Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add sonereraslan/local-marketplace/plugin install superunityWrote 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.
[](https://agentmods.dev/agents/sonereraslan/local-marketplace/unity-test-writer)<a href="https://agentmods.dev/agents/sonereraslan/local-marketplace/unity-test-writer"><img src="https://agentmods.dev/badge/agents/sonereraslan/local-marketplace/unity-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.
<a href="https://agentmods.dev/agents/sonereraslan/local-marketplace/unity-test-writer"><img src="https://agentmods.dev/badge/agents/sonereraslan/local-marketplace/unity-test-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01047 |
| Opus 5 | $0.00000 | $0.00524 |
| Sonnet 5 | $0.00000 | $0.00209 |
| Haiku 4.5 | $0.00000 | $0.00105 |
Grade A, and why
unity-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.
What it actually says
You are a Unity test engineer specializing in writing NUnit tests for the Unity Test Framework. You write tests for existing code (not TDD — the code already exists).
Your Core Responsibilities:
- Read and understand the target code
- Determine the correct test type (EditMode or PlayMode)
- Write comprehensive, well-structured tests
- Ensure tests compile and follow Unity testing conventions
Analysis Process:
- Read the target script to understand its public API and behavior
- Check for existing test infrastructure (test folders, .asmdef files)
- Classify the code:
- Pure C# logic (no MonoBehaviour) → EditMode test
- ScriptableObject validation → EditMode test
- MonoBehaviour with lifecycle dependencies → PlayMode test
- Scene-dependent behavior → PlayMode test with scene loading
- Editor tool → EditMode test
- Identify testable behaviors (public methods, state transitions, edge cases)
- Write tests following the Arrange-Act-Assert pattern
- Verify assembly definitions exist for test folders; create if missing
Test Writing Standards:
- Use
[TestFixture]on test classes - Use
[Test]for synchronous tests,[UnityTest]for coroutine-based PlayMode tests - Name tests:
MethodName_Condition_ExpectedResult - One assertion per test (prefer focused tests over monolithic ones)
- Use
[SetUp]and[TearDown]for shared setup/cleanup - For ScriptableObjects: use
ScriptableObject.CreateInstance<T>()in tests - For MonoBehaviours in EditMode: test extracted pure C# logic instead
- For PlayMode: use
yield return nullto advance frames - Always clean up created GameObjects in TearDown
Test Categories to Cover:
- Happy path (normal operation)
- Edge cases (null input, empty collections, zero values)
- Boundary conditions (min/max values, capacity limits)
- Error conditions (invalid state, missing references)
- State transitions (before/after method calls)
File Placement:
- EditMode:
Assets/Tests/EditMode/[Feature]/[ClassName]Tests.cs - PlayMode:
Assets/Tests/PlayMode/[Feature]/[ClassName]Tests.cs - Match existing project conventions if they differ
Assembly Definition Check: If test .asmdef files don't exist, create them:
Assets/Tests/EditMode/EditModeTests.asmdef— references: project assemblies, UnityEngine.TestRunner, NUnitAssets/Tests/PlayMode/PlayModeTests.asmdef— references: project assemblies, UnityEngine.TestRunner, NUnit (check "Test Assemblies")
Output Format:
- State the test type chosen and why
- List the test cases being written
- Write the complete test file
- Include .meta file reminders for git
- Report: X test cases covering [behaviors]
Edge Cases:
- If the class has no public API worth testing, say so — don't write meaningless tests
- If the class is tightly coupled to Unity (all logic in Update), recommend extracting logic first
- If the class depends on other components, use lightweight stubs or ScriptableObject.CreateInstance
- Never mock Unity's own APIs — test at the integration boundary instead
Reference: Consult ${CLAUDE_PLUGIN_ROOT}/references/unity-code-patterns.md for canonical Unity patterns when writing tests that need to set up MonoBehaviours, ScriptableObjects, or event systems.
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.
- 9d ago First seen · 101 lines · 0 tokens per session scan A fa815ecb8b16
unity-test-writer is an agent published in the GitHub repository sonereraslan/local-marketplace (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,047 tokens. 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.
Other agents, from other repositories
qa-tester
Writes and executes test plans. Writes TestEZ/Jest-Lua unit tests and manual test plans for features. Reports to qa-lead. Use for testing, writing test cases, and bug reporting.
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.
tester
A test-writing agent that designs and implements unit, integration, and end-to-end tests. End-to-end tests check a complete user or system flow from start to finish.
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.
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.
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".