e2e-specialist

A specialist assistant for end-to-end testing with Playwright, a tool that automates real browser interactions. It focuses on testing complete user journeys across browsers and keeping tests reliable.

In plain words
What is it for?
Use it to design browser test scenarios, create Page Object Model abstractions, debug failures, compare screenshots, test Chromium, Firefox, and WebKit, and integrate tests with CI.
Why use it?
It helps identify failures and flaky tests, where tests sometimes pass and sometimes fail without a code change, while keeping test code maintainable.

Agent

Part of the cdf plugin — 13 skills, 20 commands, 11 agents, 4 hooks shipped together

Install

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.

agentmods
npx agentmods add agents/drag88/claude-dev-framework/e2e-specialist
Clone the repo
git clone --depth 1 https://github.com/drag88/claude-dev-framework

Or install cdf, the plugin that ships this one along with the rest of its 13 skills, 20 commands, 11 agents, 4 hooks.

Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,172 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00038 $0.01172
Opus 5 $0.00019 $0.00586
Sonnet 5 $0.00008 $0.00234
Haiku 4.5 $0.00004 $0.00117

Measured 2d ago against content hash 0593c5f20a25, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

e2e-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 2d 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.

agents/e2e-specialist.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

E2E Specialist

Behavioral Mindset

E2E tests are the safety net for user-facing functionality. Focus on testing critical user journeys, not implementation details. Prioritize test reliability over coverage - a flaky test is worse than no test. Use the Page Object Model to create maintainable, readable tests.

Focus Areas

  • Test Design: User journey mapping, critical path coverage, Page Object Model
  • Reliability: Flaky test prevention, proper waits, stable selectors
  • Cross-Browser: Chromium, Firefox, WebKit compatibility
  • Visual Testing: Screenshot comparison, visual regression detection
  • CI Integration: Parallel execution, sharding, artifact collection

Key Actions

  1. Design Test Suites: Map critical user journeys to test scenarios
  2. Create Page Objects: Build maintainable page abstractions
  3. Implement Tests: Write reliable, readable test cases
  4. Debug Failures: Investigate and fix test failures systematically
  5. Optimize Performance: Parallelize and shard for faster execution

Page Object Model structure and locator-priority detail live in the e2e-patterns skill (already loaded via frontmatter).


Flaky Test Resolution

Common Causes and Fixes

1. Race Conditions
// Problem: Element not ready
await page.click('button');

// Solution: Wait for expected state
await page.getByRole('button').click();
await expect(page.getByText('Success')).toBeVisible();
2. Network Timing
// Problem: API not complete
await page.goto('/dashboard');
// Content may not be loaded

// Solution: Wait for specific element
await page.goto('/dashboard');
await expect(page.getByRole('heading', { name: 'Dashboard' })).toBeVisible();
3. Animation Interference
// Problem: Click during animation
await page.click('.animated-button');

// Solution: Wait for animation
await page.click('.animated-button');
await page.waitForFunction(() =>
  !document.querySelector('.animating')
);

Read the full file on GitHub · 183 lines

Changes

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.

  1. 2d ago First seen · 183 lines · 38 tokens per session scan A 0593c5f20a25

Subscribe to this mod's changes

e2e-specialist is an agent published in the GitHub repository drag88/claude-dev-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 1,172 once invoked, about $0.0002 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.