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 skills/easingthemes/dx-aem-flow/aem-verifynpx skills add easingthemes/dx-aem-flow --skill aem-verifygit clone --depth 1 https://github.com/easingthemes/dx-aem-flowWrote 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.
[](https://agentmods.dev/skills/easingthemes/dx-aem-flow/aem-verify)<a href="https://agentmods.dev/skills/easingthemes/dx-aem-flow/aem-verify"><img src="https://agentmods.dev/badge/skills/easingthemes/dx-aem-flow/aem-verify.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00050 | $0.04296 |
| Opus 5 | $0.00025 | $0.02148 |
| Sonnet 5 | $0.00010 | $0.00859 |
| Haiku 4.5 | $0.00005 | $0.00430 |
Grade A, and why
aem-verify 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 6d 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 — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Platform note: This skill uses context: fork + agent: aem-inspector for isolated execution. If subagent dispatch is unavailable (e.g., VS Code Chat), you may run inline but AEM MCP tools (AEM/*, playwright/*) must be available. If they are not, inform the user: "AEM verification requires AEM and Playwright MCP servers. Please use Claude Code or Copilot CLI."
Applicability Check (Cross-Repo Dependencies)
Before running, determine if AEM verification is meaningful from the current repo alone.
Read .ai/config.yaml for repos section. If the project uses multiple repos (e.g., separate BE and FE):
Backend-only repos:
- CAN verify: dialog changes, HTL template changes, model/exporter JSON data, component definitions
- CANNOT verify: visual rendering that depends on FE code from another repo
- Skip if changes require FE code from a separate frontend repo
Frontend-only repos:
- CAN verify: FE-only changes where the BE is already deployed to AEM (styling, JS behavior, FE rendering)
- CANNOT verify: changes that depend on new BE code not yet deployed
- Skip if changes require BE code from a separate backend repo not yet deployed to AEM
How to determine: Check .ai/specs/*-*/explain.md or .ai/specs/*-*/research.md for "Repos Required" or "Cross-Repo Scope". If the other repo's changes are a prerequisite, skip.
Flow
digraph aem_verify {
"Cross-repo applicability check" [shape=box];
"Applicable from this repo?" [shape=diamond];
"STOP: cross-repo dependency" [shape=doublecircle];
"Existing verification check" [shape=box];
"Previous aem-after.md exists?" [shape=diamond];
"Ask user: overwrite or compare?" [shape=box];
"Load baseline and plan" [shape=box];
"Parallel discovery (dialog + pages)" [shape=box];
"Get current dialog fields" [shape=box];
"Baseline exists?" [shape=diamond];
"Compare with baseline" [shape=box];
"Read site config for scoping" [shape=box];
"Find existing pages" [shape=box];
"Get authored config from page" [shape=box];
"Discover proper test page placement" [shape=box];
"Create or reuse demo page" [shape=box];
"Configure demo data" [shape=box];
"Write verification docs" [shape=box];
"Return summary" [shape=doublecircle];
"Cross-repo applicability check" -> "Applicable from this repo?";
"Applicable from this repo?" -> "STOP: cross-repo dependency" [label="no"];
"Applicable from this repo?" -> "Existing verification check" [label="yes"];
"Existing verification check" -> "Previous aem-after.md exists?";
"Previous aem-after.md exists?" -> "Ask user: overwrite or compare?" [label="yes"];
"Previous aem-after.md exists?" -> "Load baseline and plan" [label="no"];
"Ask user: overwrite or compare?" -> "Load baseline and plan";
"Load baseline and plan" -> "Parallel discovery (dialog + pages)";
"Parallel discovery (dialog + pages)" -> "Get current dialog fields";
"Get current dialog fields" -> "Baseline exists?";
"Baseline exists?" -> "Compare with baseline" [label="yes"];
"Baseline exists?" -> "Read site config for scoping" [label="no"];
"Compare with baseline" -> "Read site config for scoping";
"Read site config for scoping" -> "Find existing pages";
"Find existing pages" -> "Get authored config from page";
"Get authored config from page" -> "Discover proper test page placement";
"Discover proper test page placement" -> "Create or reuse demo page";
"Create or reuse demo page" -> "Configure demo data";
"Configure demo data" -> "Write verification docs";
"Write verification docs" -> "Return summary";
}
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.
- 6d ago First seen · 376 lines · 50 tokens per session scan A 32af143067ee
aem-verify is a skill published in the GitHub repository easingthemes/dx-aem-flow (6 stars, last pushed 4d ago), licensed MIT. It adds 50 tokens to every session and 4,296 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…