performance

performance is a skill for Claude Code, Codex from liuyi0808/android-review. It costs 79 tokens per session (1,170 once invoked), scanned A, original, MIT.

An Android app performance audit for Kotlin and Jetpack Compose projects. It checks areas such as startup time, dropped frames, memory use, battery use, and background work.

In plain words
What is it for?
Use it before release or when investigating slow startup, frozen screens, memory crashes, unnecessary Compose redraws, battery drain, or excessive network activity.
Why use it?
It helps locate code patterns that make an app slow, unresponsive, memory-hungry, or wasteful with battery and network use. The result is a structured report with priorities and suggested fixes.

Skill for Claude CodeCodex

Part of the android-review plugin — 7 skills 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 skills/liuyi0808/android-review/performance
Any agent
npx skills add liuyi0808/android-review --skill performance
Clone the repo
git clone --depth 1 https://github.com/liuyi0808/android-review

Made for: Claude Code, Codex.

Or install android-review, the plugin that ships this one along with the rest of its 7 skills.

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 performance

README.md
[![agentmods](https://agentmods.dev/badge/skills/liuyi0808/android-review/performance.svg)](https://agentmods.dev/skills/liuyi0808/android-review/performance)
Your own site
<a href="https://agentmods.dev/skills/liuyi0808/android-review/performance"><img src="https://agentmods.dev/badge/skills/liuyi0808/android-review/performance.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,170 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 $0.00079 $0.01170
Opus 5 $0.00039 $0.00585
Sonnet 5 $0.00016 $0.00234
Haiku 4.5 $0.00008 $0.00117

Measured 5d ago against content hash a1f0a68cb7ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

performance 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 5d 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/performance/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Android Performance Audit

Produce a structured audit report with prioritized findings and concrete fixes.

Audit Process

Phase 1: Triage

Scan project structure (build.gradle, AndroidManifest.xml, source tree) to determine which categories apply. SKIP categories with no relevant code.

Category Skip If
Startup No custom Application class, no splash screen
Recomposition No Jetpack Compose (@Composable not found)
Memory No ViewModel / Repository / singleton patterns
ANR No SharedPreferences / BroadcastReceiver / sync I/O
Pagination No list screens or large data sets
Baseline Profiles NEVER skip — always relevant
Battery & Network No background work, location, or network calls

Phase 2: Parallel Scan

Run all relevant categories in PARALLEL using independent Task agents. Each agent:

  1. Grep for the category's anti-patterns (see search guide below)
  2. Read matched files to confirm the finding is real
  3. Return findings in the per-finding format below

Phase 3: Report

Merge parallel results into the final report format below.

Thresholds

Metric Target Critical
Cold start < 500ms > 1000ms
Warm start < 300ms > 600ms
Hot start < 100ms > 200ms
ANR rate < 0.47% > 1%
Crash rate < 1.09% > 2%

Anti-Pattern Search Guide

Grep-ready patterns per category. Only search categories that passed triage.

Startup

  • class \w+ : Application → check onCreate body for heavy sync init
  • ContentProvider in manifest → auto-init SDKs blocking startup
  • Missing reportFullyDrawn() anywhere in codebase

Recomposition

  • List< / MutableList< / ArrayList< in @Composable fun parameters → unstable type, use ImmutableList or @Immutable wrapper
  • { viewModel. or { \w+ViewModel. inline in Composable call sites → lambda recreated every recomposition, extract with remember
  • items( without key = in LazyColumn/LazyRow
  • .value read outside graphicsLayer / Modifier.layout / Modifier.drawBehind → state read triggers full recomposition instead of layout/draw only
  • Missing composeCompiler { reportsDestination } in build.gradle → no compiler metrics

Read the full file on GitHub · 131 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. 5d ago First seen · 131 lines · 79 tokens per session scan A a1f0a68cb7ed

Subscribe to this mod's changes

performance is a skill published in the GitHub repository liuyi0808/android-review (11 stars, last pushed 9d ago), licensed MIT. It adds 79 tokens to every session and 1,170 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.

Related

Other skills, from other repositories

orca-emulator-android

Control an Android emulator / device from inside Orca using the orca CLI. Use for listing/booting AVDs, taps, swipes, typing, hardware buttons (incl. Back and Recents), rotation, app install/launch, runtime permissions, the accessibility tree, and logcat — driving a real adb-connected device or emulator.…

stablyai/orca · 104 tokens

android-tombstone-symbolication

Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…

dotnet/skills · 176 tokens

dogfood

Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.

callstack/agent-device · 55 tokens

winapp-maui

Package and sign .NET MAUI Windows apps with winapp, resolving the resizetizer manifest dependency. Use when packaging or signing a .NET MAUI Windows app, building a MAUI MSIX or signed unpackaged build in CI, or fixing 'manifest contains unresolved placeholders ($placeholder$)' errors from winapp package.

microsoft/winappCli · 71 tokens

apple-search-ads

When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT"…

Eronred/aso-skills · 127 tokens

android-pentest

安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.

Netw0rkNoob/VulnClaw · 32 tokens