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 bdfinst/agentic-dev-team --skill browser-testinggit clone --depth 1 https://github.com/bdfinst/agentic-dev-teamWrote 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/bdfinst/agentic-dev-team/browser-testing)<a href="https://agentmods.dev/skills/bdfinst/agentic-dev-team/browser-testing"><img src="https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/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/bdfinst/agentic-dev-team/browser-testing"><img src="https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/browser-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 22 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00032 | $0.00737 |
| Opus 5.5 | $0.00013 | $0.00295 |
| Sonnet 5.5 | $0.00006 | $0.00147 |
| Haiku 4.5 | $0.00003 | $0.00074 |
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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Testing Skill
Overview
This skill provides reusable patterns for browser-based testing and visual verification using Playwright. Agents load this skill when they need to interact with a running application through a real browser.
Prerequisites
Playwright must be installed with at least the Chromium browser — /project-init installs it for frontend projects, or install manually:
npx playwright install chromium
Playwright Patterns
| Category | Description |
|---|---|
| Navigation | goto, waitForSelector, waitForNavigation with network-idle |
| Form Interaction | fill, selectOption, check, setInputFiles, submit |
| Click Actions | Click by selector/text, double-click, right-click, hover |
| Screenshots | Full page, viewport, element, and clipped region captures |
| Waiting Strategies | Selector appear/disappear, text match, network response |
| Data Extraction | textContent, getAttribute, inputValue, count, isVisible |
| Script Template | Full /browse boilerplate with error capture and console logging |
| Error Handling | Common timeout, connection, and protocol errors with resolutions |
| CAPTCHA/Auth Handoff | Detect walls, report to user, resume from storageState |
See references/playwright-patterns.md for full code examples, the script template, and the error handling table.
Fast Feedback Loop
A verification pass is usually a sequence of related checks, not one isolated check — keep the loop cheap:
- Batch checks into one session. Launch the browser once, run the full sequence of actions/waits/screenshots needed for the verification pass, then close — don't relaunch a fresh browser per individual check.
- Reserve
networkidlefor the first navigation. After the initialgoto, a re-check following a known, small change should wait on the specific signal that changed (waitForSelector,waitForResponse) rather than re-waiting on full network idle. - Skip the reload when nothing routed. If the change under verification didn't require a new route or a fresh document, act on the already-loaded page instead of calling
page.goto()again or relaunching; usepage.reload()only when a fresh document is genuinely required. - Scope intermediate screenshots. Prefer element/clip screenshots for the in-between checks in a sequence; reserve full-page screenshots for the final verification.
What ships with it
1 file 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.
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 · 63 lines · 32 tokens per session scan A 74c804861c5e
browser-testing is a skill published in the GitHub repository bdfinst/agentic-dev-team (295 stars, last pushed 4d ago), licensed MIT. It adds 32 tokens to every session and 737 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 2026-09-03.
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…