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 roundpilot/superpowers-antigravity --skill browser-testinggit clone --depth 1 https://github.com/roundpilot/superpowers-antigravityWrote 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/roundpilot/superpowers-antigravity/browser-testing)<a href="https://agentmods.dev/skills/roundpilot/superpowers-antigravity/browser-testing"><img src="https://agentmods.dev/badge/skills/roundpilot/superpowers-antigravity/browser-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/roundpilot/superpowers-antigravity/browser-testing"><img src="https://agentmods.dev/badge/skills/roundpilot/superpowers-antigravity/browser-testing.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 | $0.00021 | $0.00552 |
| Opus 5.5 | $0.00008 | $0.00221 |
| Sonnet 5.5 | $0.00004 | $0.00110 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
browser-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 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.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Testing
Overview
Never claim UI work is correct without visual evidence. Browser automation makes verification fast and produces artifacts the user can review.
Core principle: Evidence before assertions. Screenshots and DOM inspection prove correctness; text descriptions don't.
When to use: After implementing any UI or frontend changes, before claiming the work is correct.
The Process
- Navigate to the page under test using browser automation
- Screenshot the current state — embed in walkthrough artifact
- Inspect DOM to verify structure matches expectations (correct elements, classes, attributes)
- Record a walkthrough of the key user flow (if multi-step interaction)
- Embed evidence in a walkthrough artifact with screenshots and recordings
Quick Reference
| What to verify | Tool | Output |
|---|---|---|
| Visual appearance | Screenshot |  |
| DOM structure | Inspect elements | Element presence, attributes, classes |
| User flow | Recording | Embedded video in artifact |
| Responsive layout | Screenshot at viewport | Multiple screenshots at different widths |
Common Mistakes
| Mistake | Fix |
|---|---|
| Not waiting for page load before screenshot | Wait for key elements to be visible |
| Checking only one viewport size | Test at desktop (1280px) and mobile (375px) minimum |
| Visual-only verification (no DOM check) | Always inspect DOM structure — visual can hide broken markup |
| Forgetting to embed evidence | Every claim needs a screenshot or recording in the artifact |
| Saying "looks correct" without proof | Take the screenshot. Embed it. Let the user judge. |
Evidence classification in artifacts: Use GitHub-style alerts:
> [!TIP]for passing checks> [!CAUTION]for failing checks> [!NOTE]for observations that need human judgment
Integration
- superpowers:verification-before-completion — browser-testing is specialized verification for UI work
- superpowers:test-driven-development — browser tests complement unit tests, they don't replace them
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 · 56 lines · 21 tokens per session scan A 4718ee129b7f
browser-testing is a skill published in the GitHub repository roundpilot/superpowers-antigravity (72 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 552 once invoked, about $0.0001 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
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…