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 OpenKnots/okcode --skill playwrightgit clone --depth 1 https://github.com/OpenKnots/okcodeWrote 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/openknots/okcode/playwright)<a href="https://agentmods.dev/skills/openknots/okcode/playwright"><img src="https://agentmods.dev/badge/skills/openknots/okcode/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/openknots/okcode/playwright"><img src="https://agentmods.dev/badge/skills/openknots/okcode/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 | $0.00011 | $0.00417 |
| Opus 5.5 | $0.00004 | $0.00167 |
| Sonnet 5.5 | $0.00002 | $0.00083 |
| Haiku 4.5 | $0.00001 | $0.00042 |
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.
What it actually says
Playwright Skill
When to use this skill
- Use when the task needs browser automation, UI verification, end-to-end testing, or scripted web interactions.
- Use when the user needs reproducible validation of browser behavior rather than manual spot-checking.
- Use when screenshots, DOM assertions, navigation flows, or form automation are part of the task.
- Use when the user wants a reliable browser-based regression check from the terminal.
What this skill does
- Designs Playwright workflows that are deterministic, inspectable, and resilient to minor UI changes.
- Prefers stable selectors and event-driven waits over brittle timing assumptions.
- Captures actionable failure context such as URLs, selectors, screenshots, and expectation mismatches.
- Keeps test intent focused on behavior, not incidental implementation details.
Implementation
- Clarify whether the goal is one-off browser automation, a reusable test, or a debugging workflow.
- Prefer semantic selectors and stable locators over deep CSS selectors tied to styling structure.
- Use assertions that reflect user-observable behavior rather than implementation accidents.
- Prefer waits based on navigation, visible UI state, or network/DOM readiness rather than arbitrary sleep intervals.
- If the task is exploratory, keep scripts short and focused on reproducing the target behavior.
- If the task is test authoring, structure steps and assertions so failures are easy to diagnose.
- Capture enough context on failure for a human to reproduce and fix the issue quickly.
Best practices
- Avoid timing-based waits unless no stronger signal exists.
- Keep selectors robust and understandable.
- Prefer behavior-level assertions over snapshotting everything.
- Include screenshots or other evidence when reporting a browser failure.
- Keep scripts and tests maintainable; do not overfit to current DOM noise.
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 · 50 lines · 11 tokens per session scan A 6e0e017d388a
playwright is a skill published in the GitHub repository OpenKnots/okcode (24 stars, last pushed 5mo ago), licensed MIT. It adds 11 tokens to every session and 417 once invoked, about $0.0000 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
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…