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 instructions/adobe/aem-desktop/claude-mdgit clone --depth 1 https://github.com/adobe/aem-desktopWrote 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/instructions/adobe/aem-desktop/claude-md)<a href="https://agentmods.dev/instructions/adobe/aem-desktop/claude-md"><img src="https://agentmods.dev/badge/instructions/adobe/aem-desktop/claude-md.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 | $0.03717 | $0.03717 |
| Opus 5 | $0.01858 | $0.01858 |
| Sonnet 5 | $0.00743 | $0.00743 |
| Haiku 4.5 | $0.00372 | $0.00372 |
Grade A, and why
aem-desktop CLAUDE.md 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 3d 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Navigation hub and working agreement for the AEM Desktop app — a desktop shell for Adobe Experience Manager Edge Delivery Services. This file is the first thing to read before making changes.
AGENTS.mdis a symlink to this file.
What this is
An Electron desktop application. Today it is an empty shell (window + version readout); the point of this repository is the development environment around it: auto-update and a signed, notarized release pipeline so feature work can start on a solid foundation.
Deliberate stack choices (kept close to @adobe/aem-cli / helix-cli, not slicc):
- Pure ESM JavaScript — no TypeScript, no bundler. The renderer is plain
ESM over
file://; the main process is ESM run directly by Electron. - No Vite / webpack. No bundler runtime; reload the renderer with Cmd+R (see below).
node --testfor unit and integration tests (no Mocha/Vitest).- ESLint with
@adobe/eslint-config-helix(Apache headers enforced). No Prettier. - electron-builder for packaging/signing/notarization, electron-updater for in-app updates, semantic-release to drive versioning and releases.
Module map
| Path | Purpose |
|---|---|
src/main/index.js |
App entry: lifecycle, BrowserWindow, IPC, menu, updater, UA, dev console |
src/main/window-options.js |
Pure builder of secure BrowserWindow options (unit tested) |
src/main/update-policy.js |
Pure shouldAutoUpdate() decision (unit tested) |
src/main/updater.js |
electron-updater wiring against the GitHub release feed |
src/main/logger.js |
Shared electron-log logger (use instead of console.log) |
src/main/dev-config.js |
Pure dev helpers: CDP port + screenshot filename (unit tested) |
src/main/dev-console.js |
Forwards the renderer console to the dev terminal (dev only) |
src/main/cli-install.js |
Installs the content CLI launcher on PATH (pure builders unit tested) |
src/main/source-log.js |
Pure reducer of api.aem.live audit-log entries → source changes (tested) |
src/main/user-agent.js |
Pure builder of the AEM-Desktop user-agent token (unit tested) |
src/main/aem-guard.js |
Guards the .aem pristine store: read-only originals + README/.gitignore deterrents (tested) |
src/preload/index.cjs |
Sandboxed contextBridge API — the only CommonJS file (see note) |
src/renderer/ |
index.html + renderer.js + styles.css — the UI shell |
src/cli/content.js |
The content CLI entry (sites/download/update/upload); Node-only |
src/cli/cli-lib.js |
Pure CLI arg parser + site selector (unit tested) |
scripts/dev.js |
Dev launcher: runs Electron once with CDP (no auto-reload; Cmd+R instead) |
test/ |
node --test unit + config integration tests |
build/ |
electron-builder resources (entitlements; add icons here) |
electron-builder.yml |
Packaging, signing, notarization, DMG layout, GitHub publish target |
.releaserc.cjs |
semantic-release plugin chain (build → attach artifacts → tag) |
.github/workflows/ |
main.yaml (lint/test/build smoke on mac+win), release.yaml (mac+win release) |
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.
- 3d ago First seen · 254 lines · 3,717 tokens per session scan A bfb267358639
aem-desktop CLAUDE.md is an instructions file published in the GitHub repository adobe/aem-desktop (2 stars, last pushed 8d ago), licensed Apache-2.0. It adds 3,717 tokens to every session, about $0.0186 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.