aso

aso is a command for Claude Code from fatihkan/badi. It costs 0 tokens per session (1,009 once invoked), scanned A, original, MIT.

An App Store Optimization tool for analyzing iPhone and iPad app listings. App Store Optimization means improving an app's store page so it is easier to find and more appealing to potential users.

In plain words
What is it for?
Use it to audit your app, compare it with another app, research keywords, or prepare metadata for a new listing using the iTunes API.
Why use it?
It helps replace guesswork with checks of listing details, search terms, reviews, and competing apps.

Command for Claude Code

Part of the badi plugin — 28 commands, 30 agents 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 commands/fatihkan/badi/aso
Clone the repo
git clone --depth 1 https://github.com/fatihkan/badi

Made for: Claude Code.

Or install badi, the plugin that ships this one along with the rest of its 28 commands, 30 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 aso

README.md
[![agentmods](https://agentmods.dev/badge/commands/fatihkan/badi/aso.svg)](https://agentmods.dev/commands/fatihkan/badi/aso)
Your own site
<a href="https://agentmods.dev/commands/fatihkan/badi/aso"><img src="https://agentmods.dev/badge/commands/fatihkan/badi/aso.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 1,009 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 $0.00000 $0.01009
Opus 5 $0.00000 $0.00504
Sonnet 5 $0.00000 $0.00202
Haiku 4.5 $0.00000 $0.00101

Measured 4d ago against content hash d5cc0a1ba125, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aso 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 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.

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.

.claude/commands/aso.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

App Store Optimization command. iOS app listing analysis via the iTunes API, keyword optimization, and competitor comparison.

Required Tools

  • Bash (badi aso commands)

Procedure

Step 1: Set the Target

Ask the user: "What do you want to analyze?"

  • Your own app — Audit + keywords + reviews
  • Competitor comparison — 2 apps side-by-side
  • Keyword research — Market discovery
  • New app metadata — Listing preparation

The App ID is required: take it from the https://apps.apple.com/app/id[APP_ID] URL.

2026 Algorithm Reality (verify live — read the audit through these)

The store algorithms shifted in 2026; re-verify since they keep moving:

  • Apple ranks on LLM semantic relevance + behavior — write metadata for MEANING, not exact-match fragments; a natural, topically-dense title/subtitle now ranks better than a keyword-stuffed 100-char field. Core limits are UNCHANGED (Title 30 / Subtitle 30 / Keywords 100).
  • Apple Search Ads took a second, in-organic slot — paid results now sit where high organic positions used to convert; discount organic-install forecasts on high-intent/branded terms and treat defending your own brand keywords with paid as near-mandatory in competitive categories.
  • Discovery extends beyond the listing — declaring App Intents + indexing content as Spotlight entities surfaces the app in Spotlight / Siri / Apple Intelligence; treat it as an ASO task, not just engineering.
  • Screenshot captions are indexed — put real target keywords in the first 1–3 screenshot captions (a de-facto extra indexed field; verify per app, Apple hasn't documented it).
  • Custom Product Pages expanded (up to 70, keyword-assignable) — build per-query/segment CPPs for incremental organic surface + tailored conversion.
  • AI review summaries — users read an AI-generated summary built from recurring review themes; manage the themes (drive feature mentions, resolve recurring complaints), not just the star average.
  • Google Play (I/O 2026) — optimize for "Ask Play" answer-style AI search (clear functional descriptions that map to user questions), front-load the Short Description with primary functional keywords, treat technical health (ANR / battery / retention) as ranking inputs, and use Gemini keyword-targeted custom store listings + Play Shorts where eligible.

Read the full file on GitHub · 120 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. 4d ago First seen · 120 lines · 0 tokens per session scan A d5cc0a1ba125

Subscribe to this mod's changes

aso is a command published in the GitHub repository fatihkan/badi (7 stars, last pushed 18d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,009 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 2026-08-31.