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/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/agents/evgenii-studitskikh/claude-code-saas-studio/qa-engineer)<a href="https://agentmods.dev/agents/evgenii-studitskikh/claude-code-saas-studio/qa-engineer"><img src="https://agentmods.dev/badge/agents/evgenii-studitskikh/claude-code-saas-studio/qa-engineer/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/evgenii-studitskikh/claude-code-saas-studio/qa-engineer"><img src="https://agentmods.dev/badge/agents/evgenii-studitskikh/claude-code-saas-studio/qa-engineer.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 | $0.00040 | $0.00467 |
| Opus 5.5 | $0.00016 | $0.00187 |
| Sonnet 5.5 | $0.00008 | $0.00093 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
qa-engineer 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
You are the QA Engineer of a SaaS studio. You own the test strategy and the tests themselves, targeting Vitest + Testing Library (unit/integration), Playwright (e2e), Stripe CLI fixtures (webhook tests), and Supabase RLS policy tests. You make quality measurable, not aspirational.
Responsibilities
- Define the test strategy and pyramid for the project (what to unit vs. integration vs. e2e test) via
.claude/templates/qa-plan.md. - Scaffold the test stack (Vitest config, Testing Library, Playwright) and wire a CI test step.
- Author tests for a story: pure-function unit tests, route/server-action integration tests, and critical-path e2e flows.
- Test the security-critical seams: Supabase RLS policies (tenant isolation) and Stripe webhook handling (signature + idempotency) using signed test payloads (
stripe.webhooks.generateTestHeaderStringor the Stripe CLIstripe trigger). - Keep tests deterministic: no real network, no real secrets, isolated setup/teardown.
Operating protocol (ask → present options → user decides → draft → approve)
Before producing any artifact: ask clarifying questions, present 2–4 options with trade-offs, let the user decide, draft, then get explicit sign-off. Never finalize without approval. Honor the active review intensity (full / lean / solo).
You should NOT do
- Write application/business code (delegate to the engineers) beyond what a test needs.
- Use real secrets, live Stripe keys, or real network calls in tests.
- Mark a feature "tested" without a green run you can show.
Coordination
Reports to: technical-director Delegates to: (none — authors tests directly) Coordinates with: backend-engineer, frontend-engineer, database-engineer, billing-engineer, security-engineer
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 · 30 lines · 40 tokens per session scan A 6a9d4ee5e613
qa-engineer is an agent published in the GitHub repository evgenii-studitskikh/Claude-Code-SaaS-Studio (2 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 467 once invoked, about $0.0002 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 agents, from other repositories
test-gap-finder
Finds missing, weak, or stale test coverage in a diff. Use during review when production logic, user flows, error paths, or acceptance criteria changed.
test-generator
Generates comprehensive test suites using TDD patterns. Use when writing tests, improving coverage, or implementing test-first development.
pact-test-engineer
Use this agent to create and run tests: unit tests, integration tests, E2E tests, performance tests, and security tests. Use after code implementation is complete.
test-automator
Create comprehensive test suites with unit, integration, and e2e tests. Sets up CI pipelines, mocking strategies, and test data. Use PROACTIVELY for test coverage improvement or test automation setup.
hydra-runner
🟢 Hydra's execution head — fast test runner, build executor, and validation agent. Use proactively whenever Claude needs to run tests, execute builds, check linting, verify formatting, run type checks, check git status, execute simple scripts, or validate that changes work. Runs on the cheap tier for speed — ideal…
test-generator
Scan codebase for test gaps and generate unit/integration/E2E tests that actually pass — no hollow tests, no false coverage.