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 agents/kumaran-is/claude-code-onboarding/browser-testinggit clone --depth 1 https://github.com/kumaran-is/claude-code-onboardingWhat 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 | $0.00136 | $0.01296 |
| Opus 5 | $0.00068 | $0.00648 |
| Sonnet 5 | $0.00027 | $0.00259 |
| Haiku 4.5 | $0.00014 | $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 2d 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.
- 2d 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 (35 stars, last pushed 2mo ago), licensed MIT. It adds 136 tokens to every session and 1,296 once invoked, about $0.0007 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 agents, from other repositories
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
audit-geo
Evaluates AI crawler access, llms.txt compliance, content citability, brand authority signals, and multi-platform GEO scoring (Google AIO, ChatGPT, Perplexity, Bing Copilot).
praman-sap-planner-cli
SAP UI5 test planner via Playwright CLI. Token-efficient alternative to MCP planner. Generates test plan + gold-standard spec using CLI commands.
FAI Browser Agent
Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".