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 LandonSchropp/agent-toolkit --skill playwrightgit clone --depth 1 https://github.com/LandonSchropp/agent-toolkitWrote 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/landonschropp/agent-toolkit/playwright)<a href="https://agentmods.dev/skills/landonschropp/agent-toolkit/playwright"><img src="https://agentmods.dev/badge/skills/landonschropp/agent-toolkit/playwright/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/landonschropp/agent-toolkit/playwright"><img src="https://agentmods.dev/badge/skills/landonschropp/agent-toolkit/playwright.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 | $0.00045 | $0.00718 |
| Opus 5.5 | $0.00018 | $0.00287 |
| Sonnet 5.5 | $0.00009 | $0.00144 |
| Haiku 4.5 | $0.00005 | $0.00072 |
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 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playwright
REQUIRED: Use the playwright-cli skill for the commands themselves. Drive the browser through playwright-cli, never through the Playwright MCP tools, which know nothing about the session.
Always name the session, and pass the name on every later command:
playwright-cli --session=<name> open <url> [flags]
Later commands attach to that browser and inherit the flags it was opened with, so one omitting --headed still drives the headed window. Name the session after the site or account, not the task, and prefer the long --session over -s.
Headed Or Headless
Assume headless unless the instructions or the user say otherwise, or unless the work is blocked on something only the user can do in the window. A window steals focus, so open one only when it earns the interruption: signing in, approving a prompt, or watching the work happen.
Profiles
Use a profile whenever the work depends on a login, in this phase or a later one. Without one the profile is in memory and every login dies with the session.
--browser=chrome --profile="$HOME/.local/share/agent-toolkit/playwright/<profile>"
When using profiles, always use --browser=chrome. This ensures that the user can use their password manager to log into the website.
main is the profile unless a skill names its own. Chrome allows one browser per profile at a time, so an open that fails because the profile is in use should reuse the running session rather than start a second. Ignore the --isolated flag that failure suggests, which hands back a copy holding none of the logins.
When the profile directory is missing, create it with ./scripts/set-up-profile.rb --profile <name>, never by hand. It writes the profile with Chrome's own password manager turned off, and the user installs 1Password in it before the first sign-in.
Write $HOME, not ~, which is not expanded after =.
Recipes
| Situation | Headed | Profile |
|---|---|---|
| Reading a public page | Headless | None |
| Taking a look at a page together | Headed | None |
| Working behind a login | Headless | Profile |
| Signing in to a site | Headed | Profile |
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.
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 Changed · +1 lines · +3 tokens per session 1acc581204b6
- 1mo ago First seen · 59 lines · 42 tokens per session scan A f1841388663f
playwright is a skill published in the GitHub repository LandonSchropp/agent-toolkit (3 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 718 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 2026-08-31.
Other skills, from other repositories
eval-graphics
Turn an eval study's numbers into on-brand, publish-ready figures using the Newsjack chart room (the eval design system), then validate them with Playwright. For producing the charts in a published eval/data study.
news-search
Search current news for a topic, company, competitor, or hook and return dated, attributed articles. Uses the newsjack CLI and Medialyst REST API when available, tries direct Medialyst MCP if the CLI is missing, and falls back to host web/browser search with explicit caveats only when neither cloud path is available.
loom-e2e-testing
End-to-end testing for web applications with Playwright, Cypress, Selenium, and Puppeteer.
browser-extension-builder
Expert in building browser extensions that solve real problems - Chrome, Firefox, and cross-browser extensions. Covers extension architecture, manifest v3, content scripts, popup UIs, monetization strategies, and Chrome Web Store publishing. Use when: browser extension, chrome extension, firefox addon, extension…
web-system-tests
The web realization of the system-tests contract — browser-driven system tests with Playwright against a running frontend. Owns the project layout (tests/), the Playwright configuration (baseURL plus webServer, cross-engine projects), the role- and label-based selector policy, code coverage as an opt-in second run…
browser-automation
Browser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable system comes down to understanding selectors, waiting strategies, and anti-detection patterns. This skill covers Playwright (recommended) and Puppeteer, with patterns for testing, scraping…