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.
npx skills add ofcskn/mobile-automation-plugin --skill managing-app-permissionsgit clone --depth 1 https://github.com/ofcskn/mobile-automation-pluginWrote 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.
[](https://agentmods.dev/skills/ofcskn/mobile-automation-plugin/managing-app-permissions)<a href="https://agentmods.dev/skills/ofcskn/mobile-automation-plugin/managing-app-permissions"><img src="https://agentmods.dev/badge/skills/ofcskn/mobile-automation-plugin/managing-app-permissions/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.
<a href="https://agentmods.dev/skills/ofcskn/mobile-automation-plugin/managing-app-permissions"><img src="https://agentmods.dev/badge/skills/ofcskn/mobile-automation-plugin/managing-app-permissions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00072 | $0.00390 |
| Opus 5 | $0.00036 | $0.00195 |
| Sonnet 5 | $0.00014 | $0.00078 |
| Haiku 4.5 | $0.00007 | $0.00039 |
Grade A, and why
managing-app-permissions 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 8d 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.
What it actually says
Managing App Permissions
Why permissions cause rejections
Apple rejects apps that:
- Declare a permission (e.g. NSCameraUsageDescription) with an empty or generic string
- Request permissions not used in the app binary
- Use APIs that require permissions without declaring them
- Use NSTrackingUsageDescription without ATT framework implementation
Google rejects apps that:
- Request sensitive permissions not justified by core functionality
- Use deprecated permissions (READ_EXTERNAL_STORAGE without media alternatives)
- Declare ACCESS_BACKGROUND_LOCATION without foreground location approval
iOS permission rules
All NS*UsageDescription strings must:
- Be non-empty
- Explain WHY the app needs the permission (not just WHAT it does)
- Be in the user's language (localize for non-English markets)
❌ Bad: "Camera access" ✅ Good: "Used to scan QR codes for adding contacts"
Android permission rules
Permissions are declared in app.json under expo.android.permissions[].
Only declare permissions your app actually uses.
Dangerous permissions (CAMERA, LOCATION, CONTACTS, etc.) trigger runtime dialogs.
Process
- Read app's
app.jsonorapp.config.ts - Extract iOS infoPlist NS*UsageDescription entries
- Extract Android permissions array
- Validate each iOS entry has a meaningful description (not empty, not generic)
- Flag dangerous Android permissions and confirm they're intentional
- Optionally scan source code to detect permission API usage
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 49 lines · 72 tokens per session scan A 4554bc72a147
managing-app-permissions is a skill published in the GitHub repository ofcskn/mobile-automation-plugin (2 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 390 once invoked, about $0.0004 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.
Other skills, from other repositories
android-ui-journey-testing
XML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.
solopi-ai
A command-line framework for testing Android apps and devices with SoloPi, including on-device or cloud AI decision models. It manages devices, test cases, recorded interactions, replays, performance history, and evidence.
app-store-preflight-compliance
Pre-submission compliance scanner workflow for Apple App Store apps. Use when reviewing iOS, macOS, tvOS, watchOS, or visionOS projects (Swift, Objective-C, React Native, Expo) for App Store rejection risks, submission readiness, privacy compliance, or guideline violations.
uniwind
Uniwind — Tailwind CSS v4 styling for React Native. Use when adding, building, or debugging components in a React Native project that uses Uniwind classNames. Covers setup, Metro config, global.css, theming, className props, accent- color props, platform/data/state/responsive variants, CSS variables, custom utilities…
e2e-testing
AI-powered E2E testing for any app — Flutter, React Native, iOS, Android, Electron, Tauri, KMP, .NET MAUI. Connects via MCP to running apps so the agent can take screenshots, tap elements, enter text, scroll, inspect UI trees, and verify state with natural language. Use when the user wants to test an app's UI…
Appium Mobile Testing
Mobile application testing skill using Appium for iOS and Android, covering device capabilities, selectors, gestures, and cross-platform testing strategies.