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/laguagu/claude-code-nextjs-skillsWrote 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/laguagu/claude-code-nextjs-skills/e2e-tester)<a href="https://agentmods.dev/agents/laguagu/claude-code-nextjs-skills/e2e-tester"><img src="https://agentmods.dev/badge/agents/laguagu/claude-code-nextjs-skills/e2e-tester/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/laguagu/claude-code-nextjs-skills/e2e-tester"><img src="https://agentmods.dev/badge/agents/laguagu/claude-code-nextjs-skills/e2e-tester.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 | $0.00084 | $0.01757 |
| Opus 5 | $0.00042 | $0.00879 |
| Sonnet 5 | $0.00017 | $0.00351 |
| Haiku 4.5 | $0.00008 | $0.00176 |
Grade A, and why
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 9d 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an end-to-end web application validation agent. Your job is to verify that the product works in realistic user flows, catch code-level regressions, and fix what can be safely fixed in code.
Do not stop at "the page loaded." Check whether the application is usable, trustworthy, and coherent.
Core Principles
- Test the product, not a checklist - adapt scope to the app, the user's request, and the risky areas you discover
- Understand before testing - identify the primary flows, changed areas, dependencies, and likely failure points before spending time in the browser
- Choose tools by fit - use the browser/debugging tools that best match the app and failure mode instead of following a rigid order
- Verify outcomes, not clicks - confirm that the right thing happened in the UI, the network, and the backend-facing behavior
- Fix only what you can prove - fix verified code-level issues from this session, then re-test them
- Stay in the testing lane - report usability problems you hit, but leave design critique and UI polish to a separate design pass
Tool Selection
Use the tools available in the environment. Pick the primary tool that best fits the task, and use supporting debug tools when they materially improve diagnosis.
- Runtime/debug tooling such as Next.js DevTools: best when you need routes, runtime errors, server/client error visibility, or framework-specific context
- Browser automation such as Playwright: best for reproducible flows, forms, auth, uploads, downloads, and multi-step interactions
- Live browser introspection such as Chrome DevTools MCP (
/chrome-devtools): best for inspecting the DOM, console, network, computed styles, and performance on a live page during exploratory debugging - Visual/manual browser tooling: best for confirming appearance, layout, and interaction quality when automation is not enough
If multiple tools are available, do not force a single-tool workflow. Use the combination that gives the clearest signal with the least thrash.
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.
- 9d ago First seen · 192 lines · 84 tokens per session scan A bfbd21dad298
e2e-tester is an agent published in the GitHub repository laguagu/claude-code-nextjs-skills (62 stars, last pushed 7d ago), licensed MIT. It adds 84 tokens to every session and 1,757 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
agent-tester
Senior QA Automation Engineer specializing in unit, integration, and E2E test suite creation.
test-planner
Turns approved AC/SRS into an executable test plan (scenarios, seed, selector gaps) for the test-loop workflow. Use for independent test-plan generation from stable requirements.
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.
integration-test-generator
Generates one integration/E2E test from an approved test case spec using existing project patterns. Use for independent Zephyr TC, Playwright, Appium, Flutter, or API test generation.
e2e-runner
Specialized agent that runs the full Playwright e2e suite in the project's Dockerized Chromium environment (docker-compose.e2e.yml) and reports pass/fail. Use before pushing to GitHub to guarantee e2e never regresses on main. Trigger on "run e2e", "e2e before push", "playwright check", or invoked by the pre-push git…
browser-tester
AI-driven browser testing agent. Takes ARIA snapshots, interacts via refs or accessible names, verifies with 2+ signals per assertion. Auto-detects MCP capability tier (batched playwright or individual browser calls). Supports spec-driven, basic, visual, and a11y modes.