A workflow for setting up a complete Playwright end-to-end testing system, including browser test roles, authentication setup, network mocking, project guidance, and gated continuous integration checks.

Use it to onboard Playwright in a project, separate test authentication, make network behavior predictable, document critical flows, and add test checks to CI.

It provides the surrounding structure needed for dependable browser tests instead of only generating individual test files. Playwright is a tool for automating browsers and checking user journeys.

e2e-setup — Skill for Claude Code by YoungjaeDev/my-claude-plugins

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add YoungjaeDev/my-claude-plugins

Claude Code

/plugin install dev

Made for: Claude Code.

Or install dev, the plugin that ships this one along with the rest of its 12 skills, 3 agents.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/e2e-setup/github.svg)](https://agentmods.dev/skills/youngjaedev/my-claude-plugins/e2e-setup)

Your own site

<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/e2e-setup"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/e2e-setup/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/e2e-setup"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/e2e-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 211 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,571 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00211	$0.04571
Opus 5.5	$0.00084	$0.01828
Sonnet 5.5	$0.00042	$0.00914
Haiku 4.5	$0.00021	$0.00457

Measured 13d ago against content hash 4048542af162, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

e2e-setup scanned grade B with 1 finding 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 13d 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.

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

- Do not invent an unsupported loop. Feature-detect `--loop=codex` rather than version-guessing (`npx playwright init-agents --help | grep -qw codex`). Even when it is advertised, Codex cannot register the generated agen

plugins/dev/skills/e2e-setup/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

E2E Setup: full Playwright harness onboarding

Stand up Playwright's official AI test harness (planner -> generator -> healer) plus the surrounding engineering (auth separation, deterministic mocking, an E2E SSOT doc, gated CI). The harness is the point: a test run is a sensor, a test file is a spec, and the three roles form a self-improving loop. This skill only does setup + orchestration + CI + integration; it does not re-implement the roles.

Two runtime paths (Step 2). Under Claude Code, init-agents --loop=claude generates the planner/generator/healer as registerable .claude/agents/*.md, and e2e-author / e2e-debug dispatch them by name (Path A). Under Codex, those generated agent files are not registerable as named subagents, so setup skips them, ensures the .mcp.json playwright-test entry, and the author/debug skills run the same roles as generic subagents carrying the bundled references/role-contracts.md (Path B), or sequentially when no delegation is available (Path C). The engineering below (Steps 3-7) and every gate are identical on both paths.

Why this skill exists (the harness-engineering point). Installing the official agents is NOT enough: out of the box they skip auth setup, can't resolve project-known API errors, and don't know test-account usage, because they lack codebase context. Steps 3-7 below onboard them like a new hire: the config, auth scaffold, route-mock guidance, and especially the E2E SSOT doc are the context an agent needs to work autonomously. Skipping them is the usual reason "the official agents didn't just work."

Bundled templates live at <plugin-root>/assets/. Resolve <plugin-root> with the cross-runtime block in Step 0 (Claude CLAUDE_PLUGIN_ROOT, Codex plugin cache). Codex does not export CLAUDE_PLUGIN_ROOT, so a bare ${CLAUDE_PLUGIN_ROOT}/assets/... copy fails there. The three template files are playwright-ci.yml, e2e-guidelines.template.md, route-mock.scaffold.ts.

Check the installed Playwright, not this file. Probe each subcommand instead of trusting a version floor: npx playwright init-agents --help (and npx playwright trace --help for the headless trace CLI) must print that subcommand's own usage, not the top-level help. Read that init-agents --help output, with npx playwright --version, before relying on any flag value or output filename below; those change between releases, and Playwright's docs say agent definitions "should be regenerated whenever Playwright is updated," so re-run init-agents after upgrades.

Read the full file on GitHub · 188 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.

13d ago Changed 4048542af162
23d ago Changed · +1 lines d5ae3cbd8fe6
1mo ago Changed · +17 lines · +56 tokens per session ad7f58b46c52
1mo ago Changed 27f0de70ffa8
1mo ago Changed d8d8d1ab3990
2mo ago First seen · 170 lines · 155 tokens per session scan B ffc2e6594575

Subscribe to this mod's changes

e2e-setup is a skill published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed today), licensed MIT. It adds 211 tokens to every session and 4,571 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Browser automation E2E testing Testing

browse

Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).

garrytan/gstack · 32 tokens

cua-driver

Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.

davidondrej/skills · 68 tokens

create-verification-skill

Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".

get-bb/bb · 57 tokens

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

anthropics/skills · 35 tokens

browser-qa

A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.

hashgraph-online/awesome-codex-plugins · 58 tokens

test-electron-app

Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…

PostHog/posthog-foss · 112 tokens

e2e-setup