dx-aem-flow: Instructions file for Claude Code

CLAUDE.md

dx-aem-flow CLAUDE.md is an instructions file for Claude Code from easingthemes/dx-aem-flow. It costs 9,613 tokens per session, scanned B, original, MIT.

Repository instructions for four Claude Code add-ons that support Azure DevOps work, multi-repository coordination, Adobe Experience Manager checks, and automation. The repository itself is hosted on GitHub and contains Markdown instructions and shell helpers.

In plain words
What is it for?
Use them when developing or maintaining the add-ons, testing changes, handling GitHub branches and pull requests, or coordinating work across several repositories.
Why use it?
They tell the coding agent which tools and workflows belong to this repository, reducing mistakes such as using the wrong source-control service or skipping project-specific checks.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions .claude-plugin; mentions CLAUDE.md.

This is easingthemes/dx-aem-flow's own configuration. It tells Claude Code how to work on dx-aem-flow itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dx-aem-flow configures →

Reuse

Borrowing it

Nothing to install: this file belongs to easingthemes/dx-aem-flow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/easingthemes/dx-aem-flow/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/easingthemes/dx-aem-flow

Made for: Claude Code.

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 dx-aem-flow CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/easingthemes/dx-aem-flow/claude-md/github.svg)](https://agentmods.dev/instructions/easingthemes/dx-aem-flow/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/easingthemes/dx-aem-flow/claude-md"><img src="https://agentmods.dev/badge/instructions/easingthemes/dx-aem-flow/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for dx-aem-flow CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/easingthemes/dx-aem-flow/claude-md"><img src="https://agentmods.dev/badge/instructions/easingthemes/dx-aem-flow/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9,613 This file is loaded in full into every session.
When invoked 9,613 The same file — it is already loaded in full.
Security scan B 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 $0.09613 $0.09613
Opus 5.5 $0.03845 $0.03845
Sonnet 5.5 $0.01923 $0.01923
Haiku 4.5 $0.00961 $0.00961

Measured 9d ago against content hash 61d2daa3a404, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

dx-aem-flow CLAUDE.md scanned grade B 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 9d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Set it in `/config` → Project instructions, or in `~/.claude/settings.json`:
CLAUDE.md · 419 lines

How it starts

The opening of the file, as written. The whole thing — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

This Repo's SCM

This repo is on GitHub (github.com/easingthemes/dx-aem-flow), not Azure DevOps. For any git operation on this repo (branches, PRs, commits, checks), use git and gh CLI — never ADO MCP tools (mcp__ado__repo_*, mcp__ado__pipelines_*). The plugin contents describe ADO workflows for consumer projects; the repo itself is GitHub.

Public Repo — No Consumer Data

This repo is public. Nothing from a consumer project may land in a file, file name, commit message, branch name, PR/issue title, body or comment: org, project, repo, brand or customer names; work-item, PR, build, pipeline or policy IDs; GUIDs; URLs; people's names or emails. Debugging a consumer's pipeline puts exactly these values in context (pasted issues, build logs, .ai/config.yaml), and they have leaked into test fixtures, commit messages and PR descriptions before. Use placeholders — my-org, my-project, my-repo, 12345, [email protected] — and describe evidence generically ("a consumer pipeline run", not its ID). The commit message for such a fix is generic too: say what changed in the code (test: use placeholder values in fixtures), not that data was removed.

Enforced in two places by scripts/check-customer-data.sh, against a denylist that is never committed:

  • CI (.github/workflows/content-check.yml) — diff, paths, commit messages, PR title and body, from the CUSTOMER_DENYLIST repository secret. Re-runs when the PR text is edited. Fork PRs get no secret and skip with a warning.
  • Locally (.claude/hooks/customer-data-guard.sh, PreToolUse on Bash) — blocks git commit/git push/gh pr|issue writes before anything is published, from a gitignored .customer-denylist (one regex per line) or $CUSTOMER_DENYLIST. Inert without a list.

The check reports location and entry number only, never the matched text, because CI logs of a public repo are public too. A hit means fix the text; never quote the term back in a commit or PR to explain it.

Read the full file on GitHub · 419 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. 9d ago Changed · +10 lines · +397 tokens per session 61d2daa3a404
  2. 16d ago Changed a566c2a0cd05
  3. 20d ago Changed · +1 lines · +110 tokens per session 9857bd9ad03b
  4. 21d ago Changed · +1 lines · +276 tokens per session e162b7af7169
  5. 22d ago Changed · +9 lines · +938 tokens per session a7e767a06b4b
  6. 1mo ago Changed · +2 lines · +446 tokens per session b2aa36c96a66
  7. 1mo ago Changed · +20 lines · +524 tokens per session scan A → B d45f790ef5c4
  8. 1mo ago Changed · +5 lines · +504 tokens per session f54b1c4f3e3a
  9. 1mo ago Changed · +4 lines · +143 tokens per session scan B → A 8619665c8432
  10. 2mo ago First seen · 367 lines · 6,275 tokens per session scan B f43cba1fa86e

Subscribe to this mod's changes

dx-aem-flow CLAUDE.md is an instructions file published in the GitHub repository easingthemes/dx-aem-flow (7 stars, last pushed 2d ago), licensed MIT. It adds 9,613 tokens to every session, about $0.0385 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

dx-aem-flow CLAUDE.md compared with instructions from other repositories

dx-aem-flow CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
dx-aem-flow CLAUDE.mdeasingthemes/dx-aem-flowInstructions file72d agoMITB9,613Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode