Mobilerun Docs Reference
droidrun/mobilerun
Answers questions about Mobilerun, the LLM-agent framework for automating Android and iOS devices, by pointing the agent to the right page of its v5 documentation.
Controls an Android device over ADB in a loop of screenshot, vision analysis, tap and verification, so the agent acts on real on-screen coordinates.
Install Burner Phone Android Control
$ npx skills add smallnest/goclaw --skill burner-phone -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install smallnest/goclaw burner-phone --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/smallnest/goclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/internal/builtin_skills/burner-phone .claude/skills/burner-phone && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "burner-phone" agent skill from https://github.com/smallnest/goclaw/tree/master/internal/builtin_skills/burner-phone into .claude/skills/burner-phone/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "burner-phone", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/smallnest/goclaw/tree/master/internal/builtin_skills/burner-phoneType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add smallnest/goclaw --skill burner-phone -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install smallnest/goclaw burner-phone --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/smallnest/goclaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/internal/builtin_skills/burner-phone .agents/skills/burner-phone && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "burner-phone" agent skill from https://github.com/smallnest/goclaw/tree/master/internal/builtin_skills/burner-phone into .agents/skills/burner-phone/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "burner-phone", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add smallnest/goclaw --skill burner-phone -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install smallnest/goclaw burner-phone --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/smallnest/goclaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/internal/builtin_skills/burner-phone .cursor/skills/burner-phone && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "burner-phone" agent skill from https://github.com/smallnest/goclaw/tree/master/internal/builtin_skills/burner-phone into .cursor/skills/burner-phone/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "burner-phone", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/smallnest/goclaw.git --path internal/builtin_skills/burner-phone--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add smallnest/goclaw --skill burner-phone -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install smallnest/goclaw burner-phone --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/smallnest/goclaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/internal/builtin_skills/burner-phone .gemini/skills/burner-phone && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "burner-phone" agent skill from https://github.com/smallnest/goclaw/tree/master/internal/builtin_skills/burner-phone into .gemini/skills/burner-phone/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "burner-phone", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install smallnest/goclaw burner-phoneInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add smallnest/goclaw --skill burner-phone -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/smallnest/goclaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/internal/builtin_skills/burner-phone .github/skills/burner-phone && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "burner-phone" agent skill from https://github.com/smallnest/goclaw/tree/master/internal/builtin_skills/burner-phone into .github/skills/burner-phone/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "burner-phone", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add smallnest/goclaw --skill burner-phone -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install smallnest/goclaw burner-phone --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/smallnest/goclaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/internal/builtin_skills/burner-phone .opencode/skills/burner-phone && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "burner-phone" agent skill from https://github.com/smallnest/goclaw/tree/master/internal/builtin_skills/burner-phone into .opencode/skills/burner-phone/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "burner-phone", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
burner-phone- GitHub stars
- 599
- Token cost
- ~436 tokens
- SKILL.md length
- 103 words
- Files
- 7 (incl. scripts, assets)
- Skills in repo
- 6
- Repo updated
- First seen
- Licence
- MIT
At a glance
Controls an Android device over ADB in a loop of screenshot, vision analysis, tap and verification, so the agent acts on real on-screen coordinates.
- Works in 4 steps: Screenshot: Capture the current screen → Analyze: Use vision model to understand… → Act: Perform the action using exact… → …
- Automating taps and swipes in a mobile app on a connected Android phone
- SKILL.md covers Vision Feedback Loop, Available Commands and Rules
- Runs Shell and Python scripts from its folder
What it does
Every action follows the same four steps. The agent captures the screen with `adb exec-out screencap`, sends the image to `scripts/vision_helper.py` to get a description and the coordinates of tappable elements, performs the action at exactly those coordinates, and takes another screenshot to confirm it worked. The rules are to screenshot before acting, never guess coordinates, and use the vision tool's numbers unchanged.
Available commands cover tapping, swiping with a duration, typing text, key events such as Home, Back and Enter, and launching an app by activity name with `adb shell am start`. The package includes `scripts/setup.sh`, the vision helper script, a README and banner assets, and all paths are relative to the skill root. The skill is written to cover any request involving phone screens or mobile app automation.
When your agent uses it
- Automating taps and swipes in a mobile app on a connected Android phone
- Reading what is currently on a phone screen through a screenshot
- Walking through an app flow where each step needs visual confirmation
Example prompts
- “Open the Settings app on the connected phone and tell me what battery options are on screen.”
- “Take a screenshot of the phone and tap the Sign in button.”
- “Scroll down in the Clock app and verify the alarm list with a fresh screenshot.”
Requirements
- ADB with an Android device connected
- Python 3 for the vision helper script
- Access to a vision model for screen analysis
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Screenshot: Capture the current screen
- Analyze: Use vision model to understand the screen
- Act: Perform the action using exact coordinates from step 2
- Verify: Screenshot again to confirm the action worked
What it can do on your machine
Read from SKILL.md and the folder at commit e05c79d. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 2 files in scripts/ (Shell and Python), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Burner Phone Android Control loads about 436 tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 103 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from smallnest/goclaw at commit e05c79d, republished under its MIT licence (© smallnest). 103 words, ~436 tokens.
Download SKILL.mdSave it as
.claude/skills/burner-phone/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.- name
- burner-phone
- description
- Control Android devices via ADB with vision feedback. Use this to see the screen, take screenshots, analyze UI elements, and automate phone tasks.
- model
- qwen2.5-omni:3b
- keywords
- android, phone, adb, screenshot, vision, screen, tap, swipe, automation
Burner Phone Control
Use this skill for ANY request involving phone screens or mobile app automation.
Vision Feedback Loop
ALWAYS follow this pattern:
Screenshot: Capture the current screen
bash(cmd="adb exec-out screencap -p > ./assets/screen.png")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.\"")Act: Perform the action using exact coordinates from step 2
bash(cmd="adb shell input tap <x> <y>")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
- ALWAYS screenshot before acting - never guess coordinates
- ALWAYS use vision_helper.py to get coordinates
- Use coordinates provided by the vision tool EXACTLY
- All paths are relative to the skill root directory
© smallnest, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 6 other files (scripts, assets) in internal/builtin_skills/burner-phone of smallnest/goclaw.
- SKILL.md
- README.md
- assets/.gitkeep
- assets/banner.png
- burner-phone-pfp.webp
- scripts/setup.sh
- scripts/vision_helper.py
Open the folder on GitHubat commit e05c79d
Compare with similar skills
Burner Phone Android Control next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Burner Phone Android Control this skillsmallnest/goclaw | 599 | — | ~436 | Automated safety check: Pass | MIT | |
| Mobilerun Docs Referencedroidrun/mobilerun | 9.6k | — | ~943 | Automated safety check: Pass | MIT | |
| Phoneagentrounak/PhoneAgent | 800 | — | ~2.2k | Automated safety check: Pass | MIT | |
| Appium Skillsickn33/agentic-awesome-skills | 47k | 1 repos | ~2.8k | Automated safety check: Pass | MIT | |
| Re Mobile Forensicsdslsdzc/rev-skills | 135 | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| Autofish Android Controlfelinics/Autofish | 118 | — | ~1.7k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Phoneagent
rounak/PhoneAgent
Control a connected iPhone, iOS simulator, Android emulator, or Android device from macOS through PhoneAgent's JSON-RPC bridge.
Appium Skill
sickn33/agentic-awesome-skills
Generates production-grade Appium mobile automation scripts for Android and iOS in Java, Python, or JavaScript.
Re Mobile Forensics
dslsdzc/rev-skills
移动设备取证：Android/iOS 备份解析、应用数据提取、删除恢复与时间线. An agent skill from dslsdzc/rev-skills.
Autofish Android Control
felinics/Autofish
Controls an Android device through the af CLI with observe, act and verify steps, ref-based taps, screenshots and recovery when a step goes wrong.
OpenGUI Android Control
Core-Mate/OpenGUI
Drives locally connected Android phones through OpenGUI screenshots and allowlisted actions, one observed step at a time, for app, game and multi-device tasks.
More from smallnest/goclaw
Crawl4AI Web Scraping
smallnest/goclaw
Scrapes sites, handles JavaScript-heavy pages and extracts structured data with Crawl4AI, through its crwl CLI or Python SDK, including schema-based extraction without an LLM.
Discord Actions for OpenClaw
smallnest/goclaw
Reference for OpenClaw's discord tool: sending messages, reactions, stickers, emoji uploads, polls, threads and moderation in Discord channels and DMs.
Actionbook Browser Action Manuals
smallnest/goclaw
Looks up action manuals with verified selectors for multi-step website tasks, then drives the browser with the actionbook CLI in a dedicated or an existing Chrome session.
Feishu Upload Image
smallnest/goclaw
Upload images to Feishu/Lark. An agent skill from smallnest/goclaw.
goclaw Skill Finder
smallnest/goclaw
Helps you find, install, update and remove skills in the goclaw agent framework, using the goclaw skills commands and outside skill sources.
Related
Categories
Questions about Burner Phone Android Control
What does Burner Phone Android Control do?
Controls an Android device over ADB in a loop of screenshot, vision analysis, tap and verification, so the agent acts on real on-screen coordinates. Every action follows the same four steps.py` to get a description and the coordinates of tappable elements, performs the action at exactly those coordinates, and takes another screenshot to confirm it worked.
When should I use Burner Phone Android Control?
Burner Phone Android Control fits situations like: automating taps and swipes in a mobile app on a connected Android phone; reading what is currently on a phone screen through a screenshot; walking through an app flow where each step needs visual confirmation.
How do I install Burner Phone Android Control in Claude Code?
Run `npx skills add smallnest/goclaw --skill burner-phone -a claude-code`. Or copy the skill folder (internal/builtin_skills/burner-phone in smallnest/goclaw) into .claude/skills/burner-phone in your project. Claude Code loads it when a task matches its description.
How do I install Burner Phone Android Control in Codex?
Run `npx skills add smallnest/goclaw --skill burner-phone -a codex`. Or copy the skill folder (internal/builtin_skills/burner-phone in smallnest/goclaw) into .agents/skills/burner-phone in your project. Codex loads it when a task matches its description.
Can I use Burner Phone Android Control in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add smallnest/goclaw --skill burner-phone -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/burner-phone, .gemini/skills/burner-phone, .github/skills/burner-phone and .opencode/skills/burner-phone in your project.
What does Burner Phone Android Control need to run?
Going by SKILL.md and its folder, Burner Phone Android Control needs a shell and Python for the scripts in its folder. Our summary lists: ADB with an Android device connected; Python 3 for the vision helper script; Access to a vision model for screen analysis.
Does Burner Phone Android Control access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Burner Phone Android Control safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Burner Phone Android Control use?
Burner Phone Android Control is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Burner Phone Android Control use?
About 436 tokens (SKILL.md is roughly 1.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Burner Phone Android Control?
Skills that share tags, products or a category with Burner Phone Android Control: Mobilerun Docs Reference (droidrun/mobilerun, 9.6k stars), Phoneagent (rounak/PhoneAgent, 800 stars), Appium Skill (sickn33/agentic-awesome-skills, 47k stars) and Re Mobile Forensics (dslsdzc/rev-skills, 135 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Burner Phone Android Control?
smallnest (a GitHub user) maintains it in smallnest/goclaw, which has 599 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on March 27, 2026.
Source: smallnest/goclaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.