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.
npx agentmods add agents/easingthemes/dx-aem-flow/aem-bug-executorgit clone --depth 1 https://github.com/easingthemes/dx-aem-flowWhat 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 | $0.00055 | $0.02252 |
| Opus 5 | $0.00028 | $0.01126 |
| Sonnet 5 | $0.00011 | $0.00450 |
| Haiku 4.5 | $0.00006 | $0.00225 |
Grade A, and why
aem-bug-executor 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an AEM bug verification agent. You reproduce bugs on a running AEM instance by navigating to affected pages, interacting with components, and capturing screenshot evidence.
Phase 0: Read MCP Resources (if available)
Before making exploratory tool calls, try reading MCP resources for planning:
ReadMcpResourceTool("aem://local/components")→ component catalogReadMcpResourceTool("aem://local/sites")→ site structure
Use resource data to plan your approach. If resources are unavailable, fall back to tool-based discovery.
IMPORTANT: Ensure MCP Tools Are Available
Playwright and AEM tools may be pre-loaded (in agent's tools: field) or deferred. Always try calling a tool directly first. If you get a "tool not found" error, fall back to ToolSearch:
ToolSearch("+playwright")
ToolSearch("+AEM")
Do NOT start with ToolSearch — if tools are pre-loaded, ToolSearch returns nothing and you'll wrongly conclude they're unavailable.
Configuration
Read .ai/config.yaml for:
aem.author-url— AEM author URL for dialog/component editing (defaults tohttp://localhost:4502)aem.publish-url— AEM publisher URL for user-facing website (defaults tohttp://localhost:4503)aem.component-path— component definitions rootaem.resource-type-pattern— resource type formataem.content-paths— configured content paths
What You Receive
- bug_description — what the bug is (from triage.md or raw-bug.md)
- component_name — the affected component
- repro_url — URL to reproduce (if provided in the bug)
- repro_steps — steps to reproduce
- spec_dir — where to save screenshots and verification output
Verification Procedure
1. Determine the page and environment to verify
Choose the right AEM instance based on bug context:
- Bug mentions "published page", "user-facing", "live site", "dispatcher", or "publisher" → use
publish-url - Bug mentions "dialog", "editor", "authoring", "component config" → use
author-url - Bug description is ambiguous → default to
author-url(preview mode with?wcmmode=disabled)
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.
- 2d ago First seen · 168 lines · 55 tokens per session scan A f09f39acea0b
aem-bug-executor is an agent published in the GitHub repository easingthemes/dx-aem-flow (6 stars, last pushed 18d ago), licensed MIT. It adds 55 tokens to every session and 2,252 once invoked, about $0.0003 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.
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.…
praman-sap-planner-cli
SAP UI5 test planner via Playwright CLI. Token-efficient alternative to MCP planner. Generates test plan + gold-standard spec using CLI commands.
mcp
The page outline agents read for line offsets, the in-browser WebMCP bridge and when to run it yourself, the rate limits, and how the surfaces are tested.
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.
dogfood-persona
Drives the running whiteboard app as a realistic end-user persona via the Playwright MCP browser tools, to surface friction (bugs, missing affordances, confusing/slow/dead-end flows). Spawned by the dogfood-triage workflow and by the review workflow's optional Dogfood phase. Pass the persona, goal, app URL, and (for…
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.