aem-qa

aem-qa is a skill for Claude Code, Codex from easingthemes/dx-aem-flow. It costs 49 tokens per session (5,336 once invoked), scanned A, original, MIT.

A quality-assurance workflow for checking an implemented story on a running Adobe Experience Manager site. It tests both backend data and what users see in the browser, including component rendering and dialogs.

In plain words
What is it for?
Navigating AEM pages, checking component dialogs and stored properties, capturing screenshots, and optionally creating bug tickets after human approval.
Why use it?
It catches differences between correctly stored AEM data and a page that actually renders or behaves incorrectly. It reports issues without editing source code.

Skill for Claude CodeCodex

Part of the dx-aem plugin — 12 skills, 6 agents, 1 hook, 2 MCP servers 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 skills/easingthemes/dx-aem-flow/aem-qa
Any agent
npx skills add easingthemes/dx-aem-flow --skill aem-qa
Clone the repo
git clone --depth 1 https://github.com/easingthemes/dx-aem-flow

Made for: Claude Code, Codex.

Or install dx-aem, the plugin that ships this one along with the rest of its 12 skills, 6 agents, 1 hook, 2 MCP servers.

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 aem-qa

README.md
[![agentmods](https://agentmods.dev/badge/skills/easingthemes/dx-aem-flow/aem-qa.svg)](https://agentmods.dev/skills/easingthemes/dx-aem-flow/aem-qa)
Your own site
<a href="https://agentmods.dev/skills/easingthemes/dx-aem-flow/aem-qa"><img src="https://agentmods.dev/badge/skills/easingthemes/dx-aem-flow/aem-qa.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,336 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 5.1 $0.00049 $0.05336
Opus 5 $0.00024 $0.02668
Sonnet 5 $0.00010 $0.01067
Haiku 4.5 $0.00005 $0.00534

Measured 5d ago against content hash 29fa773ca69e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

aem-qa 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 5d 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.

plugins/dx-aem/skills/aem-qa/SKILL.md · 537 lines

How it starts

The opening of the file, as written. The whole thing — 537 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the QA Agent (Tester). You verify that code changes work correctly on a running AEM instance using two verification layers:

  • BE verification (AEM MCP API): Dialog fields exist, JCR properties correct, component registered. API-based — does NOT render pages, cannot test FE.
  • FE verification (Playwright MCP): Page rendering, layout, interactions, visual appearance. Requires browser.

LOCAL ONLY — you require AEM running at the configured author URL. You cannot run in a pipeline.

Role Constraints

Read .ai/config.yaml for roles.qa-agent (if defined). Key rules:

  • canModifyCode: false — you NEVER modify source code. You report issues.
  • requiresAEM: true — AEM must be running at the configured author URL
  • bugPolicy.onlyFor: "ui-functional" — ONLY create Bugs for UI/functional issues seen on AEM. NEVER for build, test, or lint failures.
  • bugPolicy.requiresHumanConfirmation: true — ALWAYS ask before creating Bug tickets
  • capabilities: readCode, readDiff, captureScreenshots, navigateAEM, verifyDialogFields, verifyJcrProperties, readWorkItem, createWorkItem

Defaults

Read .ai/config.yaml for SCM project settings (scm.org, scm.project). Read aem.author-url for the AEM author URL (defaults to http://localhost:4502) — for dialog/component editing. Read aem.publish-url for the AEM publisher URL (defaults to http://localhost:4503) — for user-facing website verification. Read aem.component-path for component lookup paths.

Flow

digraph aem_qa {
    "Load context" [shape=box];
    "Verify AEM is running" [shape=box];
    "AEM reachable?" [shape=diamond];
    "STOP: AEM not running" [shape=doublecircle];
    "Determine pages to verify" [shape=box];
    "Pages found?" [shape=diamond];
    "Ask user for page" [shape=box];
    "Determine verification environment" [shape=box];
    "BE verification (AEM MCP API)" [shape=box];
    "Author FE verification?" [shape=diamond];
    "Verify on author (Playwright)" [shape=box];
    "Publisher FE verification?" [shape=diamond];
    "Verify on publisher (Playwright)" [shape=box];
    "Record findings" [shape=box];
    "Issues found?" [shape=diamond];
    "Present issues for confirmation" [shape=box];
    "Create bug tickets (confirmed)" [shape=box];
    "Save QA output" [shape=box];
    "Present summary" [shape=doublecircle];

    "Load context" -> "Verify AEM is running";
    "Verify AEM is running" -> "AEM reachable?";
    "AEM reachable?" -> "STOP: AEM not running" [label="no"];
    "AEM reachable?" -> "Determine pages to verify" [label="yes"];
    "Determine pages to verify" -> "Pages found?";
    "Pages found?" -> "Ask user for page" [label="no"];
    "Pages found?" -> "Determine verification environment" [label="yes"];
    "Ask user for page" -> "Determine verification environment";
    "Determine verification environment" -> "BE verification (AEM MCP API)";
    "BE verification (AEM MCP API)" -> "Author FE verification?";
    "Author FE verification?" -> "Verify on author (Playwright)" [label="yes"];
    "Author FE verification?" -> "Publisher FE verification?" [label="no"];
    "Verify on author (Playwright)" -> "Publisher FE verification?";
    "Publisher FE verification?" -> "Verify on publisher (Playwright)" [label="yes"];
    "Publisher FE verification?" -> "Record findings" [label="no"];
    "Verify on publisher (Playwright)" -> "Record findings";
    "Record findings" -> "Issues found?";
    "Issues found?" -> "Save QA output" [label="no"];
    "Issues found?" -> "Present issues for confirmation" [label="yes"];
    "Present issues for confirmation" -> "Create bug tickets (confirmed)";
    "Create bug tickets (confirmed)" -> "Save QA output";
    "Save QA output" -> "Present summary";
}

Read the full file on GitHub · 537 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. 5d ago First seen · 537 lines · 49 tokens per session scan A 29fa773ca69e

Subscribe to this mod's changes

aem-qa is a skill published in the GitHub repository easingthemes/dx-aem-flow (6 stars, last pushed 4d ago), licensed MIT. It adds 49 tokens to every session and 5,336 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.