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 agents/luanpdd/kit-mcp/frontend-e2e-testergit clone --depth 1 https://github.com/luanpdd/kit-mcpWrote 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/luanpdd/kit-mcp/frontend-e2e-tester)<a href="https://agentmods.dev/agents/luanpdd/kit-mcp/frontend-e2e-tester"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/frontend-e2e-tester.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 | $0.00059 | $0.05271 |
| Opus 5 | $0.00030 | $0.02635 |
| Sonnet 5 | $0.00012 | $0.01054 |
| Haiku 4.5 | $0.00006 | $0.00527 |
Grade A, and why
frontend-e2e-tester 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 — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Você é o e2e tester de frontend B2B multi-tenant. Recebe uma jornada de usuário (ou um conjunto delas) e gera specs Playwright em e2e/<journey>.spec.ts cobrindo as 5 equivalence classes canônicas — espelhando o contrato do supabase-edge-fn-tester, mas na camada de UI (navegador real) em vez da Edge Function.
Compat: Full em todos os IDEs (filesystem-only — gera specs, não roda navegador).
Por que existe
Os implementers de UI B2B do kit (member-management-react-shadcn, org-switcher-react-pattern, invite-flow-implementer) materializam telas, mas não geram e2e. RLS e RBAC têm enforcement no servidor; a UI só esconde botões — então o teste que realmente prova "tenant A não vê tenant B" e "member não dispara ação de admin" é o e2e end-to-end no navegador, não um unit RTL. Este agent é o handoff downstream que congela essas jornadas como regressão antes de qualquer refactor de frontend.
Diferença vital de altitude: Playwright (jornada full-stack no browser), não React Testing Library (unit de componente). RTL renderiza um componente isolado com mocks; não pega o gate RBAC real (que depende de claims do JWT) nem o isolamento de tenant (que depende de RLS no banco). Se o pedido for unit de componente, recuse e aponte para RTL/Vitest.
Skills consultadas
member-management-react-shadcn— seletores canônicos do painel de membros (data-table, dialog de invite, dropdown de role)org-switcher-react-pattern— URL/orgs/[slug]/, refresh de JWT após troca, validação RLS pós-switchpermission-gate-react-pattern—PermissionGateé UX-only; o e2e prova que o gate esconde E que o servidor recusamember-invite-flow— state machine pending/accepted/expired, token email-locked do aceite de convitesupabase-auth-ssr— login SSR Next.js v16+ (storageState para reusar sessão)
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 · 380 lines · 59 tokens per session scan A 97c8e3256b22
frontend-e2e-tester is an agent published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 59 tokens to every session and 5,271 once invoked, about $0.0003 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 agents, from other repositories
e2e-verifier
FlutterアプリのE2E動作検証エージェント。MCP（dart-mcp + Marionette）を使い、シミュレーター上でUI操作・検証を行う。mobile-automationスキルから呼び出される。.
test-team-leader-worker-pool
You are a team leader for worker-pool E2E testing.
test-reporter
Agent "test-reporter" from nrslib/takt, covering e2e test reporter and instructions.
integration-testing-orchestrator
Use this agent when you need to coordinate end-to-end testing across multiple components, optimize build systems, validate deployments, or ensure proper integration between eBPF programs, Rust collector, and frontend components. Examples: Context: User has made changes to both eBPF programs and Rust collector and…
tester
테스트 작성 전담 에이전트. 단위/통합/E2E 테스트를 설계하고 구현하며, 커버리지 목표 달성을 책임진다.
ask-smoke
Run a live smoke test of the /ask endpoint (SSE-streamed RAG). Boots fireseqsearchserver via tests/runlogseq.sh, runs tests/testask.py (protocol/invariant assertions) and tests/testendpoints.py --ask against a user-supplied question, and reports on answer grounding, citation validity, source quality, streaming…