permissions

permissions is a skill for Claude Code, Codex from piyushverma0/android-agent-skills. It costs 83 tokens per session (1,155 once invoked), scanned A, original, MIT.

A guide for handling Android runtime permissions, which are access requests shown to users for features such as the camera, location, microphone, contacts, notifications, and Bluetooth.

In plain words
What is it for?
Use it when building Android features that request, check, or respond to one or more device permissions, especially in Jetpack Compose.
Why use it?
It helps avoid incorrect permission flows, including missing explanations when a user denies access or asks why a feature needs it.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when building Android features that request, check, or respond to one or more device permissions, especially in Jetpack Compose.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/piyushverma0/android-agent-skills/permissions
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 piyushverma0/android-agent-skills --skill permissions
Clone the repo
git clone --depth 1 https://github.com/piyushverma0/android-agent-skills

Made for: Claude Code, Codex.

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 permissions

README.md
[![agentmods](https://agentmods.dev/badge/skills/piyushverma0/android-agent-skills/permissions/github.svg)](https://agentmods.dev/skills/piyushverma0/android-agent-skills/permissions)
Your own site
<a href="https://agentmods.dev/skills/piyushverma0/android-agent-skills/permissions"><img src="https://agentmods.dev/badge/skills/piyushverma0/android-agent-skills/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.

agentmods 80×15 button for permissions

Your own site · 80×15
<a href="https://agentmods.dev/skills/piyushverma0/android-agent-skills/permissions"><img src="https://agentmods.dev/badge/skills/piyushverma0/android-agent-skills/permissions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,155 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 $0.00083 $0.01155
Opus 5 $0.00042 $0.00577
Sonnet 5 $0.00017 $0.00231
Haiku 4.5 $0.00008 $0.00115

Measured 10d ago against content hash e8c0b04d6677, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

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 10d 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/permissions/SKILL.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Android Runtime Permissions

Rule 1: Always use Accompanist Permissions in Compose

implementation(libs.accompanist.permissions)
// ✅ Single permission
@OptIn(ExperimentalPermissionsApi::class)
@Composable
fun CameraScreen() {
    val cameraPermission = rememberPermissionState(Manifest.permission.CAMERA)

    when {
        cameraPermission.status.isGranted -> {
            CameraPreview()
        }
        cameraPermission.status.shouldShowRationale -> {
            PermissionRationale(
                title = "Camera required",
                description = "This feature requires camera access to scan items.",
                onRequest = { cameraPermission.launchPermissionRequest() }
            )
        }
        else -> {
            // First time or permanently denied
            LaunchedEffect(Unit) { cameraPermission.launchPermissionRequest() }
        }
    }
}

// ✅ Multiple permissions
@OptIn(ExperimentalPermissionsApi::class)
@Composable
fun LocationScreen() {
    val locationPermissions = rememberMultiplePermissionsState(
        listOf(
            Manifest.permission.ACCESS_FINE_LOCATION,
            Manifest.permission.ACCESS_COARSE_LOCATION
        )
    )

    when {
        locationPermissions.allPermissionsGranted -> LocationContent()
        locationPermissions.shouldShowRationale -> PermissionRationale(
            title = "Location required",
            description = "We need your location to show nearby items.",
            onRequest = { locationPermissions.launchMultiplePermissionRequest() }
        )
        else -> LaunchedEffect(Unit) { locationPermissions.launchMultiplePermissionRequest() }
    }
}

Rule 2: Rationale dialog — always explain before requesting

// ✅ Standard permission rationale composable
@Composable
fun PermissionRationale(
    title: String,
    description: String,
    onRequest: () -> Unit,
    onDismiss: () -> Unit = {},
    onOpenSettings: (() -> Unit)? = null
) {
    AlertDialog(
        onDismissRequest = onDismiss,
        icon = { Icon(Icons.Default.Info, contentDescription = null) },
        title = { Text(title) },
        text = { Text(description) },
        confirmButton = {
            TextButton(onClick = onRequest) { Text("Grant permission") }
        },
        dismissButton = {
            if (onOpenSettings != null) {
                TextButton(onClick = onOpenSettings) { Text("Open settings") }
            } else {
                TextButton(onClick = onDismiss) { Text("Not now") }
            }
        }
    )
}

// ✅ Open app settings when permanently denied
fun Context.openAppSettings() {
    startActivity(Intent(Settings.ACTION_APPLICATION_DETAILS_SETTINGS).apply {
        data = Uri.fromParts("package", packageName, null)
    })
}

Read the full file on GitHub · 167 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. 10d ago First seen · 167 lines · 83 tokens per session scan A e8c0b04d6677

Subscribe to this mod's changes

permissions is a skill published in the GitHub repository piyushverma0/android-agent-skills (15 stars, last pushed 4mo ago), licensed MIT. It adds 83 tokens to every session and 1,155 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 2026-08-30.