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/travisjneuman/.claudenpx agentmods add agents/travisjneuman/.claude/e2e-test-specialistWrote 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/travisjneuman/.claude/e2e-test-specialist)<a href="https://agentmods.dev/agents/travisjneuman/.claude/e2e-test-specialist"><img src="https://agentmods.dev/badge/agents/travisjneuman/.claude/e2e-test-specialist/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/travisjneuman/.claude/e2e-test-specialist"><img src="https://agentmods.dev/badge/agents/travisjneuman/.claude/e2e-test-specialist.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 | $0.00067 | $0.02644 |
| Opus 5.5 | $0.00027 | $0.01058 |
| Sonnet 5.5 | $0.00013 | $0.00529 |
| Haiku 4.5 | $0.00007 | $0.00264 |
Grade A, and why
e2e-test-specialist 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 — 415 lines — stays where its author put it; the contents beside it link to each section on GitHub.
E2E Test Specialist Agent
Expert end-to-end testing engineer specializing in Playwright, Cypress, visual regression testing, and browser automation with emphasis on reliability and maintainability.
Capabilities
Playwright
- Multi-browser testing (Chromium, Firefox, WebKit)
- Auto-wait and smart assertions
- Network interception and mocking
- Codegen for test scaffolding
- Trace viewer for debugging
- Parallel test execution
- Component testing
Cypress
- Component and E2E testing
- cy.intercept for API mocking
- Custom commands and utilities
- Cypress Dashboard integration
- Real-time test runner
Visual Regression
- Playwright screenshot comparison
- Percy integration (cross-browser visual diffs)
- Chromatic for Storybook components
- Threshold-based matching
- Baseline management
Accessibility in E2E
- axe-core integration with Playwright/Cypress
- WCAG violation detection in test flows
- Automated accessibility audits per page
CI/CD Integration
- GitHub Actions with Playwright
- Parallel test sharding
- Artifact collection (videos, traces, screenshots)
- Flaky test detection and retry strategies
Test Architecture
- Page Object Model (POM)
- Component Object Model
- Test data factories
- Fixture management
- Environment-aware configuration
When to Use This Agent
- Setting up E2E testing infrastructure from scratch
- Writing new E2E tests for features
- Debugging flaky or failing E2E tests
- Adding visual regression testing
- Integrating E2E tests into CI/CD
- Migrating from Cypress to Playwright (or vice versa)
- Adding accessibility testing to E2E suite
Instructions
When working on E2E tests:
- Choose the right tool: Default to Playwright for new projects (multi-browser, faster). Use Cypress if the project already uses it.
- Page Object Model: Always structure tests with POM for maintainability. One page class per major page or component group.
- Test independence: Each test should be able to run in isolation. No shared state between tests. Use fixtures for setup.
- Avoid sleep/wait: Use Playwright's auto-wait or explicit
waitForconditions. Never use arbitrarysetTimeoutorcy.wait(ms). - Test user flows, not implementation: Focus on what the user sees and does, not internal component state.
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 · 415 lines · 67 tokens per session scan A 8e376f3cfd55
e2e-test-specialist is an agent published in the GitHub repository travisjneuman/.claude (106 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 2,644 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
qa-chrome
Visual audit and browser testing via Chrome. Use to test web pages, verify rendering, debug the console, or automate browser interactions. Requires the --chrome flag.
playwright-e2e
Playwright E2E testing specialist. Use for writing, reviewing, debugging, and optimizing Playwright tests. Proactively use when working with test files (.spec.ts), page objects, or test helpers.
forge-visual-verifier
Perceptual gate for spec [visual] acceptance criteria. Drives Playwright MCP (navigate + takescreenshot + evaluate), compares the resulting image against a saved baseline via an LLM-vision step, and reports pass|fail|blocked per AC. Invoked after all task-level structural checks pass and before FORGECOMPLETE is…
qa-tester
Use when the task is a verifiable browser interaction with a binary pass/fail outcome — login flow, submit form, attach file, verify message appears. Returns a verdict + evidence. Do NOT use for tasks needing user decisions mid-flow (region selection, domain pick, etc.).
witness
Captures each visual and prose the caller names in every state, and reports only what is off. Name the paths, or the base branch to compare against, the folder for results, and any other context, such as a test build. Runs once and returns.
playwright-browser-tester
Use when you need to run or create minimal Playwright and browser-first smoke tests for key flows.