mobile-deeplink

mobile-deeplink is a skill for Claude Code from berkcangumusisik/claude-code-practices. It costs 17 tokens per session (323 once invoked), scanned A, original, MIT.

A setup and review tool for deep links in React Native and Expo mobile apps. Deep links are URLs that open a particular screen in an installed app, such as a product or account page.

In plain words
What is it for?
Use it to configure or audit links for Expo Router or React Navigation, create iOS and Android link-file templates, and test routes on simulators or emulators.
Why use it?
It helps ensure that app routes, URL schemes, and operating-system settings point to the right screens. It also checks the files needed for iOS Universal Links and Android App Links.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

Good fit Use it to configure or audit links for Expo Router or React Navigation, create iOS and Android link-file templates, and test routes on simulators or emulators.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/berkcangumusisik/claude-code-practices/mobile-deeplink
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.

Any agent
npx skills add berkcangumusisik/claude-code-practices --skill mobile-deeplink
Clone the repo
git clone --depth 1 https://github.com/berkcangumusisik/claude-code-practices

Made for: Claude Code.

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 mobile-deeplink

README.md
[![agentmods](https://agentmods.dev/badge/skills/berkcangumusisik/claude-code-practices/mobile-deeplink/github.svg)](https://agentmods.dev/skills/berkcangumusisik/claude-code-practices/mobile-deeplink)
Your own site
<a href="https://agentmods.dev/skills/berkcangumusisik/claude-code-practices/mobile-deeplink"><img src="https://agentmods.dev/badge/skills/berkcangumusisik/claude-code-practices/mobile-deeplink/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mobile-deeplink

Your own site · 80×15
<a href="https://agentmods.dev/skills/berkcangumusisik/claude-code-practices/mobile-deeplink"><img src="https://agentmods.dev/badge/skills/berkcangumusisik/claude-code-practices/mobile-deeplink.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 323 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 $0.00017 $0.00323
Opus 5 $0.00009 $0.00161
Sonnet 5 $0.00003 $0.00065
Haiku 4.5 $0.00002 $0.00032

Measured 9d ago against content hash 47e211c9973c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mobile-deeplink 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 9d 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/mobile-deeplink/SKILL.md · 45 lines

What it actually says

App scheme: $1 (e.g., myappmyapp://)

  1. Detect navigation library:
cat package.json | grep -E '"@react-navigation"|"expo-router"|"react-native-navigation"'
cat app.json 2>/dev/null | grep -E "scheme\|intentFilters\|associatedDomains"
  1. For Expo Router (file-based):

    • Check app.json for scheme
    • Review app/ directory structure for dynamic routes
    • Generate app/+not-found.tsx if missing
  2. For React Navigation:

    • Review linking config
    • Ensure all screens are mapped
    • Check for missing parameter types
  3. Universal Links / App Links:

    • apple-app-site-association for iOS
    • assetlinks.json for Android
    • Generate templates for both
  4. Testing:

# iOS Simulator
xcrun simctl openurl booted "$1://path/to/screen"

# Android Emulator
adb shell am start -W -a android.intent.action.VIEW -d "$1://path/to/screen"
  1. Generate a deeplink test matrix - all routes with test URLs.
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. 9d ago First seen · 45 lines · 17 tokens per session scan A 47e211c9973c

Subscribe to this mod's changes

mobile-deeplink is a skill published in the GitHub repository berkcangumusisik/claude-code-practices (10 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 323 once invoked, about $0.0001 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.