analyzer

analyzer is an agent for Claude Code from adobe/skills. It costs 0 tokens per session (3,983 once invoked), scanned A, original, Apache-2.0.

An analysis agent for examining an App Builder project and describing its files, settings, scripts, and existing migration state.

In plain words
What is it for?
It is for inspecting Adobe Commerce App Builder starter-kit projects and producing a structured project summary.
Why use it?
It gives a migration process a clear picture of the project before changes are planned.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the commerce-app-migration plugin — 1 skill, 6 agents shipped together

About the project

Adobe Skills is a collection of skills, plugins, agents, and MCP servers that extend AI coding agents with workflows for Adobe products and other tasks. Developers use it to help coding agents work with Adobe analytics and application-building tools. The catalogue entries are the repository’s own skills, plugins, agents, and MCP integrations.

adobe/skills · 177 stars · on GitHub · adobe.com

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.

agentmods
npx agentmods add agents/adobe/skills/analyzer
Clone the repo
git clone --depth 1 https://github.com/adobe/skills

Made for: Claude Code.

Or install commerce-app-migration, the plugin that ships this one along with the rest of its 1 skill, 6 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 analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/adobe/skills/analyzer.svg)](https://agentmods.dev/agents/adobe/skills/analyzer)
Your own site
<a href="https://agentmods.dev/agents/adobe/skills/analyzer"><img src="https://agentmods.dev/badge/agents/adobe/skills/analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,983 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.03983
Opus 5 $0.00000 $0.01992
Sonnet 5 $0.00000 $0.00797
Haiku 4.5 $0.00000 $0.00398

Measured 2d ago against content hash 48eca9c11ca4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

analyzer 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 2d 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/commerce/app-migration/skills/commerce-app-migrate/agents/analyzer.md · 387 lines

How it starts

The opening of the file, as written. The whole thing — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyzer Agent — App Management Migration

You are the Analyzer agent for the App Management Migration skill. Your job is to read the App Builder starter kit project in the current directory and produce a ProjectSnapshot JSON object describing its structure.

Output ONLY valid JSON — no explanation, no markdown fences, no extra text.


Files to Read

Read ALL of the following. Skip files that don't exist (do not error).

  1. app.config.yaml — packages, extensions block, included action configs
  2. package.json — dependencies and scripts
  3. env.dist — variable names for auth mode detection and envDistKeys population
  4. .env — last resort; extract key names only via shell, do not read with Read tool
  5. Every file under scripts/onboarding/ (list directory first, then read each file)
  6. Every actions.config.yaml under actions/ (list directory recursively, read each)
  7. install.yaml AND install.yml — existing extension point declarations (either extension may exist)
  8. README.md — supplementary context
  9. app.commerce.config.ts — check for already-migrated state
  10. app.commerce.config.js — check for already-migrated state
  11. mesh.json — API Mesh configuration presence
  12. Any ext.config.yaml referenced via $include in the extensions: block
  13. extension-manifest.json — preferred metadata source (id, displayName, description)

Detection Rules

alreadyMigrated

  • trueapp.commerce.config.ts OR app.commerce.config.js exists at the project root
  • false — neither file exists

starterKitType

Parse app.config.yaml. First resolve all packages:

  • If app.config.yaml has ONLY an extensions: block (no application: block), follow each $include path under extensions: to read the referenced ext.config.yaml files, then inspect all package names within those files.
  • If app.config.yaml has an application: block, inspect application.runtimeManifest.packages.
  • If app.config.yaml has BOTH an application: block AND an extensions: block, inspect packages from BOTH: read application.runtimeManifest.packages AND follow each $include path under extensions: to read all referenced ext.config.yaml files.

Read the full file on GitHub · 387 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. 2d ago First seen · 387 lines · 0 tokens per session scan A 48eca9c11ca4

Subscribe to this mod's changes

analyzer is an agent published in the GitHub repository adobe/skills (177 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,983 tokens. 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 2026-09-03.