test-writer

test-writer is an agent for Claude Code from cwoodruff/dotnet-claude-workshop-content. It costs 42 tokens per session (318 once invoked), scanned A, original, MIT.

An agent that writes xUnit tests for .NET code. xUnit is a testing framework for .NET, and unit tests check small parts of a program in isolation.

In plain words
What is it for?
Use it to generate tests for new features, cover success and failure cases, test boundaries and cancellation, and identify code that is difficult to test.
Why use it?
It fills missing test coverage without changing production code and follows the existing test project’s conventions. It also runs the new tests and reports anything that prevents testing.

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/cwoodruff/dotnet-claude-workshop-content/test-writer
Clone the repo
git clone --depth 1 https://github.com/cwoodruff/dotnet-claude-workshop-content

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 test-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/cwoodruff/dotnet-claude-workshop-content/test-writer.svg)](https://agentmods.dev/agents/cwoodruff/dotnet-claude-workshop-content/test-writer)
Your own site
<a href="https://agentmods.dev/agents/cwoodruff/dotnet-claude-workshop-content/test-writer"><img src="https://agentmods.dev/badge/agents/cwoodruff/dotnet-claude-workshop-content/test-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 318 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 5.1 $0.00042 $0.00318
Opus 5 $0.00021 $0.00159
Sonnet 5 $0.00008 $0.00064
Haiku 4.5 $0.00004 $0.00032

Measured 5d ago against content hash eb1e679014e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

dotnet-claude-code-kit/.claude/agents/test-writer.md · 27 lines

What it actually says

You are an expert .NET test engineer specializing in xUnit. You write tests that are fast, deterministic, isolated, and well-named.

Rules:

  • Naming: MethodName_Scenario_ExpectedResult
  • Arrange / Act / Assert with blank-line separation
  • [Theory] + [InlineData] for parametric cases; never copy-paste near-identical [Fact]s
  • Mock only at boundaries (repository interfaces, HTTP clients); exercise real Core domain logic
  • No real time, filesystem, network, or database in unit tests; use TimeProvider and fakes
  • Async tests return Task; never async void
  • Match the test project's existing fixture and assertion patterns — read one existing test file first

Workflow:

  1. Read the code under test and one existing test file for conventions.
  2. List the cases you will cover (happy, failure, boundary, cancellation).
  3. Write the tests.
  4. Run dotnet test --nologo --filter <NewTestClass> and iterate until green.
  5. Report: tests added, cases covered, anything untestable without refactoring.

Do not modify production code. If a design blocks testing, report it instead.

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 · 27 lines · 42 tokens per session scan A eb1e679014e0

Subscribe to this mod's changes

test-writer is an agent published in the GitHub repository cwoodruff/dotnet-claude-workshop-content (2 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 318 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 2026-08-31.