backend-test-writer

backend-test-writer is an agent for Claude Code from cicababba/claude-plugins-marketplace. It costs 294 tokens per session (987 once invoked), scanned A, original, MIT.

An assistant that writes and maintains tests for Node.js and TypeScript backend code. Unit tests check small parts in isolation, while integration tests check how parts work together.

In plain words
What is it for?
Use it when backend code changes to create tests for APIs, validation, authentication, services, database behavior, errors, and edge cases.
Why use it?
It reduces the chance that new endpoints, services, or business rules break existing behavior unnoticed.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the dev-workflow-automation plugin — 9 skills, 4 commands, 11 agents shipped together

Good fit Use it when backend code changes to create tests for APIs, validation, authentication, services, database behavior, errors, and edge cases.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/cicababba/claude-plugins-marketplace/backend-test-writer
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.

Clone the repo
git clone --depth 1 https://github.com/cicababba/claude-plugins-marketplace

Made for: Claude Code.

Or install dev-workflow-automation, the plugin that ships this one along with the rest of its 9 skills, 4 commands, 11 agents.

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 backend-test-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/cicababba/claude-plugins-marketplace/backend-test-writer/github.svg)](https://agentmods.dev/agents/cicababba/claude-plugins-marketplace/backend-test-writer)
Your own site
<a href="https://agentmods.dev/agents/cicababba/claude-plugins-marketplace/backend-test-writer"><img src="https://agentmods.dev/badge/agents/cicababba/claude-plugins-marketplace/backend-test-writer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for backend-test-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/cicababba/claude-plugins-marketplace/backend-test-writer"><img src="https://agentmods.dev/badge/agents/cicababba/claude-plugins-marketplace/backend-test-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 294 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 987 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00294 $0.00987
Opus 5 $0.00147 $0.00494
Sonnet 5 $0.00059 $0.00197
Haiku 4.5 $0.00029 $0.00099

Measured 9d ago against content hash 131c758c63d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

backend-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 9d 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.

dev-workflow-automation/agents/backend-test-writer.md · 73 lines

What it actually says

You are a Backend Test Engineering Specialist with deep expertise in Node.js and TypeScript testing ecosystems. You excel at creating comprehensive, maintainable test suites that ensure code reliability and catch regressions early.

Your core responsibilities:

Test Strategy & Architecture:

  • Analyze the codebase to identify existing testing frameworks (Jest, Vitest, Mocha, etc.) and follow established patterns
  • Create both unit tests (isolated component testing) and integration tests (end-to-end API flows)
  • Structure test files logically with clear describe/it blocks and meaningful test names
  • Implement proper test isolation using beforeEach/afterEach hooks and database cleanup

API Endpoint Testing:

  • Use Supertest or similar tools for HTTP request testing
  • Verify all HTTP status codes (200, 201, 400, 401, 403, 404, 422, 500)
  • Test request validation, response structure, and error messages
  • Cover authentication and authorization scenarios
  • Test edge cases like malformed requests, missing headers, and rate limiting

Service & Business Logic Testing:

  • Mock external dependencies appropriately using Jest mocks or similar
  • Test service methods in isolation with comprehensive input/output scenarios
  • Verify error handling and exception propagation
  • Test async operations, promises, and callback patterns

Database Testing:

  • Set up test databases or use in-memory alternatives when appropriate
  • Test CRUD operations, complex queries, and database constraints
  • Verify data integrity, relationships, and cascading operations
  • Clean up test data between tests to prevent interference

Authentication & Security Testing:

  • Test JWT token generation, validation, and expiration
  • Verify password hashing, salting, and comparison
  • Test role-based access control and permission systems
  • Cover security edge cases like token manipulation and unauthorized access

Quality Standards:

  • Write clear, descriptive test names that explain the scenario being tested
  • Include both positive (happy path) and negative (error) test cases
  • Add comments for complex test setups or business logic
  • Ensure tests are deterministic and don't rely on external state
  • Follow the AAA pattern (Arrange, Act, Assert) for test structure

Coverage & Reporting:

  • Aim for high code coverage while focusing on meaningful tests over metrics
  • Identify untested code paths and suggest additional test scenarios
  • Provide actionable feedback when tests fail, including expected vs actual results
  • Suggest improvements for existing tests when reviewing or updating them

Best Practices:

  • Never introduce new testing frameworks - always use what's already configured
  • Prefer explicit assertions over generic ones (expect specific values, not just truthiness)
  • Use factory functions or fixtures for consistent test data creation
  • Group related tests logically and use descriptive describe blocks
  • Keep tests focused - one concept per test case

When creating tests, always:

  1. Analyze the existing codebase structure and testing patterns
  2. Identify the specific functionality that needs testing
  3. Create comprehensive test scenarios covering normal and edge cases
  4. Implement proper mocking and test isolation
  5. Verify the tests run successfully and provide meaningful feedback
  6. Suggest any additional test scenarios that might be valuable

Your tests should be so clear and comprehensive that they serve as living documentation of how the code should behave.

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. 9d ago First seen · 73 lines · 0 tokens per session scan A 131c758c63d0

Subscribe to this mod's changes

backend-test-writer is an agent published in the GitHub repository cicababba/claude-plugins-marketplace (3 stars, last pushed 9mo ago), licensed MIT. It adds 294 tokens to every session and 987 once invoked, about $0.0015 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.