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 agentmods add skills/microsoft/playwright/playwright-devopsnpx skills add microsoft/playwright --skill playwright-devopsgit clone --depth 1 https://github.com/microsoft/playwrightWhat 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 | $0.00023 | $0.00103 |
| Opus 5 | $0.00012 | $0.00051 |
| Sonnet 5 | $0.00005 | $0.00021 |
| Haiku 4.5 | $0.00002 | $0.00010 |
Grade A, and why
playwright-devops 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 2d 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 DevOps
Guides
- CI Commit Failure Report — analyze GitHub Actions failures for the last commit on main
- fetch-commit-logs.sh — script to download failed job logs into
~/tmp/commit-<sha>/
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.
- 2d ago First seen · 13 lines · 23 tokens per session scan A 01c6e8538882
playwright-devops is a skill published in the GitHub repository microsoft/playwright (95,378 stars, last pushed 3d ago), licensed Apache-2.0. It adds 23 tokens to every session and 103 once invoked, about $0.0001 per session on Opus 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
nextjs-ssr
Tag server-side fetches with the x-test-rcrd-id session header so SSR is recorded under the correct Playwright test session. Lead with registerProxyFetch (patch global fetch in the root layout, any runtime) and registerProxyAxios (per-axios-instance interceptor); createHeadersWithRecordingId is the patch-free per-call…
proxy-setup
Set up test-proxy-recorder for any Playwright project. Covers the proxy CLI (test-proxy-recorder --port --dir), package.json scripts for the three-service architecture (UI app → proxy → backend API), playwright.config.ts webServer block pointing to /control, per-test fixtures using playwrightProxy.before(page…
tanstack-start
Record and replay TanStack Start SSR with test-proxy-recorder. Tag server-side fetches (route loaders, server functions, server routes) with the x-test-rcrd-id session header so parallel replay stays correct. Lead with registerProxyFetch (patch global fetch once at the top of src/router.tsx)…
glance-test
Run E2E browser tests on any web application using Glance MCP. Use when the user says "test this page," "check this URL," "run E2E tests," "browser test," "test the login flow," "check if the site works," "visual regression," or "screenshot this page." Also use for post-deploy verification and smoke tests.
qa-explore
Exploratory end-to-end QA with a team of agents that drive a real browser like human testers — they click through the whole app, create/fill/submit, screenshot and visually judge rendering + data correctness, capture trace/HAR/console/video evidence, adversarially verify each finding, learn from rejected findings, and…
qa-fix
Second half of the qa-explore loop — pick up the issues a human marked as real bugs in the tracker (GitLab/GitHub), reproduce each one, write a regression test that asserts the correct behaviour, fix the code until that test goes green and the suite stays green, then open a merge request linked to the issue for human…