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/metaspartan/cybara/browser-qanpx skills add metaspartan/cybara --skill browser-qagit clone --depth 1 https://github.com/metaspartan/cybaraWrote 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/metaspartan/cybara/browser-qa)<a href="https://agentmods.dev/skills/metaspartan/cybara/browser-qa"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/browser-qa.svg" alt="Measured on agentmods" 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 | $0.00022 | $0.00242 |
| Opus 5 | $0.00011 | $0.00121 |
| Sonnet 5 | $0.00004 | $0.00048 |
| Haiku 4.5 | $0.00002 | $0.00024 |
Grade A, and why
browser-qa 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 5d 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
Browser quality
Use the embedded browser for interactive validation when a task changes or audits a web interface.
Workflow
- Start the application with the repository's existing Bun script and wait for its health endpoint or listening address.
- Open the application in the embedded browser and confirm the initial page renders without console errors.
- Exercise the primary workflow with real clicks, typing, navigation, and state changes.
- Repeat the workflow at representative desktop and narrow viewport sizes.
- Capture screenshots of the meaningful finished states and inspect them for clipping, overlap, empty regions, and broken assets.
- Verify keyboard focus order, accessible labels, reduced motion, and light and dark theme behavior when supported.
- Report the tested URL, viewport sizes, interactions, console failures, and screenshot paths.
Reliability
- Wait on observable UI state instead of fixed sleeps.
- Reuse the current embedded browser session so the user can follow the run.
- Do not claim visual correctness from source inspection alone.
- Keep authentication and destructive actions within the user's stated scope.
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.
- 5d ago First seen · 26 lines · 22 tokens per session scan A 26b031ae7393
browser-qa is a skill published in the GitHub repository metaspartan/cybara (26 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 242 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
composio-webapp-testing
Skill "composio-webapp-testing" from KornLabs/truss, covering web application testing, decision tree: choosing your approach, example: using withserver.py, reconnaissance-then-action pattern and common pitfall.
browser-testing-with-screenshots
Use when testing web applications with visual verification - automates Chrome browser interactions, element selection, and screenshot capture for confirming UI functionality.
11-browser-qa
Run post-review browser QA and produce short named videos for a locked happy path and sourced browser edge cases. Use when the user wants concise reviewer evidence for a web journey. Not for API, CLI, automated tests, diff review, or application fixes.
06-test
Write and iterate tests until they pass, or validate a user journey end to end in the browser. Use when the user wants to add coverage, find what's untested, or walk a flow. Not for auditing test health or debugging a failure.
run-dashboard-e2e-local-changes
Run Playwright E2E (tests/e2e/) against the docker/ all-in-one harness so it reflects LOCAL code changes, not a stale cached image.
loom-e2e-testing
End-to-end testing for web applications with Playwright, Cypress, Selenium, and Puppeteer.