A guide to ADB, the Android Debug Bridge used to connect a computer to Android devices and run commands on them.

Use it to connect by USB or wireless debugging, select among multiple devices, run shell commands, install APK files, inspect logs, and automate or diagnose Android devices.

It provides standard ways to connect devices, handle connection problems, inspect the system, install apps, capture logs, and investigate crashes.

android — Skill by hyperb1iss

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/hyperb1iss/hyperdroid-skill/android

Any agent

npx skills add hyperb1iss/hyperdroid-skill --skill android

Clone the repo

git clone --depth 1 https://github.com/hyperb1iss/hyperdroid-skill

Made for: Claude Code, Codex.

Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,230 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.

Model	Per session	Once invoked
Fable 5	$0.00085	$0.02230
Opus 5	$0.00043	$0.01115
Sonnet 5	$0.00017	$0.00446
Haiku 4.5	$0.00009	$0.00223

Measured yesterday against content hash f6e18aa9902f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

android 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 yesterday.

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/android/SKILL.md · 385 lines

How it starts

The opening of the file, as written. The whole thing — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Android Device Mastery

This skill covers everything about interacting with Android devices via ADB and shell commands.

Device Connection

Check Connected Devices

adb devices -l

Output shows serial, status, and device info. Common statuses:

device - Connected and authorized
unauthorized - Accept USB debugging prompt on device
offline - Connection issues, try adb kill-server && adb start-server

Wireless Debugging

Android 11+ (Recommended):

Enable Wireless debugging in Developer Options
Tap "Pair device with pairing code"
Run: adb pair <ip>:<pairing_port> and enter the code
Then: adb connect <ip>:<connection_port>

Legacy (requires USB first):

adb tcpip 5555
adb connect <device_ip>:5555

Multiple Devices

Always specify device with -s:

adb -s <serial> shell
adb -s emulator-5554 install app.apk

Shell Commands

Interactive Shell

adb shell                    # Enter shell
adb shell <command>          # Run single command
adb shell "cmd1 && cmd2"     # Chain commands

Essential Commands

# Device info
getprop ro.product.model              # Device model
getprop ro.build.version.release      # Android version
getprop ro.build.version.sdk          # SDK level

# File operations
ls -la /sdcard/
cat /path/to/file
cp /source /dest
rm /path/to/file

# Process info
ps -A | grep <name>
pidof <package_name>
top -n 1 -m 10

Safe Output Limiting

For commands with potentially large output:

adb shell "logcat -d | head -500"
adb shell "dumpsys activity | head -200"

App Management

Install/Uninstall

adb install app.apk                   # Basic install
adb install -r app.apk                # Replace existing
adb install -g app.apk                # Grant all permissions
adb install -r -g app.apk             # Both

adb uninstall com.example.app         # Full uninstall
adb uninstall -k com.example.app      # Keep data

Read the full file on GitHub · 385 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

references/deep-dive.md 9.3 KB

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.

yesterday First seen · 385 lines · 85 tokens per session scan A f6e18aa9902f

Subscribe to this mod's changes

android is a skill published in the GitHub repository hyperb1iss/hyperdroid-skill (34 stars, last pushed 7mo ago), licensed MIT. It adds 85 tokens to every session and 2,230 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.

Debugging Frontend Mobile agent android lineageos roms skills

compose-m3-theme-expert

Architect, implement, and optimize Material 3 custom themes in Jetpack Compose. Use this skill whenever the user mentions Android UI design systems, MaterialTheme overrides, dynamic wallpaper-derived colors, custom CompositionLocal providers (like NiaTheme gradients or background tokens), theme recomposition…

JosephSanjaya/skills · 90 tokens

agent-md-expert

Expert guidance for creating, auditing, and maintaining minimal, cache-friendly, and structure-decoupled context files (AGENTS.md and CLAUDE.md). Trigger this skill when the user mentions context files, repo rules, agents.md, claude.md, prompt optimization, or wants to check agent instructions.

JosephSanjaya/skills · 66 tokens

apple-container-expert

Expert guide for Apple's native container CLI (apple/container) — the open-source, Swift-native, VM-per-container runtime for Apple Silicon macOS. Read this skill BEFORE answering any question about: installing or starting apple/container; container run/build/machine/volume/network commands; configuring config.toml…

JosephSanjaya/skills · 168 tokens

medium-article-expert

Expert guidance for writing, structuring, outlining, titling, and publishing high-engagement Medium articles. Use whenever the user mentions Medium, Boost nomination, Medium titles/subtitles/kickers, article outlines, key points from a topic, SEO slugs/canonicals, or drafting/editing a Medium post — even if they only…

JosephSanjaya/skills · 143 tokens

shell-mastery

Expert shell configuration, optimization, and automation for Bash, Zsh, and PowerShell. Use when optimizing shell startup times, profiling performance bottlenecks, implementing defensive scripting patterns, configuring modern CLI tools (fzf, tmux, Atuin), writing portable POSIX scripts, engineering Zsh interactive…

JosephSanjaya/skills · 104 tokens

android-amplitude-sdk-expert

Expert guide for Amplitude Android SDK integration (Kotlin/Java). Use when tracking events, configuring autocapture, managing user identity, configuring batching or EU residency, implementing custom Enrichment/Destination plugins, migrating from legacy com.amplitude:android-sdk to modern…

JosephSanjaya/skills · 170 tokens