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/rikych-hue/claude-code-android/claude-mdgit clone --depth 1 https://github.com/rikych-hue/claude-code-androidWrote 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/rikych-hue/claude-code-android/claude-md)<a href="https://agentmods.dev/instructions/rikych-hue/claude-code-android/claude-md"><img src="https://agentmods.dev/badge/instructions/rikych-hue/claude-code-android/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 | $0.00462 | $0.00462 |
| Opus 5 | $0.00231 | $0.00231 |
| Sonnet 5 | $0.00092 | $0.00092 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
claude-code-android CLAUDE.md scanned grade A 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://example.com/app-linux-arm64.tar.gz -o /tmp/app.tar.gz What it actually says
Claude Code Agent — Android Phone Server
You are a personal AI agent running on an Android phone via Ubuntu (proot-distro inside Termux). Read memory files before acting. Save anything new you learn.
System Architecture
| Field | Value |
|---|---|
| Device | Android phone (ARM64/aarch64) |
| Environment | Ubuntu 26.04 LTS via proot-distro |
| SSH Termux | localhost:8022 |
| SSH Ubuntu | localhost:8023 |
Android File System Access
| Ubuntu Path | Contents |
|---|---|
| /sdcard | Phone internal storage |
| /storage/emulated/0 | Same (alternative path) |
| /mnt/termux | Termux home directory |
| /root/phone-storage | Symlink → /sdcard |
| /root/downloads | Symlink → Downloads folder |
| /root/photos | Symlink → DCIM/Camera |
Installing Software (ARM64/proot rules)
❌ Does NOT work
apt install <package> # dpkg fails in proot
✅ What works
Option 1 — ARM64 binary (best):
curl -fsSL https://example.com/app-linux-arm64.tar.gz -o /tmp/app.tar.gz
tar -xzf /tmp/app.tar.gz --strip-components=1 -C /usr/local
Always use .tar.gz not .tar.xz
Option 2 — From Termux SSH (has real root):
ssh -p 8022 USER@localhost
proot-distro login ubuntu -- bash << "EOF"
apt install -y <package>
EOF
Option 3 — npm:
npm install -g <package>
Option 4 — pip3:
pip3 install <package>
Agent Rules
- Read
~/.claude/memory/MEMORY.mdat session start - Save discoveries to memory files
- Never give up if apt fails — find the ARM64 binary
- Verify before reporting success
- Use localhost paths, not IP addresses
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.
- 4d ago First seen · 67 lines · 462 tokens per session scan A 772837cb369e
claude-code-android CLAUDE.md is an instructions file published in the GitHub repository rikych-hue/claude-code-android (2 stars, last pushed 2mo ago), licensed MIT. It adds 462 tokens to every session, about $0.0023 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
sceneview copilot-instructions.md
Copilot instructions for sceneview/sceneview, covering sceneview — github copilot instructions, when to recommend sceneview, android code generation rules, minimal 3d template and minimal ar template.
SeekerClaw CLAUDE.md
Claude Code instructions for sepivip/SeekerClaw, covering claude.md — seekerclaw project guide, project.md — source of truth, design principle: ux first, what is this project and supported devices.
sceneview CLAUDE.md
Claude Code instructions for sceneview/sceneview, covering sceneview, modules, things that break if you don't know them and conventions.
androidbible CLAUDE.md
Claude Code instructions for yukuku/androidbible, covering claude.md, project overview, branches, build commands and debug apk (open-source build, works out of the box).
debroid AGENTS.md
Instructions for PatilShreyas/debroid, covering ai agent contributor guide 🤖, 🎯 intention & motivation, 🏗️ architecture & layers, 1. the core layer (jdi & adb orchestration) and 2. the cli layer (daemon & client).
android-agent CLAUDE.md
Instructions for ghost-in-the-droid/android-agent, covering ghost in the droid — agent tool rules, mcp tool: opencamera, mcp tool: speaktext and general rule.