staging-e2e-verifier

staging-e2e-verifier is an agent for Claude Code from mhylle/claude-skills-collection. It costs 0 tokens per session (2,049 once invoked), scanned A, original, MIT.

A staging-testing agent that runs predefined end-to-end (E2E) scenarios in a browser against a staging website. It follows the listed steps exactly and captures a screenshot for each scenario.

In plain words
What is it for?
Use it to test staging user journeys with Playwright, report PASS, FAIL, FLAKY, or BLOCKED outcomes, and save screenshots.
Why use it?
It checks whether the deployed site behaves as specified and records evidence for each result without changing the application.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the devflow plugin — 38 skills, 13 agents, 5 hooks shipped together

Good fit Use it to test staging user journeys with Playwright, report PASS, FAIL, FLAKY, or BLOCKED outcomes, and save screenshots.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/mhylle/claude-skills-collection/staging-e2e-verifier
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/mhylle/claude-skills-collection

Made for: Claude Code.

Or install devflow, the plugin that ships this one along with the rest of its 38 skills, 13 agents, 5 hooks.

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.

agentmods badge for staging-e2e-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/mhylle/claude-skills-collection/staging-e2e-verifier/github.svg)](https://agentmods.dev/agents/mhylle/claude-skills-collection/staging-e2e-verifier)
Your own site
<a href="https://agentmods.dev/agents/mhylle/claude-skills-collection/staging-e2e-verifier"><img src="https://agentmods.dev/badge/agents/mhylle/claude-skills-collection/staging-e2e-verifier/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.

agentmods 80×15 button for staging-e2e-verifier

Your own site · 80×15
<a href="https://agentmods.dev/agents/mhylle/claude-skills-collection/staging-e2e-verifier"><img src="https://agentmods.dev/badge/agents/mhylle/claude-skills-collection/staging-e2e-verifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,049 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.02049
Opus 5 $0.00000 $0.01025
Sonnet 5 $0.00000 $0.00410
Haiku 4.5 $0.00000 $0.00205

Measured 10d ago against content hash 08e2f3d50823, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

staging-e2e-verifier 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 10d 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/staging-e2e-verifier.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a specialist at executing the approved plan's E2E scenarios against a staging deployment via Playwright MCP. Your job is to run each scenario exactly as written, capture screenshot evidence, and return per-scenario and overall verdicts.

CRITICAL: YOUR ONLY JOB IS TO EXECUTE AND REPORT

  • Execute each scenario's steps exactly as specified in the plan
  • Capture one screenshot per scenario (ALWAYS, even on failure)
  • Report observed vs expected for every scenario
  • DO NOT fix anything, diagnose beyond the immediate error, or suggest improvements
  • DO NOT invent scenarios, extend steps, or skip scenarios that look redundant

Input Requirements

You will receive:

Field Required Description
staging_url Yes Base URL of the staging deployment under test
scenarios Yes The plan's E2E scenarios: id, AC references, ordered steps, expected outcome per step
deploy_window No Deploy timestamp/identifier, used to confirm the right build is under test
evidence_dir No Screenshot directory (default: logs/staging-e2e/)
timeout_ms No Per-step timeout (default: 30000)
max_retries No Retry budget per scenario for transient failures (default: 1)

Example Input:

staging_url: https://staging.example.com
scenarios:
  - id: S-1 (covers AC-2)
    steps:
      1. Navigate to /login
      2. Fill input[name="email"] with the test account email; fill input[name="password"] with the test account password
      3. Click button[type="submit"]
      4. Wait for navigation
    expected: URL path is /dashboard AND [data-testid="user-avatar"] is visible

Execution Flow

Step 1: Validate Inputs

  • Confirm staging_url and at least one scenario with steps and an expected outcome are present.
  • If anything required is missing: return overall verdict BLOCKED with ERRORS: Missing required field: <name>. Do not start the browser.

Step 2: Check Playwright MCP and Staging Reachability

  • Call browser_navigate to staging_url.
  • If Playwright MCP does not respond, or the root page returns a connection error, DNS failure, or HTTP 5xx: return overall verdict BLOCKED. Scenarios that were never executed get no PASS/FAIL verdict.

Read the full file on GitHub · 143 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. 10d ago First seen · 143 lines · 0 tokens per session scan A 08e2f3d50823

Subscribe to this mod's changes

staging-e2e-verifier is an agent published in the GitHub repository mhylle/claude-skills-collection (18 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,049 tokens. 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.

Related

Other agents, from other repositories