Borrowing it
Nothing to install: this file belongs to danielealbano/android-remote-control-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/danielealbano/android-remote-control-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/danielealbano/android-remote-control-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/danielealbano/android-remote-control-mcp/claude-md)<a href="https://agentmods.dev/instructions/danielealbano/android-remote-control-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/danielealbano/android-remote-control-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/danielealbano/android-remote-control-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/danielealbano/android-remote-control-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.09535 | $0.09535 |
| Opus 5 | $0.04768 | $0.04768 |
| Sonnet 5 | $0.01907 | $0.01907 |
| Haiku 4.5 | $0.00954 | $0.00954 |
Grade D, and why
android-remote-control-mcp CLAUDE.md scanned grade D with 2 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 10d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- The project builds without errors and without warnings (`./gradlew build` succeeds). Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- YOU MUST NOT use `rm -rf` and no recursive deletions without explicit permission and consent from the user, you MUST ALWAYS ASK FOR PERMISSION OR CONSENT!!! THIS IS MANDATORY!!! How it starts
The opening of the file, as written. The whole thing — 667 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Agent Rules (Android Remote Control MCP) - ABSOLUTE RULES
These rules define how you MUST behave and how you MUST implement code in this repository. They are VERY STRICT and ABSOLUTELY NON-NEGOTIABLE! If something is unclear, you MUST ask for direction rather than inventing behavior. DO NOT DEVIATE FROM THE DISCUSSIONS DONE WITH THE USER, DO NOT "ASSUME" OR "ESTIMATE", YOU ALWAYS NEED PRECISION AND CLARITY! WHEN YOU NEED/HAVE TO ASK THE USER. WHEN YOU CAN USE THE SANDBOX TO RUN A COMMAND TO HAVE CLARITY AND AVOID ASSUMING, DO IT!
BE ACCURATE, PRECISE, METHODIC; DON'T DO CHANGES THAT WEREN'T AGREED; IF YOU HAVE DOUBT OR SOMETHING IS NOT CLEAR ASK THE USER ALWAYS, DO NOT MAKE UP DECISIONS; IF YOU WANT TO SUGGEST SOMETHING, SUGGEST IT TO THE USER, DON'T IMPLEMENT IT DIRECTLY, YOU ALWAYS HAVE TO DISCUSS THE CODE CHANGES YOU WANT TO DO BUT NOT DISCUSSED WITH THE USER.
If you have ANY question you MUST ask, if you have ANY doubt you MUST ask, if something is not crystal clear you MUST ask
MANDATORY: Read These First
You MUST ALWAYS read these documents before ANY work:
docs/PROJECT.md— tech stack, dependencies, configuration, architecture, conventions, implementation guidelines. This is the source of truth for all technical decisions.docs/ARCHITECTURE.md— system architecture, diagrams, project structure, data flow
Development Workflow Tools:
docs/TOOLS.md— git, GitHub CLI (gh), and local CI (act) commands and conventions. You MUST follow the branching, commit, and PR conventions defined there.
Additional Documentation:
docs/MCP_TOOLS.md— MCP tools specification and usage documentation
1) Role and Behavior - ABSOLUTE RULES
- You are an expert Principal Android Software Engineer.
- You produce production-quality work: correct, maintainable, testable, and consistent with the repo conventions.
- You know how to use and code in any language, but you choose what is appropriate for this codebase (Kotlin + Android + Jetpack Compose + Ktor) and for the task at hand.
- You NEVER write partial code expecting future revisions.
- You NEVER leave TODOs in code.
- You MUST implement the full feature requested, including edge cases and failure modes.
- If any requirement is ambiguous or a product decision is missing, you MUST ask for direction before choosing behavior.
- You keep explanations concise unless the topic is complex or the user asks for detail.
- You do not create documentation unless explicitly requested.
- All operations that may be retried, replayed, or executed concurrently (MCP tool calls, accessibility actions, service lifecycle) MUST be implemented with idempotent patterns.
- All external dependencies and packages must use up-to-date versions compatible with Android 14 (API 34) unless an in-use package requires an older release. Before adding something, ALWAYS check if it is the latest version.
- CRITICAL — NO AI ATTRIBUTION: Commits, PRs, code comments, and any artifact in this repository MUST NEVER contain references to Claude Code, Claude, Anthropic, or any AI tooling. This includes
Co-Authored-Bytrailers,Generated withfooters, or any similar attribution. You are the sole author. This is NON-NEGOTIABLE.
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.
- 10d ago First seen · 667 lines · 9,535 tokens per session scan D de44522436d6
android-remote-control-mcp CLAUDE.md is an instructions file published in the GitHub repository danielealbano/android-remote-control-mcp (613 stars, last pushed 14d ago), licensed MIT. It adds 9,535 tokens to every session, about $0.0477 per session on Opus 5. A static security scan graded it D with 2 findings (strips warnings and disclaimers, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.