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 olorehq/olore --skill 1.60.0git clone --depth 1 https://github.com/olorehq/oloreWrote 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/olorehq/olore/1.60.0)<a href="https://agentmods.dev/skills/olorehq/olore/1.60.0"><img src="https://agentmods.dev/badge/skills/olorehq/olore/1.60.0/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/olorehq/olore/1.60.0"><img src="https://agentmods.dev/badge/skills/olorehq/olore/1.60.0.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00049 | $0.00375 |
| Opus 5.5 | $0.00020 | $0.00150 |
| Sonnet 5.5 | $0.00010 | $0.00075 |
| Haiku 4.5 | $0.00005 | $0.00038 |
Grade A, and why
olore-playwright-1.60.0 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 Documentation
Playwright documentation for end-to-end testing, browser automation, cross-browser testing, selectors, assertions, and test fixtures. Version 1.60.0.
Quick Reference
| Task | Entry Point |
|---|---|
| JavaScript/TypeScript setup | contents/intro-js.md |
| Writing tests | contents/writing-tests-js.md |
| Locators and selectors | contents/locators.md |
| API reference (Page) | contents/api/class-page.md |
| Test configuration | contents/test-configuration-js.md |
| Assertions | contents/test-assertions-js.md |
| Network mocking | contents/mock.md |
| Debugging | contents/debug.md |
When to use
Use this skill when the user asks about:
- End-to-end testing and browser automation
- Locators, selectors, and element interactions
- Test configuration, fixtures, parallelism, and retries
- Network interception, mocking, and API testing
- Screenshots, videos, tracing, and debugging
- Cross-browser testing (Chromium, Firefox, WebKit)
- Accessibility testing and emulation
- Playwright Test runner (JS/TS), pytest, JUnit, NUnit integrations
How to find information
- First, read
TOC.mdfor complete file listing organized by directory - Identify relevant section based on user's question
- Read specific files for details
TOC.md contains all files organized by directory - always check it first.
What ships with it
60 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.
- contents/accessibility-testing-java.md 12 KB
- contents/accessibility-testing-js.md 14 KB
- contents/actionability.md 6.1 KB
- contents/api-testing-csharp.md 14 KB
- contents/api-testing-java.md 14 KB
- contents/api-testing-js.md 13 KB
- contents/api-testing-python.md 10 KB
- contents/api/class-apirequest.md 4.0 KB
- contents/api/class-apirequestcontext.md 29 KB
- contents/api/class-apiresponse.md 3.2 KB
- contents/api/class-apiresponseassertions.md 2.5 KB
- contents/api/class-browser.md 12 KB
- contents/api/class-browsercontext.md 55 KB
- contents/api/class-browserserver.md 720 B
- contents/api/class-browsertype.md 15 KB
- contents/api/class-cdpsession.md 5.2 KB
- contents/api/class-cdpsessionevent.md 425 B
- contents/api/class-clock.md 9.3 KB
- contents/api/class-consolemessage.md 5.3 KB
- contents/api/class-coverage.md 3.1 KB
- contents/api/class-debugger.md 1.8 KB
- contents/api/class-dialog.md 3.7 KB
- contents/api/class-disposable.md 461 B
- contents/api/class-download.md 4.8 KB
- contents/api/class-elementhandle.md 43 KB
- contents/api/class-error.md 595 B
- contents/api/class-filechooser.md 2.1 KB
- contents/api/class-formdata.md 6.8 KB
- contents/api/class-frame.md 72 KB
- contents/api/class-framelocator.md 7.5 KB
- contents/api/class-genericassertions.md 18 KB
- contents/api/class-jshandle.md 5.5 KB
- contents/api/class-keyboard.md 11 KB
- contents/api/class-locator.md 78 KB
- contents/api/class-locatorassertions.md 66 KB
- contents/api/class-logger.md 1.4 KB
- contents/api/class-mouse.md 4.2 KB
- contents/api/class-page.md 171 KB
- contents/api/class-pageassertions.md 12 KB
- contents/api/class-playwright.md 7.4 KB
- contents/api/class-playwrightassertions.md 4.2 KB
- contents/api/class-playwrightexception.md 289 B
- contents/api/class-request.md 13 KB
- contents/api/class-requestoptions.md 5.9 KB
- contents/api/class-response.md 4.9 KB
- contents/api/class-route.md 18 KB
- contents/api/class-screencast.md 4.7 KB
- contents/api/class-selectors.md 8.3 KB
- contents/api/class-snapshotassertions.md 3.2 KB
- contents/api/class-timeouterror.md 2.4 KB
- contents/api/class-touchscreen.md 1010 B
- contents/api/class-tracing.md 15 KB
- contents/api/class-video.md 1.8 KB
- contents/api/class-weberror.md 2.0 KB
- contents/api/class-websocket.md 5.0 KB
- contents/api/class-websocketframe.md 492 B
- contents/api/class-websocketroute.md 14 KB
- contents/api/class-worker.md 6.2 KB
- contents/aria-snapshots.md 18 KB
- contents/auth.md 25 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.
- 1mo ago First seen · 42 lines · 49 tokens per session scan A c10d113501a2
olore-playwright-1.60.0 is a skill published in the GitHub repository olorehq/olore (104 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 375 once invoked, about $0.0002 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
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".
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.
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.
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…