adb

adb is a skill for Claude Code, Codex from ithinkihaveacat/dotfiles. It costs 90 tokens per session (1,842 once invoked), scanned A, original, Apache-2.0.

A collection of ADB workflows and helper scripts for controlling Android phones and Wear OS watches. ADB is Android's command-line tool for device inspection and automation.

In plain words
What is it for?
Use it to capture screenshots and recordings, manage watch tiles, inspect services, install or remove packages, change device settings, and run diagnostic commands.
Why use it?
It avoids rebuilding common device-control steps and handles platform details such as circular watch screenshots, screen wake-up, and device selection.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to capture screenshots and recordings, manage watch tiles, inspect services, install or remove packages, change device settings, and run diagnostic commands.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ithinkihaveacat/dotfiles/adb
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 ithinkihaveacat/dotfiles --skill adb
Clone the repo
git clone --depth 1 https://github.com/ithinkihaveacat/dotfiles

Made for: Claude Code, Codex.

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 adb

README.md
[![agentmods](https://agentmods.dev/badge/skills/ithinkihaveacat/dotfiles/adb/github.svg)](https://agentmods.dev/skills/ithinkihaveacat/dotfiles/adb)
Your own site
<a href="https://agentmods.dev/skills/ithinkihaveacat/dotfiles/adb"><img src="https://agentmods.dev/badge/skills/ithinkihaveacat/dotfiles/adb/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 adb

Your own site · 80×15
<a href="https://agentmods.dev/skills/ithinkihaveacat/dotfiles/adb"><img src="https://agentmods.dev/badge/skills/ithinkihaveacat/dotfiles/adb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,842 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Prompt Injection · line 78
    Subtle instructions detected that may alter agent decision-making or introduce hidden biases.
    Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.
How audits are shown
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 $0.00090 $0.01842
Opus 5.5 $0.00036 $0.00737
Sonnet 5.5 $0.00018 $0.00368
Haiku 4.5 $0.00009 $0.00184

Measured 17d ago against content hash 0302f2b5c974, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

adb 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 17d 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/adb/SKILL.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Android ADB

Using Helper Scripts vs. Raw ADB

Use the scripts in scripts/ as the primary interface for device workflows. References to scripts/... in this skill are relative to this skill directory. They encapsulate solutions to common Android and Wear OS platform quirks:

  • Automatic circular display masking and density scaling for Wear OS screenshots
  • Device wake-up and keyguard dismissal prior to capture
  • Clipboard integration on macOS
  • Sensible default filenames and robust error handling

When to use raw adb: For general diagnostic inspection not covered by these scripts (e.g. adb logcat, adb shell pm list), or when building custom pipelines, standard adb commands are appropriate. If a helper script fails or lacks a specific flag you need, inspect its source in scripts/ to understand the underlying dumpsys or input sequence and adapt it.

Quick Start

When multiple devices are connected, pass -s SERIAL or --serial SERIAL before other arguments to any skill script. The flag overrides ANDROID_SERIAL; the environment variable remains available for persistent or inherited device selection.

Highest-Value Commands

  • Screenshot (auto-masks circular Wear OS displays): scripts/adb-screenshot

  • Wear OS Tile Debugging Workflow: scripts/adb-tile-add com.example/.MyTileService -> output gives INDEX scripts/adb-tile-switch INDEX

  • Inspect Wear OS Data Layer: adb exec-out dumpsys activity service WearableService

  • Package Information: scripts/packagename tiles PACKAGE_NAME scripts/packagename services PACKAGE_NAME

  • Device Info: scripts/adb-device-properties

  • Discover Activities: scripts/adb-activities (find launcher, TV, settings activities)

Script Index

See references/command-index.md for detailed usage.

Device Basics

  • scripts/adb-device-properties: Show key device properties (model, manufacturer, API level, display size, etc.).
  • scripts/adb-log: Write a message to the system log.

Read the full file on GitHub · 178 lines

Files

What ships with it

48 files 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.

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. 17d ago Changed 0302f2b5c974
  2. 18d ago Changed · +25 lines · +17 tokens per session f3ebe817da11
  3. 1mo ago First seen · 153 lines · 73 tokens per session scan A b4f8da56a3d4

Subscribe to this mod's changes

adb is a skill published in the GitHub repository ithinkihaveacat/dotfiles (48 stars, last pushed today), licensed Apache-2.0. It adds 90 tokens to every session and 1,842 once invoked, about $0.0004 per session on Opus 5.5. 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.