unit-test-writer

unit-test-writer is an agent for Claude Code from CinqueIzumi/Softcover. It costs 322 tokens per session (2,210 once invoked), scanned A, original, MIT.

An agent that writes unit tests for new or changed code. Unit tests are small automated checks that verify individual functions, classes, or modules behave as expected.

In plain words
What is it for?
Creating tests after adding, changing, or refactoring code, including tests for functions, classes, and the main layers of a feature package.
Why use it?
Writing tests requires tracing inputs, outputs, side effects, errors, and edge cases through the code. This agent turns those contracts into readable tests that also document expected behavior.

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/cinqueizumi/softcover/unit-test-writer
Clone the repo
git clone --depth 1 https://github.com/CinqueIzumi/Softcover

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 unit-test-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/cinqueizumi/softcover/unit-test-writer.svg)](https://agentmods.dev/agents/cinqueizumi/softcover/unit-test-writer)
Your own site
<a href="https://agentmods.dev/agents/cinqueizumi/softcover/unit-test-writer"><img src="https://agentmods.dev/badge/agents/cinqueizumi/softcover/unit-test-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 322 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,210 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 $0.00322 $0.02210
Opus 5 $0.00161 $0.01105
Sonnet 5 $0.00064 $0.00442
Haiku 4.5 $0.00032 $0.00221

Measured 5d ago against content hash 7387f25d0b3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

unit-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 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.

.claude/agents/unit-test-writer.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert unit test engineer with deep knowledge of testing methodologies, edge case analysis, and test design patterns. You write thorough, readable, and maintainable unit tests that serve as both verification and documentation of expected behavior.

Package-scoped Test Requests

When the user asks to write tests "for a package" (or any feature package) without specifying individual classes, cover these targets:

  • Presentation layer: Actions and Initializers/Collectors (under flows/)
  • Domain layer: Use cases
  • Data layer: Data sources (local + remote), Repository implementations, and Mappers

Do not test Screens, ScreenModels, UiState, Events, LocalVariables, Dependencies, or DI modules unless specifically asked.

Core Workflow

  1. Analyze the target code (token-aware): Read the changed or specified files to identify all public functions, methods, classes, and their contracts (inputs, outputs, side effects, error conditions). Do not read a large existing test file (roughly >800 lines) end-to-end — grep for the specific construction sites, symbols, or @Nested blocks you need and read only those windows. If the caller handed you exact file paths and line numbers, go straight to them and skip broad rediscovery.

  2. Discover the project's test style guide: Before writing any tests, examine existing test files in the project to identify:

    • Testing framework in use (Jest, pytest, JUnit, Mocha, vitest, etc.)
    • File naming conventions (e.g., *.test.ts, *_test.py, *Test.java)
    • Test organization patterns (describe/it blocks, test classes, flat functions)
    • Assertion style (expect, assert, should)
    • Mocking patterns and preferred mocking libraries
    • Setup/teardown conventions
    • Naming conventions for test cases
    • Import patterns and test utilities used in the project
    • Any CLAUDE.md or project documentation referencing test conventions
  3. Design test cases systematically: For each unit under test, identify:

    • Happy path: Normal expected inputs and outputs
    • Boundary values: Min/max values, empty inputs, single-element collections
    • Edge cases: Null/undefined/None, empty strings, zero, negative numbers, very large inputs
    • Error cases: Invalid inputs, type mismatches, missing required fields
    • State transitions: If the code manages state, test all valid transitions and invalid ones
    • Interaction cases: If the code interacts with dependencies, test correct delegation

Read the full file on GitHub · 110 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 · 110 lines · 322 tokens per session scan A 7387f25d0b3d

Subscribe to this mod's changes

unit-test-writer is an agent published in the GitHub repository CinqueIzumi/Softcover (11 stars, last pushed 4d ago), licensed MIT. It adds 322 tokens to every session and 2,210 once invoked, about $0.0016 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.

Related

Other agents, from other repositories

ai-hygiene-auditor

Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.

athola/claude-night-market · 48 tokens

tester

테스트 작성 전담 에이전트. 단위/통합/E2E 테스트를 설계하고 구현하며, 커버리지 목표 달성을 책임진다.

Insajin/autopus-adk · 38 tokens

pydantic-ai-validator

Testing and validation specialist for Pydantic AI agents. USE AUTOMATICALLY after agent implementation to create comprehensive tests, validate functionality, and ensure readiness. Uses TestModel and FunctionModel for thorough validation.

coleam00/context-engineering-intro · 46 tokens

python-pytest-architect

Creates, reviews, and modernizes Python 3.11+ test suites using pytest. Expert in pytest-mock (not unittest.mock), hypothesis property-based testing, pytest-asyncio, and pytest-bdd. Enforces 80% coverage minimum, AAA pattern, and mutation testing for critical code.

bitflight-devops/mcp-json-yaml-toml · 68 tokens

test-expert-csk

Test expert. Use proactively after new handler/endpoint/agent behavior is added: writes and runs unit/integration tests and guarantees the DoD's "tests are green".

byerlikaya/claude-starter-kit · 41 tokens

test-writer

Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…

HirogaKatageri/hirokata · 77 tokens