app-analyzer

A two-stage tool for examining an Android app or website. It maps screens and navigation, then produces a report about the product, user experience, design, and business model.

In plain words
What is it for?
Use it to study competitor apps, document navigation flows, review user experience, extract design patterns, and compare Android or web products.
Why use it?
It replaces a manual, inconsistent review with a structured record of how the app or site works. It can also separate basic navigation mapping from the deeper analysis.

Agent

Part of the app-analyzer plugin — 1 agent shipped together

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/acaprino/daodan/app-analyzer
Clone the repo
git clone --depth 1 https://github.com/acaprino/daodan

Or install app-analyzer, the plugin that ships this one along with the rest of its 1 agent.

Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,915 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 $0.00051 $0.03915
Opus 5 $0.00026 $0.01958
Sonnet 5 $0.00010 $0.00783
Haiku 4.5 $0.00005 $0.00392

Measured 3d ago against content hash 8f51ea77adfa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

app-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 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.

exports/claude/plugins/app-analyzer/agents/app-analyzer.md · 416 lines

How it starts

The opening of the file, as written. The whole thing — 416 lines — stays where its author put it; the contents beside it link to each section on GitHub.

app-analyzer

Unified app analysis for Android (ADB) and web (Playwright MCP). Auto-detects platform. Phase 1: exhaustive navigation mapping. Phase 2: competitive intelligence report. User can stop after Phase 1.

Protocol Abstraction

Abstract operations with platform-specific implementations:

Operation ADB (Android) Playwright MCP (Web)
capture_screen adb exec-out screencap -p > file.png browser_take_screenshot
read_structure adb shell uiautomator dump + parse XML browser_snapshot (accessibility tree)
interact_tap adb shell input tap X Y browser_click
interact_fill adb shell input text "..." browser_fill_form
navigate_back adb shell input keyevent 4 browser_press_key Escape or back button
scroll adb shell input swipe ... browser_press_key PageDown
wait sleep 1 browser_wait_for

Phase 0: Setup & Platform Detection

Detect platform

  1. Check if ADB device connected:
    adb devices
    
    • Device listed -> mobile mode (Android/ADB)
  2. If no ADB device, check if URL provided and Playwright MCP tools available -> web mode
  3. If neither: STOP and tell user to connect a device or provide a URL

Web mode dependency check

Web mode requires the playwright-skill plugin for Playwright MCP tools (browser_navigate, browser_snapshot, browser_click, etc.). If Playwright MCP tools are not available, STOP and tell the user:

Missing required plugin: playwright-skill

The app-analyzer agent requires Playwright MCP tools for web app analysis.
playwright-skill is a declared dependency, distributed by its own upstream
marketplace. Install it with:
  claude plugin marketplace add lackeyjb/playwright-skill
  claude plugin install playwright-skill@playwright-skill

Initialize output

mkdir -p .app-analyzer/screenshots

Initialize or load .app-analyzer/sitemap.json (if resuming from a previous session).

Read the full file on GitHub · 416 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. 3d ago First seen · 416 lines · 51 tokens per session scan A 8f51ea77adfa

Subscribe to this mod's changes

app-analyzer is an agent published in the GitHub repository acaprino/daodan (8 stars, last pushed 7d ago), licensed MIT. It adds 51 tokens to every session and 3,915 once invoked, about $0.0003 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.