A command-line tool for driving a connected Android phone or emulator, including reading its screen, tapping controls, typing, installing apps, and reading logs.

Use it to inspect accessibility elements, interact by label, run gestures and deep links, manage permissions, capture screenshots or recordings, and investigate logcat output.

It makes repeatable Android actions possible from a terminal, script, or CI job instead of relying on manual device use.

adb-cli — Skill for Claude Code and Codex by TiagoDanin

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 TiagoDanin/Android-Debug-Bridge-MCP --skill adb-cli

Clone the repo

git clone --depth 1 https://github.com/TiagoDanin/Android-Debug-Bridge-MCP

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tiagodanin/android-debug-bridge-mcp/adb-cli/github.svg)](https://agentmods.dev/skills/tiagodanin/android-debug-bridge-mcp/adb-cli)

Your own site

<a href="https://agentmods.dev/skills/tiagodanin/android-debug-bridge-mcp/adb-cli"><img src="https://agentmods.dev/badge/skills/tiagodanin/android-debug-bridge-mcp/adb-cli/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/tiagodanin/android-debug-bridge-mcp/adb-cli"><img src="https://agentmods.dev/badge/skills/tiagodanin/android-debug-bridge-mcp/adb-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,287 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. 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: 2 findings, up to high

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 →

high System Prompt Leakage · line 222
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
medium MCP Rug Pull · line 25
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]

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.

Model	Per session	Once invoked
Fable 5.1	$0.00096	$0.03287
Opus 5.5	$0.00038	$0.01315
Sonnet 5.5	$0.00019	$0.00657
Haiku 4.5	$0.00010	$0.00329

Measured 2mo ago against content hash 8b9fcce1a1e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

adb-cli scanned grade B with 1 finding 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 2mo 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

**Answer a fingerprint prompt on an emulator:**

skills/adb-cli/SKILL.md · 298 lines

How it starts

The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADB Agent CLI

adb-agent lets you drive a connected Android device or emulator from a normal shell. It is the terminal half of Android-Debug-Bridge-MCP — the MCP server drives the same engine through tool calls instead.

Use the CLI when the flow is a sequence of steps you want to chain in one call, when artifacts should land on disk, or when the same flow has to run in a script or CI job. Use the MCP tools when you want screenshots inline in the conversation.

If adb-agent is not on the PATH, npx -p android-debug-bridge-mcp adb-agent works anywhere, and node dist/cli/index.js works inside a built checkout.

Start with doctor

adb-agent doctor

Five checks: adb on the PATH, a usable working directory, the screenshot encoder in use, exactly one device to target, and uiautomator able to dump the current screen. Every other command depends on those, so fix what it reports before going further — a red doctor means the failures you see later will be misleading. It also names the device that unqualified commands will hit, which is the fastest way to notice you are driving the wrong emulator.

The two rules that matter

1. Read the screen before you act. Never tap coordinates you guessed. Dump the tree, find the element, then act on it:

adb-agent ui find "Sign in" --json
adb-agent ui tap "Sign in"

ui tap re-reads the screen, ranks matches against text, content-description and resource-id, and taps the best one. It survives layout and resolution changes in a way fixed coordinates do not.

2. Coordinates are fractions by default. input tap 0.5 0.7 taps the middle of the lower half on any screen size. Values above 1 are pixels. Force either reading with --norm or --px.

Command surface

Every command accepts --json, -d/--device <ref> and -q/--quiet. Run adb-agent <group> --help for the exact usage of a group. --device takes a full serial, a serial prefix, a transport id or a model name, so -d pixel and -d emulator-5554 reach the same device.

Read the full file on GitHub · 298 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.

2mo ago Changed · +80 lines scan A → B 8b9fcce1a1e9
2mo ago First seen · 218 lines · 96 tokens per session scan A 73bcf58c3761

Subscribe to this mod's changes

adb-cli is a skill published in the GitHub repository TiagoDanin/Android-Debug-Bridge-MCP (38 stars, last pushed 2mo ago), licensed MIT. It adds 96 tokens to every session and 3,287 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Hardware and IoT Mobile

adb-cli next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
adb-cliTiagoDanin/Android-Debug-Bridge-MCP	Skill	38	2mo ago	MIT	B	96	Claude Code, Codex
developer-device-platform-basicsgoogle/skills	Skill	22k	yesterday	Apache-2.0	A	57	Claude Code, Codex
cameraxandroid/skills	Skill	10k	yesterday	Apache-2.0	A	47	Claude Code
mobile-platform-native-capabilities-integrateforcedotcom/sf-skills	Skill	1.1k	2d ago	Apache-2.0	A	174	Claude Code
audio-skillzeenie-ai/OpenCompany	Skill	1.1k	yesterday	MIT	A	26	Claude Code
bluetooth-skillzeenie-ai/OpenCompany	Skill	1.1k	yesterday	MIT	A	21	Claude Code
camera-skillzeenie-ai/OpenCompany	Skill	1.1k	yesterday	MIT	A	20	Claude Code

adb-cli