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/premex-ab/phone-mcp/copilot-instructionsgit clone --depth 1 https://github.com/premex-ab/phone-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/premex-ab/phone-mcp/copilot-instructions)<a href="https://agentmods.dev/instructions/premex-ab/phone-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/premex-ab/phone-mcp/copilot-instructions.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 | $0.03418 | $0.03418 |
| Opus 5 | $0.01709 | $0.01709 |
| Sonnet 5 | $0.00684 | $0.00684 |
| Haiku 4.5 | $0.00342 | $0.00342 |
Grade A, and why
phone-mcp copilot-instructions.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.
How it starts
The opening of the file, as written. The whole thing — 452 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Android MCP Server - Instructions
Project Overview
This is a multi-module Android application that implements a Server-Sent Events (SSE) MCP (Model Context Protocol) server. The server enables AI assistants to connect and interact with Android device capabilities through a standardized protocol.
Key Features
- SSE-based MCP Server: Runs as an Android foreground service with Ktor
- Modular Tool Architecture: Each device capability is a separate, pluggable module
- Dynamic Tool Management: Tools can be enabled/disabled at runtime with user consent
- Privacy-Focused: Each tool requires explicit user permission with clear disclaimers
- Authentication: Bearer token-based authentication for secure connections
- External Tool Support: Third-party apps can expose MCP tools via Content Providers
Architecture Overview
The application follows a clean, modular architecture with clear separation of concerns:
android-mcp-server/
├── app/ # Main application module
├── core/ # Core interfaces and contracts
├── mcp-provider/ # Library for external tool integration
├── externalmcptool/ # Example external tool implementation
└── tools/ # Individual tool modules
├── sms/
├── camera/
├── contacts/
├── sensor/
├── ads/
├── smsintent/
└── externaltools/
Core Modules
1. /app - Main Application Module
Purpose: Contains the UI, server logic, and service management
Key Components:
McpServerService: Foreground service that runs the Ktor SSE serverMcpServerApplication: Application class with Hilt setupMainActivity: Compose UI for server control and tool managementToolService: Manages tool states and preferencesToolPreferencesRepository: DataStore-based persistence for tool statesAuthRepository: Manages authentication tokens
Dependencies: All tool modules, core, mcp-provider
2. /core - Core Interfaces
Purpose: Defines the McpTool interface that all tools implement
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 · 452 lines · 3,418 tokens per session scan A 6e2c88a1a288
phone-mcp copilot-instructions.md is an instructions file published in the GitHub repository premex-ab/phone-mcp (10 stars, last pushed yesterday), licensed MIT. It adds 3,418 tokens to every session, about $0.0171 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 2026-08-31.
Other instructions, from other repositories
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.
DensityToggle CLAUDE.md
Instructions for channelramble/DensityToggle, covering density toggle - wear os display density control, goal, current status, how it works and how auto mode decides (v5).
touchbridge-mcp CLAUDE.md
Instructions for MarshallBear1/touchbridge-mcp, covering touchbridge, workflow, key patterns, physical devices and coordinate systems.
androir-mcp CLAUDE.md
Claude Code instructions for benasbarciauskas/androir-mcp, covering androir-mcp, scope guardrail (enforced), conventions and security.
freetube CLAUDE.md
Instructions for leshkodev/freetube, covering claude.md, 1. what this project is, 2. non-negotiable constraints, 3. tech stack (locked) and 4. project structure.