lpm: Skill for Claude Code

.claude/skills/edge-to-edge/SKILL.md

edge-to-edge is a skill for Claude Code from gug007/lpm. It costs 67 tokens per session (3,320 once invoked), scanned A, a copy of edge-to-edge, MIT.

A guide for making an Android app built with Jetpack Compose place content correctly around the status and navigation bars. Jetpack Compose is Android's toolkit for building app screens in Kotlin.

In plain words
What is it for?
Use it to migrate an app to edge-to-edge display, apply system-bar spacing, configure keyboard resizing, and check that important controls remain visible and tappable.
Why use it?
It fixes content hidden behind system bars and prevents the on-screen keyboard from covering input fields, buttons, lists, or floating action buttons.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is gug007/lpm's own configuration. It tells Claude Code how to work on lpm itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything lpm configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gug007/lpm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/gug007/lpm/main/.claude/skills/edge-to-edge/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/gug007/lpm

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 edge-to-edge

README.md
[![agentmods](https://agentmods.dev/badge/skills/gug007/lpm/edge-to-edge/github.svg)](https://agentmods.dev/skills/gug007/lpm/edge-to-edge)
Your own site
<a href="https://agentmods.dev/skills/gug007/lpm/edge-to-edge"><img src="https://agentmods.dev/badge/skills/gug007/lpm/edge-to-edge/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 edge-to-edge

Your own site · 80×15
<a href="https://agentmods.dev/skills/gug007/lpm/edge-to-edge"><img src="https://agentmods.dev/badge/skills/gug007/lpm/edge-to-edge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,320 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 98% copy Near-identical to another mod 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 $0.00067 $0.03320
Opus 5.5 $0.00027 $0.01328
Sonnet 5.5 $0.00013 $0.00664
Haiku 4.5 $0.00007 $0.00332

Measured 6d ago against content hash 4ca04cb6a533, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

edge-to-edge 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 6d 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.

Origin

This is a copy

98% identical to edge-to-edge — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/edge-to-edge/SKILL.md · 427 lines

How it starts

The opening of the file, as written. The whole thing — 427 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prerequisites

  • Project MUST use Android Jetpack Compose.
  • Project MUST target SDK 35 or later. If the SDK is lower than 35, increase the SDK to 35.

Step 1: plan

  1. Locate and analyze all Activity classes to detect which have existing edge-to-edge support. For every Activity without edge-to-edge, plan to make each Activity edge-to-edge.
  2. In each Activity, Locate and analyze all lists and FAB components to detect which have existing edge-to-edge support. For every component without edge-to-edge support, plan to make each of these components edge-to-edge.
  3. In each Activity, scan for TextField, OutlinedTextField, or BasicTextField. If found, then you MUST verify the IME doesn't hide the input field by following the IME section of this skill.

Step 2: add edge-to-edge support

  1. Add enableEdgeToEdge before setContent in onCreate in each Activity that does not already call enableEdgeToEdge.
  2. Add android:windowSoftInputMode="adjustResize" in the AndroidManifest.xml for all Activities that use a soft keyboard.

Step 3: apply insets

  • The app MUST apply system insets, or align content to rulers, so critical UI remains tappable. Choose only one method to avoid double padding:

    1. PREFERRED: When available, use Scaffolds and pass PaddingValues to the content lambda.
    Scaffold { innerPadding ->
        // innerPadding accounts for system bars and any Scaffold components
        LazyColumn(
            modifier = Modifier
                .fillMaxSize()
                .consumeWindowInsets(innerPadding),
            contentPadding = innerPadding
        ) { /* Content */ }
    }
    
    1. PREFERRED: When available, use the automatic inset handling or padding modifiers in material components.

      • Material 3 Components manages safe areas for its own components, including:
        • TopAppBar
        • SmallTopAppBar
        • CenterAlignedTopAppBar
        • MediumTopAppBar
        • LargeTopAppBar
        • BottomAppBar
        • ModalDrawerSheet
        • DismissibleDrawerSheet
        • PermanentDrawerSheet
        • ModalBottomSheet
        • NavigationBar
        • NavigationRail
      • For Material 2 Components, use the windowInsetsparameter to apply insets manually for BottomAppBar, TopAppBar and BottomNavigation. DO NOT apply padding to the parent container; instead, pass insets directly to the App Bar component. Applying padding to the parent container prevents the App Bar background from drawing into the system bar area. For example, for TopAppBar, choose only one of the following options:
        1. PREFERRED: TopAppBar(windowInsets = AppBarDefaults.topAppBarWindowInsets)
        2. TopAppBar(windowInsets = WindowInsets.systemBars.exclude(WindowInsets.navigationBars))
        3. TopAppBar(windowInsets = WindowInsets.systemBars.add(WindowInsets.captionBar))
    2. For components outside a Scaffold, use padding modifiers, such as Modifier.safeDrawingPadding() or Modifier.windowInsetsPadding(WindowInsets.safeDrawing).

Read the full file on GitHub · 427 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. 6d ago First seen · 427 lines · 67 tokens per session scan A 4ca04cb6a533

Subscribe to this mod's changes

edge-to-edge is a skill published in the GitHub repository gug007/lpm (145 stars, last pushed today), licensed MIT. It adds 67 tokens to every session and 3,320 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 98% identical to edge-to-edge, differing in 0 lines, and is treated as a copy.