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 fmind/dot --skill playwrightgit clone --depth 1 https://github.com/fmind/dotWrote 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/fmind/dot/playwright)<a href="https://agentmods.dev/skills/fmind/dot/playwright"><img src="https://agentmods.dev/badge/skills/fmind/dot/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/fmind/dot/playwright"><img src="https://agentmods.dev/badge/skills/fmind/dot/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 | $0.00020 | $0.01016 |
| Opus 5.5 | $0.00008 | $0.00406 |
| Sonnet 5.5 | $0.00004 | $0.00203 |
| Haiku 4.5 | $0.00002 | $0.00102 |
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 12d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playwright
Use Playwright for browser automation and end-to-end tests. Test strategy belongs to quality-assurance and interface critique to product-design-review; this skill owns the tool: browsers, commands, and the official skills.
Workflow
- Pin the Python integration:
uv add --dev playwright pytest-playwright, thenuv run playwright install chromium; keep both packages inuv.lock. If Linux system libraries are missing, report the administrator-owned prerequisite instead of invoking the privilegedinstall-depscommand. - Explore and record:
uv run playwright codegen --target python <url>records Python actions;uv run playwright screenshot <url> <file>anduv run playwright pdf <url> <file>produce review evidence. - Run tests:
uv run pytest -q tests/e2e --browser chromium --tracing retain-on-failure --screenshot only-on-failure. Inspect a saved trace from the shell withuv run playwright trace open <trace.zip>and the subcommands inuv run playwright trace --help(errors, actions, requests, console);trace closeremoves the extracted data.show-traceopens the GUI viewer for humans.
Gotchas
- Act only within authorized scope: use the profiles, accounts, data, and actions authorized for the task; reuse existing authorization. A test request alone does not authorize private browser-session reuse, cookie transfers, account creation, legal acceptance, purchases, or paid browser services. When a required action falls outside that scope, prepare the local test and explain the specific missing authorization before proceeding. Treat login, MFA, and CAPTCHA as explicit authentication boundaries, never bypasses.
- Reuse the shared browser cache: install only required browsers and reuse the default shared cache (
~/.cache/ms-playwrighton Linux). Do not runplaywright uninstallas task teardown: other projects can need those binaries. Remove task-created temporary profiles and passing-run artifacts, preserve requested evidence and failure traces, and review native browser cleanup separately when disk pressure requires it. - Reinstall browsers after upgrades: browsers match the Playwright version that installed them; rerun
uv run playwright install chromiumafter an upgrade.
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.
- 12d ago Changed · -3 lines 323e394ad2fd
- 14d ago Changed e78480d21d46
- 15d ago Changed · -1 lines · +1 tokens per session a985fd6bc4b1
- 17d ago Changed 9975ed62cb69
- 23d ago Changed c270317ca4a5
- 1mo ago Changed · +1 lines · -14 tokens per session 086d26cf95ea
- 1mo ago Changed c4b46b753da6
- 1mo ago Changed · +1 lines cab797e96805
- 1mo ago Changed 8f1b3ded7fdc
- 1mo ago First seen · 40 lines · 33 tokens per session scan A a6da237c2dc5
playwright is a skill published in the GitHub repository fmind/dot (12 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 1,016 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
walkthrough
Generate a hands-on browser walkthrough of a PR's user-facing changes to exercise before review; --publish posts the final version to the PR for QA.
mise
Configure pinned mise tools and canonical install, format, check, test, build, and watch tasks shared by hooks and CI.
agent-evaluation
Evaluate stochastic LLM/RAG/model/retrieval/tool agents in trials. Compare baseline/candidate on development/sealed holdouts with calibrated deterministic/model/trace graders; measure reliability, variance, leakage, safety, and cost.
quality-assurance
Design and execute risk-based test campaigns and exercise risky feature journeys; identify what remains unproved across unit, integration, E2E, browser, accessibility, performance, resilience, and manual tests. Not a diff review.
test-driven-development
Implement an isolated bug fix or behavior change with an honest red-green-refactor cycle. Use when a regression test should fail before the correction, or when tested logic, refactors, or seams must prove correctness.
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.