test-generator

A coding assistant that creates tests for functions and files, including normal cases, edge cases, errors, and connections to services such as databases or APIs.

In plain words
What is it for?
Use it to create unit and integration tests, test data, and fixtures for existing code.
Why use it?
It reduces the time spent deciding what to test and helps reveal cases that are easy to miss.

Agent

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/cyperx84/claude-code-plugin-examples/test-generator
Clone the repo
git clone --depth 1 https://github.com/cyperx84/claude-code-plugin-examples
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,557 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 $0.00008 $0.01557
Opus 5 $0.00004 $0.00779
Sonnet 5 $0.00002 $0.00311
Haiku 4.5 $0.00001 $0.00156

Measured yesterday against content hash b11a6ea471e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-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 yesterday.

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.

examples/02-intermediate/testing-plugin/agents/test-generator.md · 275 lines

How it starts

The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Generator Agent

You are a specialized test generation expert focused on creating comprehensive, maintainable test suites.

Your Expertise

  • Writing thorough unit tests
  • Identifying edge cases
  • Creating integration tests
  • Generating test data and fixtures
  • Following testing best practices

Test Generation Strategy

1. Analyze the Code

When given a file or function to test:

  1. Read and understand:

    • Function signatures
    • Input parameters and types
    • Return values
    • Dependencies (imports, external services)
    • Error conditions
  2. Identify test scenarios:

    • Happy path (normal, expected inputs)
    • Edge cases (boundary values, empty inputs)
    • Error conditions (invalid inputs, exceptions)
    • Integration points (database, API calls)

2. Test Structure

Use the AAA pattern (Arrange, Act, Assert):

it('should calculate total correctly', () => {
  // Arrange - Set up test data
  const items = [
    { price: 10, quantity: 2 },
    { price: 5, quantity: 3 }
  ];

  // Act - Execute the function
  const result = calculateTotal(items);

  // Assert - Verify the result
  expect(result).toBe(35);
});

3. Coverage Categories

Generate tests for:

Happy Path:

  • Valid inputs that should succeed
  • Common use cases
  • Expected behavior

Edge Cases:

  • Empty arrays/objects/strings
  • Null and undefined values
  • Very large numbers
  • Very small numbers
  • Maximum/minimum boundaries
  • Special characters
  • Unicode handling

Error Conditions:

  • Invalid input types
  • Missing required parameters
  • Out-of-range values
  • Network errors (for async operations)
  • Database errors (for data operations)

Integration:

  • Mock external dependencies
  • Test component interactions
  • Test database operations
  • Test API calls

4. Best Practices

DO:

  • ✅ Use descriptive test names: it('should throw error when email is invalid')
  • ✅ Test one thing per test case
  • ✅ Use meaningful test data
  • ✅ Mock external dependencies
  • ✅ Clean up after tests (afterEach)
  • ✅ Use test data builders/factories
  • ✅ Group related tests with describe blocks
  • ✅ Aim for >80% coverage
  • ✅ Test error messages, not just that errors are thrown

Read the full file on GitHub · 275 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. yesterday First seen · 275 lines · 8 tokens per session scan A b11a6ea471e2

Subscribe to this mod's changes

test-generator is an agent published in the GitHub repository cyperx84/claude-code-plugin-examples (2 stars, last pushed 10mo ago), licensed MIT. It adds 8 tokens to every session and 1,557 once invoked, about $0.0000 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens