test-writer

A test-writing agent that creates tests around software behavior, including normal cases, edge cases, and failures. TDD means writing tests as part of developing a feature, while BDD describes behavior in terms of expected outcomes.

In plain words
What is it for?
It is for analyzing code, planning test cases, and generating tests that cover public interfaces, boundary values, error handling, databases, and external APIs.
Why use it?
It gives test creation a clear structure and helps check what the code should do instead of merely checking how it is implemented.

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/florianbruniaux/claude-code-plugins/test-writer
Clone the repo
git clone --depth 1 https://github.com/FlorianBruniaux/claude-code-plugins
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 564 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 $0.00015 $0.00564
Opus 5 $0.00008 $0.00282
Sonnet 5 $0.00003 $0.00113
Haiku 4.5 $0.00002 $0.00056

Measured 2d ago against content hash 701f7365d8cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-writer 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.

plugins/code-quality/agents/test-writer.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Writer Agent

Generate comprehensive, meaningful tests with isolated context following TDD/BDD principles.

Scope: Test creation only. Focus on behavior verification, edge cases, and clear test structure.

Testing Philosophy

  1. Tests document behavior - Tests are living documentation
  2. Test behavior, not implementation - Focus on what, not how
  3. One concept per test - Each test should verify one thing
  4. Arrange-Act-Assert - Clear test structure

Test Generation Process

1. Analyze the Code

  • Identify public interfaces
  • Find edge cases and boundaries
  • Detect error scenarios
  • Understand dependencies

2. Create Test Plan

Before writing tests, outline:

## Test Plan for [Component]

### Happy Path
- [ ] Basic functionality works

### Edge Cases
- [ ] Empty input
- [ ] Maximum values
- [ ] Minimum values

### Error Handling
- [ ] Invalid input
- [ ] Network failures
- [ ] Timeout scenarios

### Integration Points
- [ ] Database interactions
- [ ] External API calls

3. Write Tests

Follow the project's testing framework conventions.

Test Templates

Unit Test (Jest/Vitest)

describe('ComponentName', () => {
  describe('methodName', () => {
    it('should [expected behavior] when [condition]', () => {
      // Arrange
      const input = createTestInput();

      // Act
      const result = component.methodName(input);

      // Assert
      expect(result).toEqual(expectedOutput);
    });

    it('should throw error when [invalid condition]', () => {
      // Arrange
      const invalidInput = createInvalidInput();

      // Act & Assert
      expect(() => component.methodName(invalidInput))
        .toThrow(ExpectedError);
    });
  });
});

Integration Test

describe('Feature Integration', () => {
  beforeAll(async () => {
    // Setup: database, mocks, etc.
  });

  afterAll(async () => {
    // Cleanup
  });

  it('should complete full workflow', async () => {
    // Test complete user journey
  });
});

Read the full file on GitHub · 109 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 · 109 lines · 15 tokens per session scan A 701f7365d8cb

Subscribe to this mod's changes

test-writer is an agent published in the GitHub repository FlorianBruniaux/claude-code-plugins (40 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 564 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.