talk-to-girlfriend-ai: Instructions file for Claude Code

CLAUDE.md

talk-to-girlfriend-ai CLAUDE.md is an instructions file for Claude Code from arlanrakh/talk-to-girlfriend-ai. It costs 645 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for Claude Code, an AI coding assistant, describing a Telegram integration that lets compatible AI tools work with Telegram. They cover the project structure, commands, testing, and setup.

In plain words
What is it for?
Use them when working on the Telegram MCP server, a program that exposes Telegram actions to AI clients, including setup, formatting, linting, tests, Docker, and its TypeScript agent.
Why use it?
They give the assistant the project context and exact commands, reducing guesswork when installing, running, checking, or changing the code.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is arlanrakh/talk-to-girlfriend-ai's own configuration. It tells Claude Code how to work on talk-to-girlfriend-ai itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything talk-to-girlfriend-ai configures →

Reuse

Borrowing it

Nothing to install: this file belongs to arlanrakh/talk-to-girlfriend-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/arlanrakh/talk-to-girlfriend-ai/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/arlanrakh/talk-to-girlfriend-ai

Made for: Claude Code.

Wrote 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.

agentmods badge for talk-to-girlfriend-ai CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/arlanrakh/talk-to-girlfriend-ai/claude-md/github.svg)](https://agentmods.dev/instructions/arlanrakh/talk-to-girlfriend-ai/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/arlanrakh/talk-to-girlfriend-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/arlanrakh/talk-to-girlfriend-ai/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.

agentmods 80×15 button for talk-to-girlfriend-ai CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/arlanrakh/talk-to-girlfriend-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/arlanrakh/talk-to-girlfriend-ai/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 645 This file is loaded in full into every session.
When invoked 645 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00645 $0.00645
Opus 5 $0.00322 $0.00322
Sonnet 5 $0.00129 $0.00129
Haiku 4.5 $0.00064 $0.00064

Measured 12d ago against content hash 782338b810e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

talk-to-girlfriend-ai 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 12d 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.

CLAUDE.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Telegram MCP Server - a full-featured Telegram integration for Claude, Cursor, and MCP-compatible clients. Uses Telethon for Telegram API access and exposes 60+ tools via the Model Context Protocol.

Commands

MCP Server (Python)

# Install dependencies
uv sync

# Run the MCP server
uv run main.py

# Generate Telegram session string
uv run session_string_generator.py

# Format code
black .

# Lint code
flake8 .

Run Tests

# Run validation tests
pytest test_validation.py -v

TypeScript Agent (in agent/)

cd agent
bun install
bun run dev

Docker

docker build -t telegram-mcp:latest .
docker compose up --build

Architecture

MCP Server (main.py)

Single-file MCP server exposing Telegram functionality as tools. Key components:

  • FastMCP("telegram") - MCP server instance
  • TelegramClient - Telethon client (supports both string and file-based sessions)
  • @mcp.tool() decorated functions - 60+ tools for chat, messaging, contacts, admin, media operations
  • @validate_id() decorator - validates chat_id/user_id parameters (accepts int, string int, or @username)
  • log_and_format_error() - centralized error handling with error codes logged to mcp_errors.log

TypeScript Agent (agent/)

CLI agent using Claude Sonnet via Vercel AI Gateway. Communicates with Telegram through an HTTP bridge:

  • telegram_api.py - FastAPI HTTP bridge exposing Telethon via REST (runs on port 8765)
  • agent/src/agent.ts - AI agent using @ai-sdk/gateway
  • agent/src/tools/ - Tool definitions (telegram.ts, nia.ts, aiify.ts)

ID Validation

All functions accept flexible ID formats:

  • Integer ID: 123456789 or -1001234567890
  • String ID: "123456789"
  • Username: "@username" or "username"

Code Style

  • Python: Black formatter (line-length 99), Flake8 linter
  • Target Python version: 3.10+
  • Use Union[int, str] for ID parameters
  • Error codes follow pattern: {CATEGORY}-ERR-{hash}

Read the full file on GitHub · 88 lines

Changes

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.

  1. 12d ago First seen · 88 lines · 645 tokens per session scan A 782338b810e3

Subscribe to this mod's changes

talk-to-girlfriend-ai CLAUDE.md is an instructions file published in the GitHub repository arlanrakh/talk-to-girlfriend-ai (545 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 645 tokens to every session, about $0.0032 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.

Related

Other instructions, from other repositories

vibe-coding-prompt-template backend.instructions.md

Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.

KhazP/vibe-coding-prompt-template · 139 tokens

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

langchain-ai/langchain · 4,469 tokens