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.
git clone --depth 1 https://github.com/peterblazejewicz/claude-pluginsWrote 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/commands/peterblazejewicz/claude-plugins/test)<a href="https://agentmods.dev/commands/peterblazejewicz/claude-plugins/test"><img src="https://agentmods.dev/badge/commands/peterblazejewicz/claude-plugins/test/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/commands/peterblazejewicz/claude-plugins/test"><img src="https://agentmods.dev/badge/commands/peterblazejewicz/claude-plugins/test.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 | $0.00030 | $0.00396 |
| Opus 5.5 | $0.00012 | $0.00158 |
| Sonnet 5.5 | $0.00006 | $0.00079 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
test 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 1mo 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
Invoke the dotnet-skills:test-driven-development skill.
For new features:
- Write xUnit or MSTest tests that describe the expected behavior (they should FAIL)
- Implement the C# code to make them pass
- Refactor while keeping tests green — run
dotnet testafter each change
For bug fixes (Prove-It pattern):
- Write a test that reproduces the bug (must FAIL)
- Confirm the test fails:
dotnet test --filter FullyQualifiedName~<NewTest> - Implement the fix
- Confirm the test passes
- Run the full test suite for regressions:
dotnet test
For integration-boundary issues — HTTP endpoints, EF Core queries against a real database, Blazor/Razor pages in a real browser, or Avalonia views — also invoke dotnet-skills:integration-testing-dotnet to cover WebApplicationFactory<T>, Testcontainers, Microsoft.Playwright, and Avalonia.Headless.XUnit.
Source & Modifications
- Upstream:
addyosmani/agent-skills—.claude/commands/test.mdat pinned SHA44dac80 - Status: modified (skill references retargeted to the
dotnet-skills:prefix; critical substitution: upstream'sagent-skills:browser-testing-with-devtoolsdoes not exist downstream — rewritten asdotnet-skills:integration-testing-dotnet, which covers the four .NET integration boundaries; framework labels changed from generic "tests" to "xUnit or MSTest tests"; commands usedotnet test --filter FullyQualifiedName~...for single-test runs)
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.
- 1mo ago First seen · 29 lines · 30 tokens per session scan A 21d45a14bb59
test is a command published in the GitHub repository peterblazejewicz/claude-plugins (8 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 396 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other commands, from other repositories
new-test
Scaffold xUnit v3 test classes with Arrange-Act-Assert, mock setup, proper naming conventions, and trait categories.
coder
Autonomous code generation with batch file operations.
modernize-uplift
Same-stack version uplift (e.g. .NET Framework 4.8 → .NET 8) — preserve the code, fix the version deltas, prove equivalence by running one test suite on both runtimes.
rust-test
Rust TDD workflow with unit and property tests.
go-test
Go TDD workflow with table-driven tests.
tdd
Enforce TDD workflow with 80%+ coverage.