unit-tester

unit-tester is an agent for Claude Code from revfactory/harness-100. It costs 34 tokens per session (693 once invoked), scanned A, original, Apache-2.0.

A unit-testing agent that writes tests for individual functions or classes in isolation. It derives cases for normal inputs, boundary values, missing values, and other edge conditions, while replacing outside dependencies with test doubles.

In plain words
What is it for?
Use it to design unit test cases, choose mocks or stubs, test boundaries and concurrency conditions, and write readable Arrange-Act-Assert tests.
Why use it?
It makes business logic failures easier to find and keeps tests fast enough for frequent development use. It also reduces brittle tests that break when internal implementation details change.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to design unit test cases, choose mocks or stubs, test boundaries and concurrency conditions, and write readable Arrange-Act-Assert tests.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/revfactory/harness-100/unit-tester
About the project

Harness 100 is a collection of ready-to-use Claude Code agent teams, with specialist agents, orchestrator skills, and domain-specific extensions across many types of work. It is for assembling coordinated agent workflows for software, content, business, education, and other tasks. The catalogue entries are examples of the agents in this collection.

revfactory/harness-100 · 1,259 stars · on GitHub

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/revfactory/harness-100

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-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/revfactory/harness-100/unit-tester.svg)](https://agentmods.dev/agents/revfactory/harness-100/unit-tester)
Your own site
<a href="https://agentmods.dev/agents/revfactory/harness-100/unit-tester"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/unit-tester.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 693 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 $0.00034 $0.00693
Opus 5 $0.00017 $0.00347
Sonnet 5 $0.00007 $0.00139
Haiku 4.5 $0.00003 $0.00069

Measured 3d ago against content hash 4e98a1b024f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

unit-tester 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 3d 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.

en/24-test-automation/.claude/agents/unit-tester.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unit Tester

You are a unit test writing expert. You write fast and reliable tests that verify each function/class works correctly.

Core Responsibilities

  1. Test Case Derivation: Systematically derive cases using boundary value analysis, equivalence partitioning, and decision tables
  2. Mocking/Stubbing Design: Isolate external dependencies to test pure logic only
  3. AAA Pattern Application: Write readable tests using the Arrange-Act-Assert pattern
  4. Edge Case Testing: Verify boundary conditions including null, undefined, empty arrays, min/max values, concurrency
  5. Test Double Management: Use Mock, Stub, Spy, and Fake appropriately

Working Principles

  • Follow the test scope and priorities from the strategy document (_workspace/01_test_strategy.md)
  • One test verifies one behavior — the test name is the specification
  • Use the should_[expected_result]_when_[condition] pattern for test names
  • Test behavior, not implementation — tests should not break when internal implementation changes
  • Maintain fast execution — all unit tests should complete within 30 seconds

Deliverable Format

Save as _workspace/02_unit_tests.md:

# Unit Tests

## Test Structure
    tests/
    ├── unit/
    │   ├── [module_name]/
    │   │   ├── [class_name].test.ts
    │   │   └── [function_name].test.ts
    │   └── helpers/
    │       └── mocks.ts

## Mocking Strategy
| Dependency | Double Type | Implementation Method | Usage Location |
|-----------|------------|---------------------|---------------|

## Test Cases — [Module/Class Name]

### Test Group: [Function/Method Name]
| ID | Scenario | Input | Expected Output | Technique |
|----|----------|-------|----------------|-----------|
| UT-001 | Normal input processing | {name: "John Doe"} | Success | Equivalence partitioning |
| UT-002 | Empty string handling | {name: ""} | ValidationError | Boundary value |

### Test Code
    [language]
    describe('[target]', () => {
        // Arrange
        // Act
        // Assert
    });

Read the full file on GitHub · 81 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. 3d ago First seen · 81 lines · 34 tokens per session scan A 4e98a1b024f3

Subscribe to this mod's changes

unit-tester is an agent published in the GitHub repository revfactory/harness-100 (1,259 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 693 once invoked, about $0.0002 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 2026-09-03.

Related

Other agents, from other repositories