burner-phone

burner-phone is a skill for Claude Code, Codex from smallnest/goclaw. It costs 33 tokens per session (448 once invoked), scanned A, original, MIT.

An Android-device control workflow using ADB, the command-line tool for communicating with Android devices, plus screenshots and visual checking.

In plain words
What is it for?
Use it to capture screens, inspect mobile interfaces, tap, swipe, type, press keys, and launch Android apps.
Why use it?
It provides a repeatable way to see the phone, interact with the correct screen elements, and confirm that each action worked.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: model in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash(cmd="adb exec-out screencap -p > ./assets/screen.png").

Good fit Use it to capture screens, inspect mobile interfaces, tap, swipe, type, press keys, and launch Android apps.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/smallnest/goclaw
agentmods
npx agentmods add skills/smallnest/goclaw/burner-phone

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 burner-phone

README.md
[![agentmods](https://agentmods.dev/badge/skills/smallnest/goclaw/burner-phone/github.svg)](https://agentmods.dev/skills/smallnest/goclaw/burner-phone)
Your own site
<a href="https://agentmods.dev/skills/smallnest/goclaw/burner-phone"><img src="https://agentmods.dev/badge/skills/smallnest/goclaw/burner-phone/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 burner-phone

Your own site · 80×15
<a href="https://agentmods.dev/skills/smallnest/goclaw/burner-phone"><img src="https://agentmods.dev/badge/skills/smallnest/goclaw/burner-phone.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 448 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 $0.00033 $0.00448
Opus 5 $0.00016 $0.00224
Sonnet 5 $0.00007 $0.00090
Haiku 4.5 $0.00003 $0.00045

Measured 11d ago against content hash 7c5c55e40cbb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

burner-phone 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 11d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/setup.sh, scripts/vision_helper.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

internal/builtin_skills/burner-phone/SKILL.md · 68 lines

What it actually says

Burner Phone Control

Use this skill for ANY request involving phone screens or mobile app automation.

Vision Feedback Loop

ALWAYS follow this pattern:

  1. Screenshot: Capture the current screen

    bash(cmd="adb exec-out screencap -p > ./assets/screen.png")
    
  2. Analyze: Use vision model to understand the screen

    bash(cmd="python3 ./scripts/vision_helper.py ./assets/screen.png \"Describe the screen and list coordinates (x,y) for interactable elements.\"")
    
  3. Act: Perform the action using exact coordinates from step 2

    bash(cmd="adb shell input tap <x> <y>")
    
  4. Verify: Screenshot again to confirm the action worked

Available Commands

Tapping

bash(cmd="adb shell input tap <x> <y>")

Swiping

bash(cmd="adb shell input swipe <x1> <y1> <x2> <y2> <duration_ms>")

Typing Text

bash(cmd="adb shell input text 'your text here'")

Key Events

bash(cmd="adb shell input keyevent KEYCODE_HOME")
bash(cmd="adb shell input keyevent KEYCODE_BACK")
bash(cmd="adb shell input keyevent KEYCODE_ENTER")

Launch App

bash(cmd="adb shell am start -n com.package.name/.MainActivity")

Rules

  1. ALWAYS screenshot before acting - never guess coordinates
  2. ALWAYS use vision_helper.py to get coordinates
  3. Use coordinates provided by the vision tool EXACTLY
  4. All paths are relative to the skill root directory
Files

What ships with it

6 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. 11d ago First seen · 68 lines · 33 tokens per session scan A 7c5c55e40cbb

Subscribe to this mod's changes

burner-phone is a skill published in the GitHub repository smallnest/goclaw (602 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 448 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 2026-08-30.