Borrowing it
Nothing to install: this file belongs to stixez/droid-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/stixez/droid-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/stixez/droid-mcpWrote 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/stixez/droid-mcp/claude-md)<a href="https://agentmods.dev/instructions/stixez/droid-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/stixez/droid-mcp/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 5.1 | $0.04073 | $0.04073 |
| Opus 5 | $0.02037 | $0.02037 |
| Sonnet 5 | $0.00815 | $0.00815 |
| Haiku 4.5 | $0.00407 | $0.00407 |
Grade A, and why
droid-mcp 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
droid-mcp
Android MCP SDK. Exposes phone capabilities (calendar, contacts, SMS, files, media, location, sensors, camera, NFC, intents, playback, screenshot, ML Kit vision, notification reply + watch, accessibility-driven UI control, custom IME typing, floating overlay, Shizuku shell-UID admin, libsu root-UID admin, etc.) via Model Context Protocol — 145 tools across 53 modules, compatible with on-device LLMs and desktop MCP clients.
Quick Reference
- Language: Kotlin 2.1, Android SDK 28+, Gradle 8.12
- Build:
./gradlew assembleDebug| Test:./gradlew :droid-mcp-core:test - 53 modules, 145 tools, sample app with Compose UI. Tiers 1–3 are the core surface; Tiers 4–5 (
shizuku,root) are opt-in power tools excluded from:droid-mcp-all. 0.10.0 adds three opt-in hardening modules (audit,tls,server-service) — also excluded from:droid-mcp-all(they pull Room/BouncyCastle/foreground-service deps).
Key Conventions
- Every tool implements
McpToolinterface:name,description,parameters,suspend fun execute() - Every module has a provider object (e.g.
CalendarTools) withall(context),requiredPermissions(),hasPermissions(context) - Limit params:
(params["limit"] as? Number)?.toInt()?.coerceIn(1, 100) ?: 10 - ContentResolver queries: use
?.use { cursor -> }, NOLIMIT/OFFSETin sortOrder (handle in cursor loop) - File access: sandboxed via
PathValidator— external storage only - Tool calls run on
Dispatchers.IO, never main thread - No fully qualified names inline — use proper imports
Don't
- Don't add
LIMITorOFFSETto ContentResolversortOrderstrings — not supported on all devices - Don't request permissions from library code — apps handle their own permission UX
- Don't use
SmsManager.getDefault()— use version-checkedcontext.getSystemService()on API 31+ - Don't require media permissions for File API access on API 33+
Architecture
Multi-module Gradle project. Each phone API is an independent module depending only on :droid-mcp-core.
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.
- 8d ago First seen · 212 lines · 4,073 tokens per session scan A d0ca7c3a8455
droid-mcp CLAUDE.md is an instructions file published in the GitHub repository stixez/droid-mcp (29 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 4,073 tokens to every session, about $0.0204 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.