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/evgenii-studitskikh/claude-code-saas-studio/test-setupnpx skills add evgenii-studitskikh/Claude-Code-SaaS-Studio --skill test-setupgit clone --depth 1 https://github.com/evgenii-studitskikh/Claude-Code-SaaS-StudioWrote 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/evgenii-studitskikh/claude-code-saas-studio/test-setup)<a href="https://agentmods.dev/skills/evgenii-studitskikh/claude-code-saas-studio/test-setup"><img src="https://agentmods.dev/badge/skills/evgenii-studitskikh/claude-code-saas-studio/test-setup.svg" alt="Measured on agentmods" 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 | $0.00047 | $0.00717 |
| Opus 5 | $0.00023 | $0.00358 |
| Sonnet 5 | $0.00009 | $0.00143 |
| Haiku 4.5 | $0.00005 | $0.00072 |
Grade A, and why
test-setup 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 4d 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 — 22 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scaffold the project's test infrastructure from the approved QA plan before any feature tests are written. Non-autonomous: present the full plan, get approval, then execute. Never install packages or write config files without sign-off.
Phases
- Load context — read
docs/specs/qa-plan.mdto understand the chosen pyramid and tooling decisions. If the file is missing, stop and direct to/qa-plan. Also readpackage.jsonand any existing test config files to avoid duplicating setup. - Present the plan — show the user the EXACT commands and files that will be created, including: install commands for Vitest,
@testing-library/react,@testing-library/jest-dom,@playwright/test, and any supporting packages (jsdom,@vitejs/plugin-react— or@vitejs/plugin-react-swcfor Next.js projects that use the SWC compiler; both requirejsdomas the Vitest test environment, etc.); a Playwright browser-binary install step (npx playwright install --with-deps) that runs after@playwright/testis installed, so thatnpm run test:e2edoes not fail with a missing-browser error; config files to be written (vitest.config.ts,vitest.setup.ts,playwright.config.ts);package.jsonscripts to be added (test,test:watch,test:e2e); and the CI test step (e.g. a GitHub Actions job snippet). Underfull, confirm each category; underlean, one confirmation for the whole plan; undersolo, proceed directly. Get explicit approval before running anything. - Apply — on approval, run the install commands (including
npx playwright install --with-deps), write the config files, and add thepackage.jsonscripts. Then add one trivial smoke test — place it under__tests__/colocated with the app (e.g.src/__tests__/smoke.test.ts, or at the project root__tests__/smoke.test.tsif there is nosrc/directory) — rendering a minimal component, and one Playwright homepage test (e2e/smoke.spec.tsvisiting/) to verify the harness end-to-end. - Verify — run
npm test(or equivalent) andnpm run test:e2eagainst the smoke tests; show the output. If anything fails, diagnose and fix before proceeding. Underfull, confirm each suite result; underleanorsolo, summarize the combined result. - Next step — on a green run, point to
/write-tests.
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.
- 4d ago First seen · 22 lines · 47 tokens per session scan A b5041c658dea
test-setup is a skill published in the GitHub repository evgenii-studitskikh/Claude-Code-SaaS-Studio (1 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 717 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
k6-load-testing
Comprehensive k6 load testing skill for API, browser, and scalability testing. Write realistic load scenarios, analyze results, and integrate with CI/CD.
deploy-release-test
Validate a commit-specific Next.js preview package and manually trigger the entire Next.js deployment test suite through the teste2edeployrelease.yml GitHub Actions workflow. Use only when asked to run the full deploy test suite or this workflow specifically from an internal vercel/next.js PR branch. Do not use for…
testing-conventions
Use when adding or changing tests, the e2e harness, test process isolation, or CI test sharding.
playwright-ci
Production-ready CI/CD configurations for Playwright — GitHub Actions, GitLab CI, CircleCI, Azure DevOps, Jenkins, Docker, parallel sharding, reporting, code coverage, and global setup/teardown.
e2e
Run end-to-end tests via the CI workflow.
openclaw-testing
Choose, run, rerun, or debug OpenClaw tests, CI checks, Docker E2E lanes, release validation, and the cheapest safe verification path.