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/easingthemes/dx-aem-flow/claude-mdgit 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/instructions/easingthemes/dx-aem-flow/claude-md)<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="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 | $0.06275 | $0.06275 |
| Opus 5 | $0.03138 | $0.03138 |
| Sonnet 5 | $0.01255 | $0.01255 |
| Haiku 4.5 | $0.00628 | $0.00628 |
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 4d 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.
`claude plugin eval` is in early access and gated per organization; if it prints `` `plugin eval` is currently in early access ``, enablement has not reached the machine (some clients need a variable Anthropic provides d How it starts
The opening of the file, as written. The whole thing — 367 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.
What This Is
Four Claude Code plugins for AI-assisted Azure DevOps development workflows. There is no build system — plugins are pure Markdown (skills, agents, rules, templates) with shell helper scripts.
- dx-core (
plugins/dx-core/) — Platform-agnostic ADO/Jira workflow: requirements → planning → execution → review → PR. Works with any tech stack. Skills prefixeddx-*. - dx-hub (
plugins/dx-hub/) — Multi-repo orchestration: hub init, config, status. Skills prefixeddx-hub-*. - dx-aem (
plugins/dx-aem/) — AEM-specific verification, QA, and demo capture. Includes AEM project knowledge (seed data). Requires dx. Skills prefixedaem-*. - dx-automation (
plugins/dx-automation/) — Autonomous AI agents (DoR checker, DoD checker, DoD fixer, PR reviewer, PR answerer, BugFix agent, QA agent, DevAgent, DOCAgent, Estimation, SimpleAgent) running 24/7 as ADO pipelines. Most are triggered by AWS Lambda webhooks; SimpleAgent, BugFix, and DoR are triggered by Azure-native Service Hooks (no Lambda) — a work-item comment containing the agent's token (@kai-simple,@kai-bugfixon a Bug,@kai-doron a User Story) fires the pipeline directly via itsresources.webhooksIncoming WebHook. BugFix (/dx-bug-all) adds full resumable recovery over its triage→verify→fix steps (the per-ticketbugfix/<id>-*branch is the durable state store;dx-bug-all.recovery.*config); DoR is a stateless check (no recovery). The remaining WI agents (DoD, QA, DevAgent, DOCAgent, Estimation) still route through the Lambda WI-Router. Requires dx. Skills prefixedauto-*.- SimpleAgent (
@kai-simplecomment trigger) applies small AEM changes (a11y / color / spacing / copy) by splitting work into authoring (AEM MCP write) or code (file edits → PR) paths. 9 confidence gates; ≤5 files / ≤50 lines / ≤10 JCR writes. Backed by the/dx-simpleskill in dx-core. Trigger is fully Azure-native (no Lambda): a comment containing the configured token (default@kai-simple;dx-simple.recovery.trigger-token) on the work item fires an ADO Service Hook (event work item commented on, filter comment contains the token) → an Incoming WebHook service connection → the pipeline'sresources.webhookslistener. The same event covers both the first run and recovery — the Lambdawi-router.mjsis not in this path (itsAGENTSarray has nosimpleentry). Resumable recovery (TODO #141): the per-ticket git branch is a durable state store — every phase/gate checkpointsresume-state.json(viascripts/save-state.sh); Phase 0 (scripts/resume-check.sh) discovers the branch by anchored ticket-id match and dispatches onstatus(fresh run vs. resume). A blocked/crashed run resumes when a human replies the token again. Token + attempt cap are config (dx-simple.recovery.*); requires.ai/specs/tracked in git; recovery is human-re-triggered, never automatic.
- SimpleAgent (
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.
- 4d ago First seen · 367 lines · 6,275 tokens per session scan B f43cba1fa86e
dx-aem-flow CLAUDE.md is an instructions file published in the GitHub repository easingthemes/dx-aem-flow (6 stars, last pushed 3d ago), licensed MIT. It adds 6,275 tokens to every session, about $0.0314 per session on Opus 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.
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.