aem-editorial-guide-capture

aem-editorial-guide-capture is an agent for Claude Code from easingthemes/dx-aem-flow. It costs 39 tokens per session (3,161 once invoked), scanned A, original, MIT.

An automated documentation agent for Adobe Experience Manager (AEM), a system where editors manage website content through component dialogs.

In plain words
What is it for?
Use it after development to open AEM author pages, trigger dialogs, capture screenshots, and create editor-friendly component guides.
Why use it?
It turns the editor’s actual interaction with a component into documentation with screenshots, reducing manual guide-writing.

Agent for Claude Code

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

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash .ai/lib/aem-playwright-auth.sh author "$INSTANCE" # writes .ai/playwright/aem-author-state.json.

Part of the dx-aem plugin — 12 skills, 6 agents, 1 hook, 2 MCP servers shipped together

Good fit Use it after development to open AEM author pages, trigger dialogs, capture screenshots, and create editor-friendly component guides.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/easingthemes/dx-aem-flow
agentmods
npx agentmods add agents/easingthemes/dx-aem-flow/aem-editorial-guide-capture

Made for: Claude Code.

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-editorial-guide-capture

README.md
[![agentmods](https://agentmods.dev/badge/agents/easingthemes/dx-aem-flow/aem-editorial-guide-capture.svg)](https://agentmods.dev/agents/easingthemes/dx-aem-flow/aem-editorial-guide-capture)
Your own site
<a href="https://agentmods.dev/agents/easingthemes/dx-aem-flow/aem-editorial-guide-capture"><img src="https://agentmods.dev/badge/agents/easingthemes/dx-aem-flow/aem-editorial-guide-capture.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,161 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.03161
Opus 5 $0.00019 $0.01580
Sonnet 5 $0.00008 $0.00632
Haiku 4.5 $0.00004 $0.00316

Measured 7d ago against content hash 21c1ba05933b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

aem-editorial-guide-capture scanned grade A 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 7d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

const resp = await fetch(window.location.href, {
plugins/dx-aem/agents/aem-editorial-guide-capture.md · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an AEM editorial guide capture agent. You use Playwright MCP tools to open AEM author pages, interact with component dialogs, capture screenshots, and write editor-friendly documentation.

Playwright MCP tools may be pre-loaded (in agent's tools: field) or deferred. Always try calling a tool directly first (e.g., mcp__plugin_dx-aem_playwright__browser_navigate). If you get "tool not found", fall back to ToolSearch("+playwright"). Do NOT start with ToolSearch — if tools are pre-loaded, ToolSearch returns nothing.

Configuration

Read .ai/config.yaml for:

  • aem.author-url — AEM author URL (defaults to http://localhost:4502)
  • aem.author-url-qa — QA author URL (e.g., https://qa-author.example.com)
  • aem.publish-url — local publisher URL (defaults to http://localhost:4503)
  • aem.publish-url-qa — QA publisher URL (e.g., https://qa.example.com)
  • aem.resource-type-pattern — to identify component editables

When the caller specifies QA mode (or the target URL is non-localhost), prefer QA URLs. Fall back to local URLs if QA URLs are not configured.

Playwright MCP Tools

  • mcp__plugin_dx-aem_playwright__browser_tabs — list / select / open / close browser tabs (action via param)
  • mcp__plugin_dx-aem_playwright__browser_navigate — navigate to URL (url only — no type)
  • mcp__plugin_dx-aem_playwright__browser_snapshot — get page accessibility tree with element refs
  • mcp__plugin_dx-aem_playwright__browser_take_screenshot — capture screenshot (filename basename; saved under the MCP --output-dir, .ai/playwright/screenshots/)
  • mcp__plugin_dx-aem_playwright__browser_click — click element by ref
  • mcp__plugin_dx-aem_playwright__browser_evaluate — run JavaScript in page context
  • mcp__plugin_dx-aem_playwright__browser_wait_for — wait for text to appear

Two distinct auth layers — different hosts, never chained

Basic Auth and the AEM login form are independent gates that live on different instances. You pass one or the other depending on which host you navigate to — never both on the same URL:

Read the full file on GitHub · 241 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. 7d ago First seen · 241 lines · 39 tokens per session scan A 21c1ba05933b

Subscribe to this mod's changes

aem-editorial-guide-capture is an agent published in the GitHub repository easingthemes/dx-aem-flow (6 stars, last pushed 6d ago), licensed MIT. It adds 39 tokens to every session and 3,161 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

alchemist

Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…

drobins25/craft · 355 tokens

FAI Browser Agent

Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.

frootai/frootai · 41 tokens

e2e-tester

Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.

mnzralee/claude-multi-agent-architecture · 41 tokens

visual-diagram-verifier

Use this agent when the architecture-designer:design or architecture-designer:review skill has opened the browser preview (Step 8 / step 4d) and wants to check whether diagrams actually render without visually overlapping elements — a real, rendered-geometry check using the chrome-devtools-mcp or firefox-devtools-mcp…

sembraniteam/claude-plugins · 112 tokens

frontend-qa-tester

Comprehensive frontend QA testing specialist using Playwright MCP. Performs manual exploratory testing, captures bugs with screenshots, monitors console errors, tests user flows, and generates detailed bug reports with fix recommendations. Use for thorough testing of web applications.

rafaelkamimura/claude-tools · 52 tokens

ecc-gan-evaluator

GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.

sakuradairong/omp-config · 34 tokens