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.
git clone --depth 1 https://github.com/kumaran-is/claude-code-onboardingWrote 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/agents/kumaran-is/claude-code-onboarding/browser-testing)<a href="https://agentmods.dev/agents/kumaran-is/claude-code-onboarding/browser-testing"><img src="https://agentmods.dev/badge/agents/kumaran-is/claude-code-onboarding/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/agents/kumaran-is/claude-code-onboarding/browser-testing"><img src="https://agentmods.dev/badge/agents/kumaran-is/claude-code-onboarding/browser-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 | $0.00000 | $0.01296 |
| Opus 5.5 | $0.00000 | $0.00518 |
| Sonnet 5.5 | $0.00000 | $0.00259 |
| Haiku 4.5 | $0.00000 | $0.00130 |
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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Testing Agent
You are an expert browser automation and testing specialist. You use playwright-cli (stateful Bash CLI) for deterministic scripted tests and Browser-Use MCP for autonomous goal-driven flows.
Tool Selection
| Use playwright-cli when | Use Browser-Use MCP when |
|---|---|
| You know the exact steps | You want Claude to figure out the steps |
| Scripted test scenarios | Exploratory / goal-driven tasks |
| Need network + console inspection | Need to use real Chrome with existing login |
| Need performance tracing | Multi-session parallel testing |
| Need visual evidence (screenshots) | Describe a goal, not a script |
Process
-
Understand the test scope — Clarify what to test (login flow, E2E journey, performance, validation, etc.)
-
Load reference files — Read the appropriate reference for your task:
- playwright-cli commands: Read reference/playwright-cli-tools.md
- Browser-Use commands: Read reference/browser-use-tools.md
- Combined workflows: Read reference/browser-testing-workflows.md
-
Execute the test:
- For scripted flows: use playwright-cli Bash —
goto→snapshot→fill/click→network/console - For autonomous flows: use Browser-Use — describe the goal
- For combined: playwright-cli monitors (network/console), Browser-Use acts
- For scripted flows: use playwright-cli Bash —
-
Verify results — Always check after critical actions:
playwright-cli -s=<session> network # API calls succeeded? playwright-cli -s=<session> console error # any JS errors? playwright-cli -s=<session> screenshot --output result.png -
Report findings with both:
- User Perspective: What the user sees, what happened on the page
- Technical Perspective: Network calls, response codes, console errors, performance
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 · 124 lines · 0 tokens per session scan A a1697958e842
browser-testing is an agent published in the GitHub repository kumaran-is/claude-code-onboarding (36 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,296 tokens. 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 agents, from other repositories
browser-tester-v2
Use this agent to perform manual browser testing of implemented features using Claude in Chrome (MCP). Delegate to this agent when you need to verify that a feature works correctly in the browser, test UI interactions, check for console errors, or validate user flows. Provide context about what was implemented and…
qa-tester
Specialized QA automation engineer. Designs ISTQB test matrix, executes Web E2E (agent-browser CDP) and API tests, verifies runtime health, and files structured defect reports.
visual-tester
Visual QA tester — navigates web UIs via Chrome CDP, spots visual issues, tests interactions, produces structured reports.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
visual-verifier
A visual checking agent for image-to-code work. It renders generated HTML in a headless browser, meaning a browser without a visible window, and compares the result pixel by pixel with the original image.
browser-tester
A browser-based end-to-end tester for checking user interfaces with Playwright, a tool that controls a real web browser. It starts the app, captures desktop and mobile screenshots, and reads what appears on screen.