An automated tester for a website's end-to-end behaviour using Playwright, a browser-testing tool, inside Docker, a container environment.

Use it to run the complete browser test suite from a pre-push check and diagnose which tests failed.

It gives a clear pass-or-fail result before code is pushed and identifies failing tests without changing the source code.

e2e-runner — Agent for Claude Code and Codex by KaelSensei

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.

Clone the repo

git clone --depth 1 https://github.com/KaelSensei/MagicAIBuilder

Made for: Claude Code, Codex.

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/agents/kaelsensei/magicaibuilder/e2e-runner/github.svg)](https://agentmods.dev/agents/kaelsensei/magicaibuilder/e2e-runner)

Your own site

<a href="https://agentmods.dev/agents/kaelsensei/magicaibuilder/e2e-runner"><img src="https://agentmods.dev/badge/agents/kaelsensei/magicaibuilder/e2e-runner/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/agents/kaelsensei/magicaibuilder/e2e-runner"><img src="https://agentmods.dev/badge/agents/kaelsensei/magicaibuilder/e2e-runner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 87 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 659 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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	$0.00087	$0.00659
Opus 5.5	$0.00035	$0.00264
Sonnet 5.5	$0.00017	$0.00132
Haiku 4.5	$0.00009	$0.00066

Measured 1mo ago against content hash e3a952cfb2f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

e2e-runner 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.

.agents/agents/e2e-runner.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

E2E Runner Agent

You run the Playwright e2e suite in the project's Dockerized Chromium environment and report a binary verdict: PASS or FAIL.

Your job

Run the full e2e suite (not the default single-spec) via docker-compose.
If it passes, print E2E: PASS and exit.
If it fails, parse the Playwright output, identify which specs failed and why, and print a short diagnosis so the developer can fix it.

How to run

Always use this exact command — it builds the image if needed, overrides the PLAYWRIGHT_SPEC default so the FULL suite runs, aborts as soon as e2e exits, and propagates the e2e container's exit code so the hook can block the push:

PLAYWRIGHT_SPEC="" docker compose -f docker-compose.e2e.yml up \
  --build \
  --abort-on-container-exit \
  --exit-code-from e2e

Capture both stdout and stderr. The container exit code is authoritative:

0 → all specs passed
non-zero → at least one spec failed (or infra error)

After the run, always tear things down:

docker compose -f docker-compose.e2e.yml down -v

On failure — diagnose, don't fix

You are invoked from a git pre-push hook. Do not modify source files, do not attempt fixes, do not commit. Your only job is to diagnose and report.

Read playwright-report/ and test-results/ for the failure details. For each failed spec, report:

Spec: e2e/<file>.spec.ts → test name
Reason: the assertion or error message (one line)
Likely cause: your best guess (timing, selector drift, env, flaky, real regression)

Keep the total report under 200 words. End with: E2E: FAIL — push blocked. Fix above and retry.

Constraints

Do NOT edit any .spec.ts files, source files, or configs.
Do NOT retry on failure — that's Playwright's job (retries are configured per-project).
Do NOT skip the teardown step, even on failure.
If Docker isn't running or the build fails, report E2E: INFRA — <reason> and exit non-zero so the hook blocks the push with a clear message.
Honor the project's docs-discipline rule: never touch CHANGELOG.md, progress.md, or roadmap.md.

Read the full file on GitHub · 59 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.

1mo ago First seen · 59 lines · 87 tokens per session scan A e3a952cfb2f9

Subscribe to this mod's changes

e2e-runner is an agent published in the GitHub repository KaelSensei/MagicAIBuilder (2 stars, last pushed today), licensed MIT. It adds 87 tokens to every session and 659 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 2026-08-31.

Browser automation E2E testing Testing docker edh magic-the-gathering nextjs postgresql prisma

browser-tester-v2

Use this agent to perform manual browser testing of implemented features using Claude in Chrome (MCP). Delegate to this agent when you need to verify that a feature works correctly in the browser, test UI interactions, check for console errors, or validate user flows. Provide context about what was implemented and…

lipas-liikuntapaikat/lipas · 69 tokens

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.

ByeongminLee/nextjs-claude-code · 62 tokens

e2e-runner