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 lexler/skill-factory --skill playwright-cligit clone --depth 1 https://github.com/lexler/skill-factoryWrote 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/lexler/skill-factory/playwright-cli)<a href="https://agentmods.dev/skills/lexler/skill-factory/playwright-cli"><img src="https://agentmods.dev/badge/skills/lexler/skill-factory/playwright-cli/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/lexler/skill-factory/playwright-cli"><img src="https://agentmods.dev/badge/skills/lexler/skill-factory/playwright-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 72 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
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 | $0.00051 | $0.00768 |
| Opus 5.5 | $0.00020 | $0.00307 |
| Sonnet 5.5 | $0.00010 | $0.00154 |
| Haiku 4.5 | $0.00005 | $0.00077 |
Grade A, and why
playwright-cli 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 1mo 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
STARTER_CHARACTER = 🎭
playwright-cli
Driving a browser from the shell. Each command prints the executed Playwright code, the page state, and a fresh snapshot.
The loop
Snapshot to see the page, act on an element by its ref, snapshot again.
playwright-cli snapshot # accessibility tree with [ref=e8] handles
playwright-cli click e8 # act on a ref
playwright-cli snapshot # confirm the result
Refs are not stable. Any DOM change renumbers them — re-snapshot before acting on a page that just changed. Acting on a stale ref hits the wrong element or none.
For a large page, snapshot a region instead of the whole tree: snapshot e34 or snapshot --depth=4.
Targeting elements
A target is one of three things — a ref, a CSS selector, or a Playwright locator:
playwright-cli click e8
playwright-cli click ".todo-list .toggle"
playwright-cli click "getByRole('button', { name: 'Submit' })"
playwright-cli click "getByText('buy milk')"
A bare descriptive phrase is not a target. click "the submit button" is parsed as a CSS selector and fails with "does not match any elements". Prefer refs; reach for getByRole/getByText when a ref won't survive a re-render.
Key commands
playwright-cli goto https://example.com
playwright-cli fill e5 "[email protected]" --submit # clear, type, then Enter — one step
playwright-cli type "free text into the focused element"
playwright-cli press Enter # also: Tab, Escape, ArrowDown
playwright-cli select e9 "option-value"
playwright-cli check e12 # uncheck / hover / dblclick likewise
playwright-cli screenshot # saves to .playwright-cli/
fill works on React/controlled inputs where raw DOM events don't. After filling, the field must blur before dependent values (totals, validation) update — --submit or a following press Tab does that.
Inspecting and verifying
playwright-cli eval "el => el.getAttribute('data-testid')" e5 # attributes the snapshot hides
playwright-cli console # page console messages
playwright-cli requests # network log, then `request <n>`
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.
- 1mo ago First seen · 79 lines · 51 tokens per session scan A 85e7a440f611
playwright-cli is a skill published in the GitHub repository lexler/skill-factory (239 stars, last pushed 16d ago), licensed Apache-2.0. It adds 51 tokens to every session and 768 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 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts and library prototype previews with the existing agent-browser CLI, including screenshots, interaction checks, and rendered DOM snapshots. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser…