appscope

appscope is a skill for Claude Code, Codex from Ahad690/open-app-intel. It costs 103 tokens per session (1,403 once invoked), scanned A, original, MIT.

A self-hosted app-market research tool that stores locally captured iOS and Android app data, such as rankings, store details, install ranges, and reviews. It produces download and revenue estimates as labelled ranges rather than claimed facts.

In plain words
What is it for?
Tracking competing apps, checking app-store rankings and reviews, researching app-store optimisation, and producing evidence-labelled download or revenue estimates.
Why use it?
It helps analyse app markets while showing how reliable each number is and refusing unsupported figures, such as invented ad spending or ungrounded install counts.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the appscope plugin — 1 skill 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 skills/ahad690/open-app-intel/appscope
Any agent
npx skills add Ahad690/open-app-intel --skill appscope
Clone the repo
git clone --depth 1 https://github.com/Ahad690/open-app-intel

Made for: Claude Code, Codex.

Or install appscope, the plugin that ships this one along with the rest of its 1 skill.

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 appscope

README.md
[![agentmods](https://agentmods.dev/badge/skills/ahad690/open-app-intel/appscope.svg)](https://agentmods.dev/skills/ahad690/open-app-intel/appscope)
Your own site
<a href="https://agentmods.dev/skills/ahad690/open-app-intel/appscope"><img src="https://agentmods.dev/badge/skills/ahad690/open-app-intel/appscope.svg" alt="Measured on agentmods" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,403 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 $0.00103 $0.01403
Opus 5 $0.00051 $0.00701
Sonnet 5 $0.00021 $0.00281
Haiku 4.5 $0.00010 $0.00140

Measured 3d ago against content hash 42aefb0f9d9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

appscope 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.

skills/appscope/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AppScope — honest app market intelligence

Self-hosted app intel from data captured on the user's own machine. Every number is produced by a documented model on real, locally-captured data, with a confidence label, method tag, and flags. The system refuses to fabricate the figures vendors model from private panels.

When to use

The user asks: how many downloads does app X get; estimate an app's revenue; what rank is an app; track a competitor app; app-store market research / ASO intelligence.

Hard rules (NON-NEGOTIABLE)

  1. Never invent an app-market number. Downloads, revenue, ranks, installs, review counts come ONLY from python3 -m appscope.cli ... output. Surface the JSON envelopes verbatim.
  2. Estimates are ranges, capped at MEDIUM confidence. Observed facts (ranks, install buckets, review counts) are HIGH. Never present an estimate as a fact.
  3. Refuse what can't be known: dollar ad spend (intensity proxies only) and panel-grade installs are never modeled. Say so if asked.
  4. Uncalibrated segment → "no data", plus how to fix it (collect Android anchor apps in that category, or refresh_dataset to pull community anchors). Never fill the gap with a guess.
  5. Local-first. The DB, ads, and creator data stay on the machine. Only public calibration anchors are ever shared, opt-in (see Federation).

Run every command from the plugin root: cd ${CLAUDE_PLUGIN_ROOT} && python3 -m appscope.cli <cmd> ... (First run: copy config.sample.json to config.json if missing.)

Workflow

Step 1 — Intake (ONE message)

Ask for: the app (name + a store URL, or the id directly), platform if ambiguous, and country (default us). Resolve the id yourself from a store URL — iOS ids are the digits after /id (e.g. .../id284882215284882215); Android ids are the ?id= package (e.g. ?id=com.spotify.music). If only a name is given, ask for the store link — do NOT guess ids.

Step 2 — Collect (writes are append-only; nothing is overwritten)

python3 -m appscope.cli collect --app <id> — metadata, install buckets (Android), reviews. Add --charts to also capture the Apple top charts (needed for rank-based estimates). Report what was collected.

Read the full file on GitHub · 109 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 · 109 lines · 103 tokens per session scan A 42aefb0f9d9d

Subscribe to this mod's changes

appscope is a skill published in the GitHub repository Ahad690/open-app-intel (0 stars, last pushed 27d ago), licensed MIT. It adds 103 tokens to every session and 1,403 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

foundation-models

On-device LLM integration using Apple's Foundation Models framework. Use when implementing AI text generation, structured output, or tool calling.

rshankras/claude-code-apple-skills · 29 tokens

liquid-glass

Implement Liquid Glass design using .glassEffect() API for iOS/macOS 26+. Covers SwiftUI, AppKit, UIKit, and WidgetKit. Use when creating modern glass-based UI effects.

rshankras/claude-code-apple-skills · 45 tokens

app-icon-generator

Generates an app icon for macOS or iOS — a fast CoreGraphics placeholder and/or flat layered source art to finish in Icon Composer (the Liquid Glass / iOS 26+ standard). Produces appearance variants (light/dark/tinted) and installs into the asset catalog. Use when the user wants to create, generate, iterate, or update…

rshankras/claude-code-apple-skills · 80 tokens

apple-search-ads

Apple Search Ads campaign strategy for indie developers — paid acquisition, keyword bidding, budget planning, and ROAS optimization. Use when user asks about running ads, paid user acquisition, or Apple Search Ads campaigns.

rshankras/claude-code-apple-skills · 46 tokens

app-intents

App Intents for Siri, Shortcuts, Spotlight, and Apple Intelligence integration including intent modes, interactive snippets, visual intelligence, and entity indexing. Use when implementing Siri integration, App Shortcuts, or Spotlight indexing.

rshankras/claude-code-apple-skills · 47 tokens

visual-intelligence

Integrate your app with iOS Visual Intelligence for camera-based search and object recognition. Use when adding visual search capabilities.

rshankras/claude-code-apple-skills · 28 tokens