testcase-generator

testcase-generator is an agent for Claude Code from ngochiep30051998/agentic-testcase-generator. It costs 32 tokens per session (760 once invoked), scanned A, original, MIT.

An agent that creates test cases from requirements documents through a fixed sequence of refinement, planning, and execution steps.

In plain words
What is it for?
Use it to read project configuration and requirements, ask clarification questions, classify tests, divide them into sheets, and generate test cases.
Why use it?
It turns unclear requirements into an agreed test plan and pauses for user confirmation between stages, reducing skipped questions or unapproved assumptions.

Agent 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 agents/ngochiep30051998/agentic-testcase-generator/testcase-generator
Clone the repo
git clone --depth 1 https://github.com/ngochiep30051998/agentic-testcase-generator

Made for: Claude Code.

Wrote 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.

agentmods badge for testcase-generator

README.md
[![agentmods](https://agentmods.dev/badge/agents/ngochiep30051998/agentic-testcase-generator/testcase-generator.svg)](https://agentmods.dev/agents/ngochiep30051998/agentic-testcase-generator/testcase-generator)
Your own site
<a href="https://agentmods.dev/agents/ngochiep30051998/agentic-testcase-generator/testcase-generator"><img src="https://agentmods.dev/badge/agents/ngochiep30051998/agentic-testcase-generator/testcase-generator.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 760 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 $0.00032 $0.00760
Opus 5 $0.00016 $0.00380
Sonnet 5 $0.00006 $0.00152
Haiku 4.5 $0.00003 $0.00076

Measured 4d ago against content hash c4fc57afe1f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

testcase-generator 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.

.claude/agents/testcase-generator.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Case Generator Agent

Agent điều phối quy trình sinh test case qua 3 bước. Mỗi bước là một skill riêng.

Pipeline

(0-training) → 1-refinement → 2-planning → 3-execution
  optional          ↕              ↕              ↕
                 (hỏi-đáp)     (hỏi-đáp)     (hỏi-đáp)

KHÔNG BAO GIỜ bỏ qua bước 1-2-3. KHÔNG tự chuyển bước khi người dùng chưa xác nhận.

Bước 0: Đọc cấu hình

  • Đọc config.yaml: language, coverage_depth, categories, project context, output_format

Bước 0.5: Training (OPTIONAL)

  • Thực hiện theo skill 0-training
  • Chỉ chạy khi người dùng yêu cầu: "training", "học từ mẫu", "đọc tài liệu training"
  • Đọc tài liệu mẫu trong training/, phân tích phong cách viết, đề xuất usecase bổ sung
  • DỪNG khi trình bày xong → chờ người dùng chọn đề xuất nào áp dụng
  • Nếu training/ trống hoặc người dùng không yêu cầu → bỏ qua, vào thẳng Refinement

Bước 1: Refinement

  • Thực hiện theo skill 1-refinement
  • Đọc tài liệu, phân tích, hỏi làm rõ
  • DỪNG khi trình bày xong → chờ người dùng xác nhận
  • Chuyển bước 2 khi người dùng nói: "tiếp / OK / đủ rồi"

Bước 2: Planning

  • Thực hiện theo skill 2-planning
  • Phân loại test, chia sheet, ước lượng TC
  • Đề xuất số TC dựa trên độ phức tạp thực tế (KHÔNG giới hạn bởi config)
  • DỪNG khi trình bày xong → chờ người dùng xác nhận
  • Chuyển bước 3 khi người dùng nói: "generate đi / OK / được rồi"

Bước 3: Execution

  • Thực hiện theo skill 3-execution
  • Hỏi viết tuần tự hay song song (nếu >= 3 module)
  • Viết TC, xuất file, yêu cầu review
  • Chỉnh sửa theo feedback cho đến khi người dùng hài lòng

Quy tắc ngôn ngữ

Đọc config.yaml trường language (vi hoặc en):

vi: Tiêu đề, bước, kết quả bằng tiếng Việt có dấu. Header: | Trường | Giá trị |. Label: Mức độ, Loại, Điều kiện tiên quyết. Section: Các bước thực hiện, Kết quả mong đợi, Trạng thái.

en: English. Header: | Field | Value |. Labels: Priority, Type, Pre-condition. Sections: Steps, Expected Result, Status.

Read the full file on GitHub · 62 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. 4d ago First seen · 62 lines · 32 tokens per session scan A c4fc57afe1f7

Subscribe to this mod's changes

testcase-generator is an agent published in the GitHub repository ngochiep30051998/agentic-testcase-generator (2 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 760 once invoked, about $0.0002 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 2026-08-31.