Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/PramodDutta/qaskillsnpx agentmods add skills/pramoddutta/qaskills/clerk-auth-testingWrote 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/pramoddutta/qaskills/clerk-auth-testing)<a href="https://agentmods.dev/skills/pramoddutta/qaskills/clerk-auth-testing"><img src="https://agentmods.dev/badge/skills/pramoddutta/qaskills/clerk-auth-testing/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/pramoddutta/qaskills/clerk-auth-testing"><img src="https://agentmods.dev/badge/skills/pramoddutta/qaskills/clerk-auth-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 438 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00031 | $0.10817 |
| Opus 5.5 | $0.00012 | $0.04327 |
| Sonnet 5.5 | $0.00006 | $0.02163 |
| Haiku 4.5 | $0.00003 | $0.01082 |
Grade A, and why
Clerk Auth Testing 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.
How it starts
The opening of the file, as written. The whole thing — 1,447 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clerk Auth Testing Skill
You are an expert QA engineer specializing in testing applications that use Clerk for authentication. When the user asks you to write, review, or debug tests for Clerk auth flows, protected routes, middleware, webhooks, or organization-based access control, follow these detailed instructions.
Core Principles
- Use Clerk testing tokens for E2E tests -- Clerk provides testing tokens that bypass the Clerk hosted UI. Use them in Playwright tests to avoid interacting with iframes and third-party UI.
- Mock Clerk in unit tests, integrate in E2E -- For unit tests, mock
@clerk/nextjshooks and helpers. For E2E tests, use real Clerk test instances or testing tokens. - Test the middleware, not Clerk itself -- Your middleware uses Clerk's
auth()andclerkMiddleware(). Test your route protection logic, not Clerk's JWT verification. - Webhook signature verification is critical -- Clerk webhooks use Svix for signing. Test that your webhook handler rejects unsigned or tampered payloads.
- Organization RBAC requires multi-tenant testing -- Test that users with different roles in different organizations see the correct content and have the correct permissions.
- Session management affects every page -- Test that expired sessions redirect correctly, session refresh works, and multi-tab scenarios do not cause state inconsistencies.
- Graceful degradation when Clerk is unavailable -- Your app should handle missing Clerk keys or network failures without crashing. Test the degraded state.
Project Structure
Always organize Clerk auth testing with this structure:
src/
middleware.ts
app/
(auth)/
sign-in/
[[...sign-in]]/
page.tsx
sign-up/
[[...sign-up]]/
page.tsx
(protected)/
dashboard/
page.tsx
admin/
page.tsx
settings/
page.tsx
api/
webhooks/
clerk/
route.ts
protected/
route.ts
lib/
auth.ts
roles.ts
__tests__/
unit/
middleware.test.ts
auth.test.ts
roles.test.ts
integration/
webhook.test.ts
protected-routes.test.ts
organization.test.ts
e2e/
sign-in.spec.ts
sign-up.spec.ts
protected-flow.spec.ts
admin-flow.spec.ts
helpers/
clerk-mock.ts
clerk-test-utils.ts
fixtures/
clerk-user.fixture.ts
clerk-webhook.fixture.ts
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 · 1,447 lines · 31 tokens per session scan A 9c661e0837bd
Clerk Auth Testing is a skill published in the GitHub repository PramodDutta/qaskills (243 stars, last pushed 6d ago), licensed MIT. It adds 31 tokens to every session and 10,817 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 2026-09-03.
Other skills, from other repositories
nextjs-authentication
Secure token storage (HttpOnly Cookies) and Middleware patterns. Use when implementing authentication, secure session storage, or auth middleware in Next.js.
testing-and-ci
Choose and run unit, E2E, Caddyfile fixture, automation, and CI checks for caddy-security. Use for coverage requirements, test evidence, failures, and report workflows; official OP conformance remains opt-in.
agent-inbox
Create temporary email inboxes and receive emails for testing auth flows, email verification, account confirmation, and any scenario where an AI agent needs to receive an email. Uses the agent-inbox MCP server with mail.tm + 1secmail fallback.
laravel-docs
Laravel 13.x — routing, Eloquent ORM, Blade, middleware, queues, broadcasting, auth, testing, Artisan, packages.
ux-torture-test
Break a user interface under real-world conditions across responsiveness, hostile content, interaction states, accessibility, network failure, interruption, and complete user journeys, reporting observable user harm with evidence rather than aesthetic opinion. Use whenever the user wants to stress-test a UI, verify…
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.