perf-profile

perf-profile is a skill for Claude Code from cenconq25/claude-code-app-studio. It costs 46 tokens per session (2,237 once invoked), scanned A, original, MIT.

A structured performance review for a mobile app covering startup time, frame rate, memory, network speed, app size, and battery use. It compares measurements with targets and identifies bottlenecks.

In plain words
What is it for?
Use it during final polish or before release to profile mobile performance and plan optimizations.
Why use it?
It turns vague reports that an app feels slow or uses too many resources into measured problems with priorities.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; names the AskUserQuestion tool.

Good fit Use it during final polish or before release to profile mobile performance and plan optimizations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cenconq25/claude-code-app-studio/perf-profile
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 cenconq25/claude-code-app-studio --skill perf-profile
Clone the repo
git clone --depth 1 https://github.com/cenconq25/claude-code-app-studio

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 perf-profile

README.md
[![agentmods](https://agentmods.dev/badge/skills/cenconq25/claude-code-app-studio/perf-profile/github.svg)](https://agentmods.dev/skills/cenconq25/claude-code-app-studio/perf-profile)
Your own site
<a href="https://agentmods.dev/skills/cenconq25/claude-code-app-studio/perf-profile"><img src="https://agentmods.dev/badge/skills/cenconq25/claude-code-app-studio/perf-profile/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 perf-profile

Your own site · 80×15
<a href="https://agentmods.dev/skills/cenconq25/claude-code-app-studio/perf-profile"><img src="https://agentmods.dev/badge/skills/cenconq25/claude-code-app-studio/perf-profile.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,237 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 $0.00046 $0.02237
Opus 5 $0.00023 $0.01118
Sonnet 5 $0.00009 $0.00447
Haiku 4.5 $0.00005 $0.00224

Measured 5d ago against content hash 55dc8531218f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

perf-profile 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.

.claude/skills/perf-profile/SKILL.md · 301 lines

How it starts

The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Perf Profile

A repeatable mobile-performance pass. Each metric has a target tool, a budget, a measurement protocol, and a severity rule. The output is a prioritized backlog of optimizations.


Phase 1: Read Budgets

Read .claude/docs/technical-preferences.md for performance budgets. Defaults if unset:

  • Cold start (clean install, no caches): under 2.0s on Tier A iPhone, under 2.5s on Tier A Android, under 3.5s on a low-end device.
  • Warm start: under 1.0s.
  • Frame budget: 16.6 ms at 60fps, 8.3 ms at 120fps. Dropped frames budget: < 0.5% of total frames in a session.
  • Memory after reaching home: under 200 MB on iOS, under 250 MB on Android.
  • App size on disk: under 100 MB iOS, under 150 MB Android (including AAB expansion).
  • Network: first-meaningful-content under 1.5s on 3G; offline path must render in under 500 ms.
  • Battery: idle drain under 5%/hour foreground, under 1%/hour background.

Confirm budgets with the user. Capture the build under test.


Phase 2: Pick Target Metrics

Parse --target. If all, run every metric in order. Otherwise run the requested one(s).

For each metric, the rest of the skill follows the same shape: tool, protocol, capture, compare, recommendation.


Phase 3: Cold Start

Tools:

  • iOS: Instruments -> App Launch template; or xcrun xctrace.
  • Android: adb shell am start -W com.app/.MainActivity; Macrobenchmark StartupBenchmark.
  • React Native: TTI (time-to-interactive) marker via Performance.now() on the home screen mount.
  • Flutter: flutter run --profile --trace-startup.

Protocol:

  1. Force-stop the app.
  2. Reboot the device (or at minimum, kill all background apps).
  3. Wait 30 seconds for OS to settle.
  4. Launch with the chosen tool.
  5. Repeat 5 times; take the median.

Capture: total cold-start time, time-to-first-frame, time-to-interactive.

Common bottlenecks to surface:

  • Synchronous work in the app entry point.
  • Eager initialization of analytics SDKs, RUM, ads SDKs.
  • Hermes / V8 startup overhead — bundle size > 5 MB is suspicious.
  • Auto-loaded modules in MainApplication / AppDelegate.
  • Heavy fonts loaded synchronously.

Read the full file on GitHub · 301 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 · 301 lines · 46 tokens per session scan A 55dc8531218f

Subscribe to this mod's changes

perf-profile is a skill published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 46 tokens to every session and 2,237 once invoked, about $0.0002 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 2026-09-03.

Related

Other skills, from other repositories

orca-emulator-android

Android device and emulator control from inside Orca over adb, with the live device view in Orca's emulator pane. Use when driving an adb-connected emulator or phone on Windows, Linux, or macOS: booting AVDs, taps, swipes, typing, hardware buttons, rotation, app install and launch, runtime permissions, the…

stablyai/orca · 102 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

A guide for authorized security testing of Android apps, covering APK inspection, runtime testing, traffic capture, code review, and function hooking. An APK is the installable package used by an Android app.

Netw0rkNoob/VulnClaw · 32 tokens