Use when asked to scrape, crawl, or extract data from websites; webfetch fails; the site has anti-bot protections; write Python code to…
remote-browser
Controls an isolated Browser Use Cloud browser from a sandboxed machine with the current Browser Use CLI.
load-github-action-thread
Download retained Codex GitHub Action thread artifacts and load their rollout history into the local Codex app. Use when asked to open, load, import, resume, or inspect a Codex automation thread from a GitHub Actions run or a related GitHub issue or pull request.
textual-screenshot
Capture a Textual terminal UI as an SVG using its headless test harness. Use when asked to make, attach, or preview a screenshot of deepagents-code/dcode or another Textual app, visually verify a TUI state, or render a modal, screen, or widget without a desktop or browser.