What is tg-mcp-guarded CLAUDE.md?

A repository guide for AI coding agents working on a Telegram API library and MCP server. It explains the project structure, important rules, and how Telegram data handling works.

Use it when developing, testing, or reviewing the Telegram clients, data exports, MCP tools, scripts, documentation, or configuration in this project.

It gives an agent the context needed to make changes that fit the repository and follow its rate limits, anti-spam rules, and security practices.

How matskevich/tg-mcp-guarded configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to matskevich/tg-mcp-guarded. 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/matskevich/tg-mcp-guarded/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/matskevich/tg-mcp-guarded

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/matskevich/tg-mcp-guarded/claude-md/github.svg)](https://agentmods.dev/instructions/matskevich/tg-mcp-guarded/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/matskevich/tg-mcp-guarded/claude-md"><img src="https://agentmods.dev/badge/instructions/matskevich/tg-mcp-guarded/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/matskevich/tg-mcp-guarded/claude-md"><img src="https://agentmods.dev/badge/instructions/matskevich/tg-mcp-guarded/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,062 This file is loaded in full into every session.

When invoked 2,062 The same file — it is already loaded in full.

Security scan C 2 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.

Model	Per session	Once invoked
Fable 5.1	$0.02062	$0.02062
Opus 5.5	$0.00825	$0.00825
Sonnet 5.5	$0.00412	$0.00412
Haiku 4.5	$0.00206	$0.00206

Measured 1mo ago against content hash 5a67f9417ac8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

tg-mcp-guarded CLAUDE.md scanned grade C 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 1mo 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

3. **Session-файлы защищены** — chmod 700/600, не коммитить

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Если используешь claude-code, в `~/.claude/settings.local.json` или project `.claude/settings.local.json` включай именно:

CLAUDE.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — контекст для AI-агентов

Этот файл — точка входа для Claude Code, Cline, Cursor и других AI-агентов.

Что это за репозиторий

tg-mcp — MCP-сервер + Python-библиотека для работы с Telegram API.

Предоставляет:

Telegram-клиенты с управлением сессиями
Rate limiting и anti-spam защита (TokenBucket, safe_call, дневные квоты)
Экспорт данных (участники, сообщения, группы)
MCP-сервер для доступа из Claude Code

Структура

/
├── tganalytics/            # Telegram-инфраструктура
│   ├── tganalytics/        # пакет (infra, domain, config)
│   ├── mcp_server.py       # MCP-сервер (9 tools)
│   ├── examples/           # примеры использования
│   └── pyproject.toml
├── tests/                  # тесты
├── scripts/                # утилиты (compliance, security)
├── docs/                   # документация
├── data/                   # runtime данные (gitignored)
│   ├── sessions/           # Telegram-сессии
│   ├── anti_spam/          # дневные счётчики
│   └── logs/
├── .cursor/rules/          # AI governance
├── .github/workflows/      # CI
├── .mcp.json               # MCP конфигурация
└── requirements.txt

Ключевые правила

Все Telegram-вызовы через safe_call — никаких прямых telethon вызовов
PII не коммитить — все выгрузки в gitignored папках
Session-файлы защищены — chmod 700/600, не коммитить
Telegram write only via Action MCP — direct client.send_* и client.delete_messages запрещены по умолчанию

MCP Server

Read/Actions MCP tools для доступа к Telegram API:

Tool	Назначение
`tg_list_sessions`	Список сессий
`tg_use_session`	Переключить сессию
`tg_get_group_info`	Инфо о группе
`tg_get_participants`	Участники группы
`tg_search_participants`	Поиск участников
`tg_get_messages`	Сообщения
`tg_get_message_count`	Количество сообщений
`tg_get_group_creation_date`	Дата создания группы
`tg_get_stats`	Статистика anti-spam
`tg_send_message`	Отправка сообщения (actions profile: dry_run -> approval_code -> confirm=true + confirmation_text)
`tg_send_file`	Отправка файла (actions profile: dry_run -> approval_code -> confirm=true + confirmation_text)
`tg_click_inline_button`	Нажатие inline-кнопки бота (actions profile: dry_run -> approval_code -> confirm=true + confirmation_text)
`tg_run_bot_steps`	Серия действий в bot-dialog за один approval (send/click/wait)
`tg_get_actions_policy`	Активные write-ограничения

Read the full file on GitHub · 183 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.

1mo ago Changed · +10 lines · +192 tokens per session 5a67f9417ac8
2mo ago First seen · 173 lines · 1,870 tokens per session scan C d2f7b5819877

Subscribe to this mod's changes

tg-mcp-guarded CLAUDE.md is an instructions file published in the GitHub repository matskevich/tg-mcp-guarded (10 stars, last pushed 2d ago), licensed MIT. It adds 2,062 tokens to every session, about $0.0082 per session on Opus 5.5. A static security scan graded it C with 2 findings (asks for root, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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 · 9,715 tokens

tg-mcp-guarded: Instructions file for Claude Code