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/claude-testing-kit/generate_automation_from_testcasesgit clone --depth 1 https://github.com/anhtester/claude-testing-kitWrote 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/claude-testing-kit/generate_automation_from_testcases)<a href="https://agentmods.dev/commands/anhtester/claude-testing-kit/generate_automation_from_testcases"><img src="https://agentmods.dev/badge/commands/anhtester/claude-testing-kit/generate_automation_from_testcases.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 | $0.00024 | $0.03863 |
| Opus 5 | $0.00012 | $0.01931 |
| Sonnet 5 | $0.00005 | $0.00773 |
| Haiku 4.5 | $0.00002 | $0.00386 |
Grade A, and why
generate_automation_from_testcases 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 5d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- generate_automation_from_testcases — 89% identical, 48 lines differ
How it starts
The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow: Sinh Automation Scripts từ Manual Test Cases
BẮT BUỘC (MANDATORY SKILLS): Bạn PHẢI nạp và đọc kỹ nội dung các skills sau trước khi bắt đầu:
skills-qa-automation-engineer(.claude/skills/skills-qa-automation-engineer/SKILL.md) — Quy tắc automation chung + workflow routingskills-ui-debug-agent(.claude/skills/skills-ui-debug-agent/SKILL.md) — Inspect DOM, thu thập locatorsskills-smart-locator-agent(.claude/skills/skills-smart-locator-agent/SKILL.md) — Sinh locator ổn địnhskills-test-data-generator(.claude/skills/skills-test-data-generator/SKILL.md) — Sinh test data unique, traceable
Workflow này giúp agent đọc file manual test cases do user cung cấp, tự mở browser inspect UI, thu thập locators thực tế, sinh automation scripts hoàn chỉnh (POM + Test), chạy test và tự sửa lỗi cho đến khi PASS.
⚠️ Nguyên tắc thực thi
- Vai trò: Agent đóng vai Senior Automation Engineer — tuân thủ Clean Code + POM
- Tất cả output bằng Tiếng Việt
- TUYỆT ĐỐI KHÔNG ĐOÁN locator — phải inspect DOM thực tế bằng MCP browser tools
- Desktop viewport 1920×1080 cho tất cả UI debugging
- ⚠️ Rule E3 (CRITICAL): Khi test FAIL → tự đọc log → phân tích → sửa code → chạy lại. CẤM hỏi user trong quá trình fix lỗi. Chỉ hỏi khi gặp business rule mâu thuẫn hoặc hết 5 vòng auto-heal
- Artifact
task.md— PHẢI tạo để theo dõi tiến độ 6 bước
Workflow này khác gì generate_automation_from_ui_flow?
from_testcases (workflow này) |
from_ui_flow |
|
|---|---|---|
| Input | File manual test cases có cấu trúc (MD/Excel/JSON) | Mô tả UI steps bằng lời hoặc chỉ URL |
| Đã có TC | ✅ Có sẵn — đọc và convert | ❌ Chưa có — agent tự khám phá |
| Approach | Đọc TC → inspect UI verify → sinh code | Chạy thật trên browser → thu thập → sinh code |
Input cần thu thập
| Input | Cách lấy | Độ ưu tiên |
|---|---|---|
| File test cases (MD/Excel/JSON/URL) | User cung cấp path hoặc URL | ⭐ Bắt buộc |
| URL ứng dụng | User cung cấp hoặc trong TC | ⭐ Bắt buộc |
| Credentials (nếu cần login) | User cung cấp hoặc dùng fixture sẵn | Tùy chọn |
| Tech stack | User chỉ định hoặc detect từ project | Tùy chọn |
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.
- 5d ago First seen · 320 lines · 24 tokens per session scan A 7d6a36af6e04
generate_automation_from_testcases is a command published in the GitHub repository anhtester/claude-testing-kit (50 stars, last pushed 27d ago), licensed MIT. It adds 24 tokens to every session and 3,863 once invoked, about $0.0001 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 commands, from other repositories
generate_automation_from_testcases
Convert manual test cases into automation scripts autonomously using the 6-step AI-RBT Framework via Antigravity 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.
expect
Diff-aware AI browser testing — reads the git diff, maps changes to affected pages via the route map, generates a targeted test plan, and executes it via agent-browser (Rust daemon + CDP, ARIA-tree-first) with pass/fail reporting. Use when testing UI changes, verifying PRs before merge, or running regression checks on…
auto-verify
프론트엔드 UX 검증 — Playwright 기반 비주얼 검증을 실행합니다.
buildable-preview
Render the running prototype in a headless browser, screenshot it, and catch runtime/visual errors.
record
Record a browser walkthrough of a URL using Antigravity (agy). Generates .webm video, screenshots, and a report. Auto-converts to MP4 if ffmpeg is available.