android-adb

A set of coding-agent rules for controlling and checking Android devices through ADB, the Android Debug Bridge command-line tool.

In plain words
What is it for?
Automating screenshots, inspecting the Android interface, performing gestures, managing apps, and debugging on a selected device.
Why use it?
It provides a consistent command layer for device actions and encourages checking the device state after each interaction.

Cursor rule for Cursor

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 rules/amit-nayar/android-adb-skill/android-adb
Clone the repo
git clone --depth 1 https://github.com/amit-nayar/android-adb-skill

Made for: Cursor.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 131 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.

ModelPer sessionOnce invoked
Fable 5 $0.00018 $0.00131
Opus 5 $0.00009 $0.00066
Sonnet 5 $0.00004 $0.00026
Haiku 4.5 $0.00002 $0.00013

Measured 2d ago against content hash 347123e36ffb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

android-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 2d 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.

.cursor/rules/android-adb.mdc · 22 lines

What it actually says

Android ADB Automation

Prefer the local command layer:

./tools/android ...

Read docs/command-contract.md for the command surface and skills/*/SKILL.md for task-specific workflows.

Default behavior:

  • Prefer ./tools/android ... --json over raw adb.
  • Pass --device <id> when the target device is known.
  • Verify state after interactions with ui dump, wait element, or screenshot.
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. 2d ago First seen · 22 lines · 18 tokens per session scan A 347123e36ffb

Subscribe to this mod's changes

android-adb is a cursor rule published in the GitHub repository amit-nayar/android-adb-skill (23 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 131 once invoked, about $0.0001 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.