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 agentmods add skills/makigjuro/cloudstack-ai-plugins/generate-testsnpx skills add makigjuro/cloudstack-ai-plugins --skill generate-testsgit clone --depth 1 https://github.com/makigjuro/cloudstack-ai-pluginsWhat 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 | $0.00042 | $0.01757 |
| Opus 5 | $0.00021 | $0.00879 |
| Sonnet 5 | $0.00008 | $0.00351 |
| Haiku 4.5 | $0.00004 | $0.00176 |
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 2d 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Tests
Generate unit and integration tests following project conventions. Analyzes the target code, identifies test scenarios, and scaffolds test classes with proper mocking and assertions.
Arguments
{target}-- Handler, entity, or class name to test (e.g.,CreateOrderHandler,Order,OrderEndpoints){service}-- Target microservice (optional, auto-detected from file location)--integration-- Also generate integration tests with Testcontainers--coverage-- Generate tests for all untested handlers in a service
Configuration
Read cloudstack.json from the project root at the start of execution. Extract:
NAMESPACE=project.namespace(default: detect from*.sln)SERVICES=backend.services[](default: discover from project structure)SOLUTION=backend.solutionPath(default: find*.sln)MESSAGING=backend.messaging(default:wolverinefx)RESULT_PATTERN=backend.resultPattern(default:true)
If cloudstack.json does not exist, auto-detect by scanning the project structure.
Process
Step 1: Locate the target
# Find the file containing the target class
grep -rl "class {target}" src/ --include="*.cs" | head -5
Read the target file completely. Identify:
- Is it a command handler? (method returns
Result<T>, takes a command record) - Is it a query handler? (method returns
Result<T>, takes a query record) - Is it an entity? (inherits from
Entity<TId>orAggregateRoot<TId>) - Is it an event handler? (handles domain/integration events)
- Is it an endpoint? (static class with
MapEndpoints)
Step 2: Analyze dependencies
Read the constructor to find injected dependencies:
grep -A 20 "class {target}" <file> | grep -E "private readonly|ILogger|I[A-Z]"
For each dependency, determine:
- Repository interfaces → mock with NSubstitute
- External services → mock with NSubstitute
- ILogger → mock or use NullLogger
- DbContext → use in-memory for unit, Testcontainers for integration
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.
- 2d ago First seen · 232 lines · 42 tokens per session scan A 855ad2316315
generate-tests is a skill published in the GitHub repository makigjuro/cloudstack-ai-plugins (1 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 1,757 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.
Other skills, from other repositories
js-in-html-testing
Test JS logic embedded in HTML using two-layer strategy - Python unit tests + Playwright browser integration tests.
api-testing
Testing patterns for MCP tool/resource handlers using createMockContext and Vitest. Covers mock context options, handler testing, McpError assertions, format testing, Vitest config setup, and test isolation conventions.
verify
Self-healing verification loop (test → clippy → fmt).
test
Run backend (.NET) xUnit unit and integration tests via the developer CLI.
backseat-driver-testing
Testing strategies for Calva Backseat Driver MCP tools. Use when: Testing Backseat Driver, validating tool updates, testing structural editing workflows, verifying REPL evaluation with who-tracking, testing shadow-cljs runtime discovery and targeting, testing output log filtering, testing load-file tool, smoke testing…
testing
Vitest and Playwright testing patterns, conventions, and gotchas for this project.