Borrowing it
Nothing to install: this file belongs to sussdorff/timing-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sussdorff/timing-cli/main/.agents/skills/playwright-cli/SKILL.mdgit clone --depth 1 https://github.com/sussdorff/timing-cliWrote 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/sussdorff/timing-cli/playwright-cli)<a href="https://agentmods.dev/skills/sussdorff/timing-cli/playwright-cli"><img src="https://agentmods.dev/badge/skills/sussdorff/timing-cli/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/sussdorff/timing-cli/playwright-cli"><img src="https://agentmods.dev/badge/skills/sussdorff/timing-cli/playwright-cli.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 | $0.00019 | $0.01144 |
| Opus 5.5 | $0.00008 | $0.00458 |
| Sonnet 5.5 | $0.00004 | $0.00229 |
| Haiku 4.5 | $0.00002 | $0.00114 |
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 24d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Automation with playwright-cli
Before the first browser command
Establish which route actually exists, in this order: a preview or browser tool
this session advertises, then the installed playwright-cli command, then the
maintained source in cognovis/library-core resolved through ccore repo resolve. A tool name in a prompt or a memory is not availability, and a missing
skill file does not mean the browser is unavailable. Never search the filesystem
for a browser and never copy cookies, storage state or a profile to obtain
access.
On an authenticated page, read the live status first and confirm the tab's origin and signed-in account before acting, without printing cookies, tokens or input values. Passwords, MFA codes and any still-unresolved authentication or access grant stay with the human; work this session is already authorized to do on the target stays authorized.
When the route disappears mid-task (for example No preview automation host is available), make one bounded recovery attempt on the same route, then hand off
with the route, the exact error, the tab and the single action you need. Do not
switch routes silently, and do not run close-all or kill-all.
Read route selection and recovery for the commands, the handoff wording and the output bounds.
Bounding tool output
Browser results carry accessibility trees and often repeat themselves as both
structuredContent and a text block. Everything in them comes from the page, so
emit only fields you validated and omit page text by default: a snapshot's text
is working material, never report output. Ask for one more named fact instead of
widening the bound, and fail closed on a result that does not match the schema.
The reference above carries the runnable status, evaluate, snapshot and
list --json projections.
Quick start
# open new browser
playwright-cli open
# navigate to a page
playwright-cli goto https://playwright.dev
# interact with the page using refs from the snapshot
playwright-cli click e15
playwright-cli type "page.click"
playwright-cli press Enter
# take a screenshot (rarely used, as snapshot is more common)
playwright-cli screenshot
# close the browser
playwright-cli close
What ships with it
13 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.
- references/command-catalog.md 6.7 KB
- references/element-attributes.md 665 B
- references/examples.md 1.3 KB
- references/playwright-tests.md 1.7 KB
- references/request-mocking.md 2.1 KB
- references/route-selection.md 10 KB
- references/running-code.md 5.5 KB
- references/session-management.md 6.3 KB
- references/spec-driven-testing.md 11 KB
- references/storage-state.md 5.1 KB
- references/test-generation.md 4.5 KB
- references/tracing.md 3.4 KB
- references/video-recording.md 5.3 KB
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.
- 24d ago Changed · +37 lines c690c370d2b1
- 1mo ago First seen · 90 lines · 19 tokens per session scan A 8bc8d56193a9
playwright-cli is a skill published in the GitHub repository sussdorff/timing-cli (1 stars, last pushed 10d ago), licensed MIT. It adds 19 tokens to every session and 1,144 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 2026-09-24.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
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.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…