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.
npx skills add mavka-ai/unit-tests-skills --skill generate-testsgit clone --depth 1 https://github.com/mavka-ai/unit-tests-skillsWrote 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/skills/mavka-ai/unit-tests-skills/generate-tests)<a href="https://agentmods.dev/skills/mavka-ai/unit-tests-skills/generate-tests"><img src="https://agentmods.dev/badge/skills/mavka-ai/unit-tests-skills/generate-tests/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/skills/mavka-ai/unit-tests-skills/generate-tests"><img src="https://agentmods.dev/badge/skills/mavka-ai/unit-tests-skills/generate-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00053 | $0.01884 |
| Opus 5 | $0.00026 | $0.00942 |
| Sonnet 5 | $0.00011 | $0.00377 |
| Haiku 4.5 | $0.00005 | $0.00188 |
Grade A, and why
generate-tests 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Tests Skill
You will analyze code and generate high-quality unit tests for a given target.
Target to test: $ARGUMENTS
Quality Standards
- Take your time to analyze the code thoroughly before generating test cases.
- Quality is more important than speed — read all relevant source files and rules carefully.
- Do not skip any step in the workflow below. Every step exists for a reason.
- Do not take shortcuts with test data — read the actual classes to use correct constructors and fields.
Instructions
Step 1: Read Rules and Analyze Context
- Read the relevant rules from
./rules/tests/based on code type (see Rules Reference below) - Read the target source file/class/method
- Read dependencies: Follow imports to read DTOs, entities, enums, custom exceptions, and other types referenced by the target (as specified in
code-context-analysisrule) - Check for existing tests: Search for
{ClassName}Testor{ClassName}Testsin the test directory (as specified inexisting-test-awarenessrule)- If found, read fully — you will add missing tests to it, not create a new file
- If not found, scan 2-3 neighboring test classes to learn project conventions
Step 2: Generate Test Cases
- Analyze ALL code branches, including:
- Success paths
- Error/exception paths
- Validation logic
- Private/protected methods called by the target
- Security annotations (if present)
- Apply the INCLUDE/EXCLUDE rules strictly
- Output the list of test cases in the format below — do NOT generate test code yet
Test Case Output Format
## Test Cases for {ClassName}.{methodName}
### 1. {testMethodName}
- **Given:** {preconditions/input state}
- **When:** {action being tested}
- **Then:** {expected outcome}
- **Code branch:** {which code path this covers}
### 2. {testMethodName}
...
Naming Convention
Test method name format: {testedMethod}_{givenState}_{expectedOutcome}
Examples:
calculateTotal_validProducts_returnsSumcalculateTotal_emptyList_throwsIllegalArgumentExceptiongetUser_unauthorized_returns401
What ships with it
22 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- rules/tests/general/cleanly-create-test-data.md 3.0 KB
- rules/tests/general/code-context-analysis.md 2.6 KB
- rules/tests/general/existing-test-awareness.md 2.6 KB
- rules/tests/general/general-principles.md 4.0 KB
- rules/tests/general/keep-cause-effect-clear.md 2.4 KB
- rules/tests/general/keep-tests-focused.md 2.5 KB
- rules/tests/general/naming-conventions.md 1.6 KB
- rules/tests/general/no-logic-in-tests.md 2.7 KB
- rules/tests/general/prefer-public-apis.md 2.9 KB
- rules/tests/general/technology-stack-detection.md 2.4 KB
- rules/tests/general/test-behaviors-not-methods.md 3.0 KB
- rules/tests/general/test-case-generation-strategy.md 2.5 KB
- rules/tests/general/verify-relevant-arguments-only.md 2.9 KB
- rules/tests/general/what-makes-good-test.md 3.2 KB
- rules/tests/java/unit/argument-matching.md 2.7 KB
- rules/tests/java/unit/controller-test-rules.md 5.2 KB
- rules/tests/java/unit/domain-service-rules.md 4.4 KB
- rules/tests/java/unit/java-test-template.md 2.5 KB
- rules/tests/java/unit/json-serialization.md 3.2 KB
- rules/tests/java/unit/logging-rules.md 3.6 KB
- rules/tests/post-generation/compilation-verification.md 2.9 KB
- rules/tests/post-generation/test-execution-verification.md 2.6 KB
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.
- 12d ago First seen · 187 lines · 53 tokens per session scan A 76d9316b6297
generate-tests is a skill published in the GitHub repository mavka-ai/unit-tests-skills (50 stars, last pushed 2d ago), licensed MIT. It adds 53 tokens to every session and 1,884 once invoked, about $0.0003 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.
Other skills, from other repositories
working-effectively-with-legacy-code
Apply Michael Feathers-inspired legacy-code rules when changing hard-to-test code safely with characterization tests, seams, sprout methods, or wrap methods.
refactoring-guru
Apply Refactoring.Guru-inspired rules when diagnosing code smells, choosing refactoring techniques, and stopping cleanup before uncontrolled redesign.
refactoring
Apply Martin Fowler-inspired refactoring rules when improving existing code structure while preserving observable behavior.
template-formal
Strongly-typed multiagent ant-robot colony exemplar — ADTs, session-typed protocols, affine-discipline resource handles, storage-as-functor framing, Active-Inference-flavored decision loop, mypy-as-oracle negative controls.
template-test-creation
Create pytest suites under the no-mocks policy — real data, temp files, subprocess, pytest-httpserver. USE WHEN adding tests, raising coverage, testing new src/ module, or user forbids mocks.
android-kotlin-testing
Android testing patterns — ViewModel unit tests with Turbine, Compose UI semantics, Hilt TestInstallIn fakes, coroutine test dispatchers, and release quality gates. Use when writing tests, setting up CI, mocking repositories, or asking "how to test ViewModel", "Compose UI test", "Turbine StateFlow".