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 commands/anhtester/claudecode_playwright_demo/generate_application_test_plangit clone --depth 1 https://github.com/anhtester/ClaudeCode_Playwright_DemoWrote 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/commands/anhtester/claudecode_playwright_demo/generate_application_test_plan)<a href="https://agentmods.dev/commands/anhtester/claudecode_playwright_demo/generate_application_test_plan"><img src="https://agentmods.dev/badge/commands/anhtester/claudecode_playwright_demo/generate_application_test_plan.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 | $0.00037 | $0.01514 |
| Opus 5 | $0.00018 | $0.00757 |
| Sonnet 5 | $0.00007 | $0.00303 |
| Haiku 4.5 | $0.00004 | $0.00151 |
Grade A, and why
generate_application_test_plan 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 4d 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.
This is a copy
92% identical to generate_application_test_plan — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow: Khám Phá Ứng Dụng & Sinh Test Plan
BẮT BUỘC (MANDATORY SKILL): Bạn PHẢI nạp và đọc kỹ nội dung của skill
qa_automation_engineer(tại.agent/skills/qa_automation_engineer/SKILL.md) trước khi bắt đầu. Ngoài ra, tham khảo thêm skillrequirements_analyzervàui_debug_agentđể hỗ trợ phân tích UI.
Workflow này giúp agent tự động khám phá một ứng dụng web, phân tích cấu trúc, xác định các modules/user flows quan trọng, và sinh ra Test Plan hoàn chỉnh.
⚠️ Nguyên tắc thực thi
- Tất cả output bằng Tiếng Việt
- KHÔNG đoán cấu trúc app — phải inspect DOM thực tế qua MCP/browser tools
- Phải chờ user xác nhận scope tại Bước 2 trước khi sinh chi tiết
- Nếu user chưa cung cấp URL → hỏi trước khi bắt đầu
2 Chế độ (Mode)
| Mode | Khi nào sử dụng | Output |
|---|---|---|
| PLAN (mặc định) | User cần khám phá app, lập test plan, xác định scenarios | Modules, User Flows, Test Scenarios, Priority |
| FULL | User yêu cầu thêm automation skeleton hoặc nói "full automation suite" | Như PLAN + Manual Test Cases + Automation Skeleton (POM + Test classes) |
Nếu user nói "generate full automation suite", "bootstrap automation", hoặc yêu cầu code → tự động chuyển sang Mode FULL.
Các bước thực hiện
Bước 1: Tiếp nhận & Khám phá ứng dụng (Recon)
- Nhận URL ứng dụng từ user
- Sử dụng MCP browser tools (Playwright MCP) để mở ứng dụng:
browser_navigate→ URLbrowser_resize(1920, 1080)→ desktop viewportbrowser_snapshot→ thu thập cấu trúc DOM
- Khám phá navigation menus, sidebar, header để xác định các modules chính
- Lần lượt truy cập từng module chính, dùng
browser_snapshotđể ghi nhận:- Tên module / trang
- Các thành phần UI chính (forms, tables, buttons, modals)
- Các action có thể thực hiện (CRUD, search, filter, export...)
- Nếu app yêu cầu đăng nhập → hỏi user cung cấp credentials hoặc dùng fixture sẵn có
Bước 2: Phân tích & Xác nhận scope (Analysis — CHECKPOINT)
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.
- 4d ago First seen · 116 lines · 37 tokens per session scan A 2e6f1880fbec
generate_application_test_plan is a command published in the GitHub repository anhtester/ClaudeCode_Playwright_Demo (2 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 1,514 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to generate_application_test_plan, differing in 8 lines, and is treated as a copy.
Other commands, from other repositories
generate_automation_from_testcases
Convert manual test cases into automation scripts autonomously using the 6-step AI-RBT Framework via Claude Code Capabilities.
generate_automation_from_ui_flow
Thực thi UI flow trực tiếp trên browser, thu thập locators từ DOM thực tế, và sinh automation scripts. Hỗ trợ Playwright, Selenium, Appium.
generate_locator
Sinh locator ổn định cho UI element. Hỗ trợ Playwright, Selenium, Appium.
import_test_results_xray
Đẩy kết quả test automation (Playwright/JUnit/Allure) lên Xray Test Management.
generate_application_test_plan
Khám phá ứng dụng web, sinh test plan và test scenarios. Hỗ trợ 2 mode — PLAN (chỉ test plan) và FULL (test plan + automation skeleton).
playwright
Write or update Playwright E2E tests following project conventions.