soak-test

soak-test is a skill for Claude Code from cenconq25/claude-code-app-studio. It costs 48 tokens per session (1,872 once invoked), scanned A, original, MIT.

A protocol for testing a mobile app during long sessions, including overnight use. It tells a person what to observe and record but does not run the test itself.

In plain words
What is it for?
Use it during release preparation to test idle use, core flows, backgrounding, unstable networks, push notifications, and low-memory conditions.
Why use it?
Short tests can miss memory leaks, battery drain, background crashes, network recovery failures, and other slow-building problems.

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 release preparation to test idle use, core flows, backgrounding, unstable networks, push notifications, and low-memory conditions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cenconq25/claude-code-app-studio/soak-test
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 soak-test
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 soak-test

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/cenconq25/claude-code-app-studio/soak-test"><img src="https://agentmods.dev/badge/skills/cenconq25/claude-code-app-studio/soak-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,872 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 $0.00048 $0.01872
Opus 5 $0.00024 $0.00936
Sonnet 5 $0.00010 $0.00374
Haiku 4.5 $0.00005 $0.00187

Measured 6d ago against content hash 92dde8afbc83, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

soak-test 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.

.claude/skills/soak-test/SKILL.md · 238 lines

How it starts

The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Soak Test

Most mobile bugs are not visible in a 5-minute test. This skill produces a written protocol that a human runs over hours (or overnight) to surface slow-burn issues: leaks, watchdog kills, queue overflow, network recovery, push-during-background, and battery cost.

This skill writes a protocol document. It does not execute the soak.


Phase 1: Inputs

Parse arguments:

  • --duration=Nh — total session length. Default 4 hours; release-gate recommends 8 hours overnight on a charger.
  • --scenario=<name> — pick from a known list: idle, core-loop, background-mix, network-flap, push-storm, low-memory-device. Default: a balanced mix.

If no scenario is provided, propose options via AskUserQuestion.

Read the current milestone and recent bug history to choose the device matrix:

  • production/milestones/ — current target platforms.
  • production/qa/bugs/ — recent S1/S2 bugs grouped by symptom (crashes, ANRs, freezes, memory).

Phase 2: Pick the Devices

Read .claude/docs/technical-preferences.md for Target Platforms. Propose a soak device set:

  • 1 Tier A device per platform (representative high-end).
  • 1 Tier C device per platform (representative low-end / low-RAM).
  • 1 device known to have reproduced a recent S1/S2.

A single soak run should cover at least one iPhone, one Android, and one constrained device. Confirm with the user.


Phase 3: Choose Observability Tools

The protocol references these tools by platform:

  • iOS: Instruments (Allocations, Leaks, Time Profiler), Console.app for logs, MetricKit reports, Xcode Memory Graph.
  • Android: Android Profiler (Memory, CPU, Network, Energy), Logcat, StrictMode, ANR traces under /data/anr/, perfetto.
  • Cross-platform telemetry: Sentry, Firebase Crashlytics, Datadog RUM, custom analytics.
  • Battery: iOS Settings -> Battery; Android adb dumpsys batterystats.

Ask which tools are wired into the build. A soak with no telemetry is a blind soak — propose adding telemetry first.

Read the full file on GitHub · 238 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 · 238 lines · 48 tokens per session scan A 92dde8afbc83

Subscribe to this mod's changes

soak-test is a skill published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 1,872 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

android_ui_verification

Automated end-to-end UI testing and verification on an Android Emulator using ADB.

sickn33/agentic-awesome-skills · 22 tokens

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.

alipay/SoloPi · 127 tokens

agent-device

Automates Apple-platform apps (iOS, tvOS, macOS), Android devices, and Amazon Vega OS TV apps in Vega Virtual Devices. Use when navigating apps, taking snapshots/screenshots where supported, driving TV remotes, tapping, typing, scrolling, extracting UI info, collecting evidence, or planning agent-device CLI commands.

callstack/agent-device · 69 tokens

ios-simulator

Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.

callstack/agent-device · 69 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

eas-simulator

EAS service (paid). Run and control a user's app on a remote iOS/Android simulator hosted on EAS cloud. Read before running any eas simulator: commands - it has the current syntax for this experimental API. Use whenever the user needs a simulator they can't run locally - 'run my app on a cloud simulator', 'use eas…

expo/skills · 249 tokens