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 haposoft/cafekit --skill web-testinggit clone --depth 1 https://github.com/haposoft/cafekitWrote 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/haposoft/cafekit/web-testing)<a href="https://agentmods.dev/skills/haposoft/cafekit/web-testing"><img src="https://agentmods.dev/badge/skills/haposoft/cafekit/web-testing/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/haposoft/cafekit/web-testing"><img src="https://agentmods.dev/badge/skills/haposoft/cafekit/web-testing.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 | $0.00051 | $0.00748 |
| Opus 5.5 | $0.00020 | $0.00299 |
| Sonnet 5.5 | $0.00010 | $0.00150 |
| Haiku 4.5 | $0.00005 | $0.00075 |
Grade A, and why
cf:web-testing 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
26 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/accessibility-testing.md 1.9 KB
- references/api-testing.md 1.8 KB
- references/ci-cd-testing-workflows.md 2.5 KB
- references/component-testing.md 2.4 KB
- references/contract-testing.md 3.3 KB
- references/cross-browser-checklist.md 1.7 KB
- references/database-testing.md 3.3 KB
- references/e2e-testing-playwright.md 2.7 KB
- references/functional-testing-checklist.md 2.7 KB
- references/interactive-testing-patterns.md 2.5 KB
- references/load-testing-k6.md 1.7 KB
- references/mobile-gesture-testing.md 2.1 KB
- references/performance-core-web-vitals.md 3.1 KB
- references/playwright-component-testing.md 2.8 KB
- references/pre-release-checklist.md 1.8 KB
- references/security-checklists.md 2.5 KB
- references/security-testing-overview.md 2.8 KB
- references/shadow-dom-testing.md 1.6 KB
- references/test-data-management.md 2.9 KB
- references/test-flakiness-mitigation.md 1.8 KB
- references/testing-pyramid-strategy.md 2.1 KB
- references/unit-integration-testing.md 2.7 KB
- references/visual-regression.md 2.2 KB
- references/vulnerability-payloads.md 1.3 KB
- scripts/analyze-test-results.js 7.8 KB runs code
- scripts/init-playwright.js 6.5 KB runs code
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 Changed · -18 lines 7a476be234af
- 1mo ago Changed · -1 tokens per session 30f3f7c80305
- 1mo ago First seen · 103 lines · 52 tokens per session scan A b2781e023db2
cf:web-testing is a skill published in the GitHub repository haposoft/cafekit (54 stars, last pushed yesterday), with no licence file. It adds 51 tokens to every session and 748 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 2026-08-30.
Other skills, from other repositories
playwright
Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions…
Playwright Browser Automation
Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions…
chrome-cdp
Drive a headless Chrome over the Chrome DevTools Protocol (CDP) for browser QA — navigate, click, fill forms, read the DOM/accessibility tree, screenshot, and assert. Use whenever a task requires loading a web page and interacting with it like a user. Chrome is launched by a bash step (recipe below); this skill…
web-test
A browser-automation tool for testing the 1C:Enterprise web client. It uses Playwright to navigate sections, fill forms, read tables and reports, and perform user actions in a browser.
BrowserBash Browser Automation
BrowserBash is a vendor-independent, natural-language browser automation CLI. Drive a real browser from plain-English objectives or committable Markdown tests, run on local Chrome, CDP/Playwright MCP, Browserbase, LambdaTest, or BrowserStack, and stream NDJSON results with CI exit codes — using free local Ollama…
selectors
Selector strategy, exploration-first workflow, locator priority order (getByRole then getByLabel then getByPlaceholder then getByText then getByTestId), and feedback/validation-message selector rules for Playwright page objects. Use when creating page objects, writing or updating locators, generating UI tests, or…