test-design

test-design is a command for Claude Code from hollandkevint/thinkhaven. It costs 0 tokens per session (1,180 once invoked), scanned A, original, Apache-2.0.

A command that designs test scenarios for a software story and recommends whether each should be tested at the unit, integration, or end-to-end level.

In plain words
What is it for?
Use it to break down story requirements, choose test levels, classify test priority, and define the data variations and failure cases to cover.
Why use it?
It turns acceptance criteria into a structured testing strategy while accounting for errors, edge cases, priorities, and unnecessary duplication.

Command for Claude Code

Written for Claude Code: installed under .claude/.

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/hollandkevint/thinkhaven/test-design
Clone the repo
git clone --depth 1 https://github.com/hollandkevint/thinkhaven

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 test-design

README.md
[![agentmods](https://agentmods.dev/badge/commands/hollandkevint/thinkhaven/test-design.svg)](https://agentmods.dev/commands/hollandkevint/thinkhaven/test-design)
Your own site
<a href="https://agentmods.dev/commands/hollandkevint/thinkhaven/test-design"><img src="https://agentmods.dev/badge/commands/hollandkevint/thinkhaven/test-design.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,180 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 5.1 $0.00000 $0.01180
Opus 5 $0.00000 $0.00590
Sonnet 5 $0.00000 $0.00236
Haiku 4.5 $0.00000 $0.00118

Measured 5d ago against content hash 15c1261b0e55, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

test-design 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

.claude/commands/BMad/tasks/test-design.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/test-design Task

When this command is used, execute the following task:

test-design

Create comprehensive test scenarios with appropriate test level recommendations for story implementation.

Inputs

required:
  - story_id: '{epic}.{story}' # e.g., "1.3"
  - story_path: '{devStoryLocation}/{epic}.{story}.*.md' # Path from core-config.yaml
  - story_title: '{title}' # If missing, derive from story file H1
  - story_slug: '{slug}' # If missing, derive from title (lowercase, hyphenated)

Purpose

Design a complete test strategy that identifies what to test, at which level (unit/integration/e2e), and why. This ensures efficient test coverage without redundancy while maintaining appropriate test boundaries.

Dependencies

data:
  - test-levels-framework.md # Unit/Integration/E2E decision criteria
  - test-priorities-matrix.md # P0/P1/P2/P3 classification system

Process

1. Analyze Story Requirements

Break down each acceptance criterion into testable scenarios. For each AC:

  • Identify the core functionality to test
  • Determine data variations needed
  • Consider error conditions
  • Note edge cases

2. Apply Test Level Framework

Reference: Load test-levels-framework.md for detailed criteria

Quick rules:

  • Unit: Pure logic, algorithms, calculations
  • Integration: Component interactions, DB operations
  • E2E: Critical user journeys, compliance

3. Assign Priorities

Reference: Load test-priorities-matrix.md for classification

Quick priority assignment:

  • P0: Revenue-critical, security, compliance
  • P1: Core user journeys, frequently used
  • P2: Secondary features, admin functions
  • P3: Nice-to-have, rarely used

4. Design Test Scenarios

For each identified test need, create:

test_scenario:
  id: '{epic}.{story}-{LEVEL}-{SEQ}'
  requirement: 'AC reference'
  priority: P0|P1|P2|P3
  level: unit|integration|e2e
  description: 'What is being tested'
  justification: 'Why this level was chosen'
  mitigates_risks: ['RISK-001'] # If risk profile exists

Read the full file on GitHub · 181 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. 5d ago First seen · 181 lines · 0 tokens per session scan A 15c1261b0e55

Subscribe to this mod's changes

test-design is a command published in the GitHub repository hollandkevint/thinkhaven (5 stars, last pushed 6d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,180 tokens. 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.