dx-doc-searcher

dx-doc-searcher is an agent for Claude Code from easingthemes/dx-aem-flow. It costs 47 tokens per session (898 once invoked), scanned A, original, MIT.

A fast lookup helper for project indexes and reference files stored in the .ai directory, including component catalogs, architecture notes, configuration, and file patterns.

In plain words
What is it for?
Use it to find components, architecture patterns, feature context, repository conventions, and project configuration details.
Why use it?
It can answer project-context questions from local reference data without making slower external code-search requests.

Agent for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: model in frontmatter.

Part of the dx-core plugin — 49 skills, 7 agents shipped together

Good fit Use it to find components, architecture patterns, feature context, repository conventions, and…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/easingthemes/dx-aem-flow/dx-doc-searcher
Install

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.

Clone the repo
git clone --depth 1 https://github.com/easingthemes/dx-aem-flow

Made for: Claude Code.

Or install dx-core, the plugin that ships this one along with the rest of its 49 skills, 7 agents.

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-doc-searcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/easingthemes/dx-aem-flow/dx-doc-searcher.svg)](https://agentmods.dev/agents/easingthemes/dx-aem-flow/dx-doc-searcher)
Your own site
<a href="https://agentmods.dev/agents/easingthemes/dx-aem-flow/dx-doc-searcher"><img src="https://agentmods.dev/badge/agents/easingthemes/dx-aem-flow/dx-doc-searcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 898 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00047 $0.00898
Opus 5 $0.00023 $0.00449
Sonnet 5 $0.00009 $0.00180
Haiku 4.5 $0.00005 $0.00090

Measured 6d ago against content hash 39c29a40f9fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

dx-doc-searcher 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.

plugins/dx-core/agents/dx-doc-searcher.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a lookup agent for .ai/ data files — indexes, configuration, and architecture reference. These files exist to avoid expensive MCP calls. They are small, so return ALL matches — never truncate.

What You Receive

A search request with:

  • query — what to look up (component name, topic, feature, pattern)
  • target_areas — which files to search (optional, defaults to all)

Data Files

Files live in .ai/ (core config) and .ai/project/ (seed data — created by /aem-init or /aem-refresh).

Core files (.ai/)

File Purpose
config.yaml Project configuration, SCM, build commands
component-index.md Local repo component scan (generated by /aem-init)
README.md Project overview, workflow summary

Project seed data (.ai/project/)

File Purpose
component-index-project.md Enriched component catalog — platform, FE, source links, dialog fields
project.yaml Repos, brands, markets, platforms, defaults
file-patterns.yaml Source file path conventions per platform
content-paths.yaml AEM content tree structure, language defaults, search config
architecture.md Rendering pipelines, patterns, key libraries
features.md Domain feature documentation

The exact files available vary by project. Not all projects have .ai/project/ files.

Search Procedure

  1. Discover available files — Glob both .ai/*.md, .ai/*.yaml, .ai/project/*.md, and .ai/project/*.yaml to see what's available.

  2. Mandatory component check — If the query could be a component name, ALWAYS check component-index.md AND component-index-project.md regardless of target_areas. This is non-negotiable — component lookups must hit both indexes.

  3. Grep across all files — use multiple keyword variations:

    pattern: {query keywords}
    path: .ai/
    output_mode: content
    context: 5
    

    This covers both .ai/ and .ai/project/ (recursive).

Read the full file on GitHub · 87 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. 6d ago First seen · 87 lines · 47 tokens per session scan A 39c29a40f9fe

Subscribe to this mod's changes

dx-doc-searcher is an agent published in the GitHub repository easingthemes/dx-aem-flow (6 stars, last pushed 5d ago), licensed MIT. It adds 47 tokens to every session and 898 once invoked, about $0.0002 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.