Borrowing it
Nothing to install: this file belongs to anhtester/claude-testing-kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/anhtester/claude-testing-kit/main/.claude/commands/generate_manual_testcases_rbt.mdgit 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_manual_testcases_rbt)<a href="https://agentmods.dev/commands/anhtester/claude-testing-kit/generate_manual_testcases_rbt"><img src="https://agentmods.dev/badge/commands/anhtester/claude-testing-kit/generate_manual_testcases_rbt/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/commands/anhtester/claude-testing-kit/generate_manual_testcases_rbt"><img src="https://agentmods.dev/badge/commands/anhtester/claude-testing-kit/generate_manual_testcases_rbt.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 | $0.00024 | $0.01935 |
| Opus 5.5 | $0.00010 | $0.00774 |
| Sonnet 5.5 | $0.00005 | $0.00387 |
| Haiku 4.5 | $0.00002 | $0.00194 |
Grade A, and why
generate_manual_testcases_rbt 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BẮT BUỘC (MANDATORY SKILL): Bạn PHẢI nạp và đọc kỹ nội dung của skill
skills-rbt-manual-testing(tại.claude/skills/skills-rbt-manual-testing/SKILL.md) trước khi bắt đầu thực hiện tác vụ này. Sử dụng Mode FULL RBT của skill. Ngoài ra, tham khảo thêm skillskills-requirements-analyzerđể hiểu cách phân tích giao diện nếu cần.
Command: Sinh Manual Test Cases theo AI-RBT Framework (FULL RBT Mode)
Command này sử dụng Mode FULL RBT của skill skills-rbt-manual-testing — quy trình AI-RBT (AI-Driven Risk-Based Testing) gồm 6 bước tuần tự để sinh manual test cases từ tài liệu yêu cầu.
[!NOTE] Luồng này dành cho Claude Code (slash command). Agent thực hiện theo hướng dẫn trong skill, KHÔNG cần đọc file prompt.txt. Nếu QA team muốn dùng prompt chi tiết hơn (ChatGPT/Claude Web), hãy copy-paste từng bước từ
plans/manual/01-06/prompt.txt.
⚠️ Nguyên tắc thực thi
- Mode: FULL RBT (6 bước tuần tự)
- BẮT BUỘC chạy tuần tự từng bước, KHÔNG gộp nhiều bước
- PHẢI dừng lại chờ user phản hồi tại Bước 2 (Q&A) và Bước 4 (Review Scenarios)
- Nếu user chưa cung cấp requirements, hỏi user cung cấp trước khi bắt đầu
- Tất cả output bằng Tiếng Việt
Các bước thực hiện
Thực hiện theo hướng dẫn chi tiết trong skill skills-rbt-manual-testing → phần Mode 2: FULL RBT.
Bước 1: Khởi tạo ngữ cảnh (Context & Role-play)
- Yêu cầu user cung cấp: tên dự án, mô tả hệ thống, mục tiêu MVP, tài liệu yêu cầu
- Đọc kỹ tài liệu, xác nhận hiểu bối cảnh
- Chờ user xác nhận → sang Bước 2
Bước 2: Phân tích yêu cầu (Analysis & QnA)
- Xác định Happy Path, Alternate Paths, Exception Paths
- Phát hiện Ambiguities (thiếu sót, mâu thuẫn, chưa rõ ràng)
- Đặt câu hỏi Q&A có đánh số (Q1, Q2...) cho user/PO/BA, kèm ngữ cảnh + assumption
- DỪNG LẠI — Chờ user trả lời câu hỏi → sang Bước 3
Bước 3: Phân rã hệ thống (Decomposition)
- Chia tính năng thành Modules / Sub-modules
- Mô tả chức năng từng Module + Dependencies giữa chúng
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 · 88 lines · 24 tokens per session scan A 2bffc2fbebee
generate_manual_testcases_rbt is a command published in the GitHub repository anhtester/claude-testing-kit (61 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 1,935 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 2026-08-30.
Other commands, from other repositories
case
A command for registering and managing Testany cases. A case is a reusable package containing one automated testing step, its metadata, and its scripts.
test-reviewer
A review process for an independent test package, checking whether its tests cover the requirements, can be run, and have supporting evidence.
test-spec-writer
A process for turning approved product and technical documents into a complete set of software test cases. It produces a traceability matrix, which links requirements and risks to tests, plus instructions for running and automating them.
test-strategy-reviewer
A command that reviews a software test strategy before detailed design and test specifications begin. It checks the planned tests, environments, dependencies, automation, and release rules.
case-writing
A command that turns traditional test scenarios into Testany platform cases, including metadata, scripts, and uploadable ZIP packages. It supports API, user-interface, end-to-end, Java, and Postman-based tests.
execution
A command for observing and managing Testany executions, meaning individual pipeline runs after they have started. It can show progress and results, search run history, refresh status, and cancel runs that have not started.