generate_combinatorial_test_data

A test-data generation workflow for multi-step combinations across connected application modules. It can create structured data from an existing combination matrix or run the combinations through a browser.

In plain words
What is it for?
Use it to produce JSON, CSV, or Markdown test data for combinations, or prepare data for later manual test cases and automation.
Why use it?
It turns abstract test combinations into usable inputs without requiring every dataset to be assembled manually.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/anhtester/claude-testing-kit/generate_combinatorial_test_data
Clone the repo
git clone --depth 1 https://github.com/anhtester/claude-testing-kit

Made for: Claude Code.

Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,167 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00027 $0.04167
Opus 5 $0.00014 $0.02083
Sonnet 5 $0.00005 $0.00833
Haiku 4.5 $0.00003 $0.00417

Measured 2d ago against content hash 3fd14204cc20, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

generate_combinatorial_test_data 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.

.claude/commands/generate_combinatorial_test_data.md · 376 lines

How it starts

The opening of the file, as written. The whole thing — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/generate_combinatorial_test_data — Sinh Test Data Cho Ma Trận Kết Hợp

Dùng khi: Đã có ma trận kết hợp (từ /generate_cross_module_test_plan) và cần tạo test data thực tế bằng cách chạy qua nhiều modules trên browser, hoặc sinh bộ data có cấu trúc sẵn sàng cho automation.

BẮT BUỘC (MANDATORY): Trước khi bắt đầu, PHẢI nạp và đọc kỹ:

  • Skill: .claude/skills/skills-test-data-generator/SKILL.md — Quy tắc sinh data (xem phần Multi-Step Pipeline)
  • Skill: .claude/skills/skills-ui-debug-agent/SKILL.md — Inspect DOM khi chạy browser
  • Workflow: .claude/commands/generate_cross_module_test_plan.md — Hiểu cấu trúc ma trận đầu vào

Mối quan hệ với các workflows khác

/generate_cross_module_test_plan     →  Ma trận kết hợp (input)
        ↓
/generate_combinatorial_test_data    →  Bộ test data (workflow này)
        ↓
/generate_manual_testcases_rbt       →  Test cases chi tiết
        ↓
/generate_automation_from_testcases  →  Automation scripts

2 Modes

Mode Khi nào dùng Output
GENERATE (mặc định) Sinh bộ data có cấu trúc từ ma trận — KHÔNG chạy browser File JSON/CSV/Markdown với data cho mỗi bộ kết hợp
PIPELINE (lựa chọn cuối) Bắt buộc phải đi qua UI mới tạo được data Data thật đã tạo + IDs + screenshots evidence

Agent tự chọn mode:

  • User nói "sinh data", "generate data" → GENERATE
  • User nói "tạo data trên hệ thống", "chạy tạo data", "setup data thật" → xem Thứ tự ưu tiên bên dưới
  • Nếu không rõ → hỏi user

⚠️ Thứ tự ưu tiên khi cần data THẬT trên hệ thống

PIPELINE (drive browser qua N modules × N combos) là cách đắt nhất và kém ổn định nhất. Trước khi chọn PIPELINE, agent PHẢI hỏi user theo thứ tự:

# Cách Khi nào dùng Chi phí / Rủi ro
1 Seed qua API Hệ thống có API tạo record ⭐ Rẻ, nhanh, ổn định — luôn ưu tiên
2 Seed qua DB / script Có quyền truy cập DB test Rẻ, nhanh — cẩn thận ràng buộc toàn vẹn
3 Import file Hệ thống hỗ trợ import Excel/CSV Trung bình
4 PIPELINE (browser) 3 cách trên không khả thi — nghiệp vụ chỉ tồn tại ở tầng UI ⚠️ Chậm, dễ vỡ, để lại rác data

Read the full file on GitHub · 376 lines

Changes

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.

  1. 2d ago First seen · 376 lines · 27 tokens per session scan A 3fd14204cc20

Subscribe to this mod's changes

generate_combinatorial_test_data is a command published in the GitHub repository anhtester/claude-testing-kit (49 stars, last pushed 24d ago), licensed MIT. It adds 27 tokens to every session and 4,167 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.