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.
npx agentmods add instructions/ghost-in-the-droid/android-agent/claude-mdgit clone --depth 1 https://github.com/ghost-in-the-droid/android-agentWrote 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.
[](https://agentmods.dev/instructions/ghost-in-the-droid/android-agent/claude-md)<a href="https://agentmods.dev/instructions/ghost-in-the-droid/android-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/ghost-in-the-droid/android-agent/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00324 | $0.00324 |
| Opus 5 | $0.00162 | $0.00162 |
| Sonnet 5 | $0.00065 | $0.00065 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
android-agent CLAUDE.md 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 5d 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.
What it actually says
Ghost in the Droid — Agent Tool Rules
MCP Tool: open_camera
For ANY task involving taking a photo, selfie, video, or opening the camera:
- Load the tool:
ToolSearch({"query": "select:mcp__android-agent__open_camera"}) - Call it:
mcp__android-agent__open_camera(device=<serial>, mode=<mode>, timer_s=<seconds>)
modes: photo (rear photo), video (rear video), selfie (front photo), selfie_video (front video)
timer_s: 0 (off), 2, 3, 5, 10
This single call opens the correct camera mode AND sets the timer. Do NOT:
- use
launch_appfor camera tasks - check
list_skillsfor a camera skill - tap camera UI manually to switch modes or set timers
MCP Tool: speak_text
To make the phone speak text aloud:
ToolSearch({"query": "select:mcp__android-agent__speak_text"})mcp__android-agent__speak_text(device=<serial>, text="...", rate=1.0)
Works from PC and on-device — always emits audio from the phone.
General rule
All mcp__android-agent__* tools are already loaded by the MCP server. To use any of them:
ToolSearch({"query": "select:mcp__android-agent__<tool_name>"}) then call it directly.
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.
- 5d ago First seen · 31 lines · 324 tokens per session scan A f774b831e144
android-agent CLAUDE.md is an instructions file published in the GitHub repository ghost-in-the-droid/android-agent (338 stars, last pushed 22d ago), licensed MIT. It adds 324 tokens to every session, about $0.0016 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.
Other instructions, from other repositories
androir-mcp CLAUDE.md
Claude Code instructions for benasbarciauskas/androir-mcp, covering androir-mcp, scope guardrail (enforced), conventions and security.
scrcpy-mcp AGENTS.md
Instructions for JuanCF/scrcpy-mcp, covering agents.md, project overview, project documentation, build/lint/test commands and build the project.
Autofish AGENTS.md
Instructions for felinics/Autofish, covering agents.md, project, context, current baseline and rules.
native-devtools-mcp AGENTS.md
AGENTS.md instructions for vectora-foundry/native-devtools-mcp, covering agent context: native-devtools-mcp, 🧠 core reasoning loop, 🗺️ capabilities matrix (strategy guide), 🛠️ tool definitions & schemas and 1. vision & perception (the "eyes").
uiautomator2-mcp-server AGENTS.md
Instructions for tanbro/uiautomator2-mcp-server, covering uiautomator2-mcp-server, project overview, project structure, development setup and install dependencies (uses uv lock file).
uiautomator2-mcp-server CLAUDE.md
Instructions for tanbro/uiautomator2-mcp-server, a project described as: A MCP (Model Context Protocol) server that provides tools for controlling and interacting with Android devices using uiautomator2.