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 rules/transloadit/node-sdk/playwrightgit clone --depth 1 https://github.com/transloadit/node-sdkWhat 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 | $0.00000 | $0.00300 |
| Opus 5 | $0.00000 | $0.00150 |
| Sonnet 5 | $0.00000 | $0.00060 |
| Haiku 4.5 | $0.00000 | $0.00030 |
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 yesterday.
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
- Prefer user-centric locators:
getByRole/getByTextwith accessible names; avoidpage.locator('body'),innerText(), or raw CSS unless there is no accessible alternative. - Treat
data-*attributes as implementation details in browser tests unless they are the only stable contract available. If UI needs testing via state such as notifications, prefer adding or using an accessible role/name/state contract over asserting hidden implementation attributes. - Make positive assertions on expected UI/text instead of looping over regexes to assert absence.
- Keep tests simple: no control-flow loops or extra variables for straightforward assertions.
- For localized route work, cover page chrome as well as body content: navbar/mobile nav, search
labels, subnav, post metadata/bylines, dynamic cards,
html lang, canonical, and hreflang. - Navigate with relative URLs (
page.goto('/path')) by settingbaseURLinplaywright.config.ts; avoid stringing environment URLs in tests. - Stub or mock external/third‑party requests (Intercom, Sentry, etc.) and any auth/login endpoints to keep tests deterministic; return minimal valid JSON when the app expects data.
- Each unexpected error should surface and fail the test.
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.
- yesterday First seen · 17 lines · 0 tokens per session scan A 562806840602
playwright is a cursor rule published in the GitHub repository transloadit/node-sdk (73 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 300 tokens. 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 cursor rules, from other repositories
i18n-patterns
國際化 (i18n) 使用規範與翻譯檔維護策略.
rails-standards
Rails coding standards — security, RuboCop compliance, DRY principles, and i18n translations.
as-contract-cast-smell
// ❌ WRONG — bypasses the family ContractSerializer seam const contract = JSON.parse(raw) as Contract; const contract = JSON.parse(raw) as Contract .
no-barrel-files
Avoid barrel files and unnecessary re-exports.
interface-factory-pattern
Interface-based design with factory functions (keep classes private).
explicit-opt-in-over-diagnostics
Prefer requiring explicit opt-in over emitting diagnostics on intentional user paths.