telegram-notification-mcp: Instructions file for Claude Code

CLAUDE.md

telegram-notification-mcp CLAUDE.md is an instructions file for Claude Code from ilya24b/telegram-notification-mcp. It costs 4,388 tokens per session, scanned A, original, MIT.

Project instructions for a Telegram notification connector that links Claude with a Telegram bot. It describes sending and editing messages and media, reading business-chat messages, and managing queued tasks through a Cloudflare Worker.

In plain words
What is it for?
Working on the connector’s Telegram message, media, business-chat, task-queue, and message-editing features. The excerpt lists thirteen tools, including sending messages, photos, videos, documents, voice notes, and video notes.
Why use it?
It gives a coding agent the project’s architecture, file locations, infrastructure notes, and handling rules for keys and addresses.

Instructions file for Claude Code

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

This is ilya24b/telegram-notification-mcp's own configuration. It tells Claude Code how to work on telegram-notification-mcp 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 telegram-notification-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ilya24b/telegram-notification-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.

Copy the file
curl -O https://raw.githubusercontent.com/ilya24b/telegram-notification-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ilya24b/telegram-notification-mcp

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 telegram-notification-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ilya24b/telegram-notification-mcp/claude-md.svg)](https://agentmods.dev/instructions/ilya24b/telegram-notification-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ilya24b/telegram-notification-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ilya24b/telegram-notification-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,388 This file is loaded in full into every session.
When invoked 4,388 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.04388 $0.04388
Opus 5 $0.02194 $0.02194
Sonnet 5 $0.00878 $0.00878
Haiku 4.5 $0.00439 $0.00439

Measured 7d ago against content hash 28444d22ba6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

telegram-notification-mcp CLAUDE.md scanned grade A with 1 finding 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 7d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

20. **`/tmp` у Bash и у Windows-питона — разные папки.** Bash пишет в `%TEMP%`, python видит `C:\tmp`. Из-за этого 28.08 вышло, что `curl` успешно отправлял кружки, а падал только разбор ответа — и три лишних кружка ушли
CLAUDE.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Telegram Notification MCP — протокол проекта

Как называть этот файл: протокол. Решено владельцем 29.08.2026, раньше он назывался уставом. В разговоре и в заметках — «протокол», без синонимов, чтобы не было разночтений.

Что это

MCP-коннектор на Cloudflare Workers, связывающий claude.ai (чат и рутины) с Telegram-ботом @claude_24b_bot. Тринадцать инструментов, по назначению:

Отправка: send_telegram_message (уведомление в личку владельцу), send_photo, send_video, send_document, send_voice, send_video_note (кружок). Аргумент media — это file_id или публичный HTTPS-URL.

Переписка: get_new_messages — читает входящие через Secretary Mode (Telegram Business API) за период времени, из буфера в KV. send_business_reply — отвечает от лица владельца в подключённом бизнес-чате (business_connection_id).

Правка отправленного: edit_message_text, edit_message_caption, delete_messages (от одного до ста сообщений за раз).

Очередь задач: get_pending_tasks (что владелец поставил боту, пока Клод был недоступен), mark_task_done (отметить сделанным или невыполнимым с причиной).

Медиа и монтаж: list_recent_media (что бот получил), stage_media_for_processing (временные ссылки наружу), montage_videos (склейка нескольких роликов в один).

Локальный файл — не инструмент, а маршрут. Отправить файл с диска (скриншот, результат ffmpeg) инструментом нельзя: воркер не видит диск, а в аргумент вызова байты не положишь. Для этого есть POST /send и обёртка scripts/send-local.mjs — см. раздел «Отправка локальных файлов».

Входящие сообщения ловятся вебхуком (/telegram-webhook) и складываются в Cloudflare KV (MESSAGES_KV) — это обязательный буфер, потому что Business API отдаёт события только в момент их появления, задним числом историю не запросить.

Где что лежит

Протокол намеренно короткий: он уходит на сервер с каждым сообщением, поэтому здесь только то, что нужно всегда. Остальное — рядом, в репозитории:

  • docs/plans.md — что делаем дальше, со всеми принятыми решениями и тем, что решено не делать. Читать, когда выбираем следующую задачу.
  • docs/journal.md — история: завершённые работы, разборы устройства (монтаж, локальные файлы, скриншоты, очередь задач), живые прогоны, состояние на конец прошлых сессий. Читать, когда надо вспомнить, как что устроено и почему так.

Read the full file on GitHub · 147 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. 7d ago First seen · 147 lines · 4,388 tokens per session scan A 28444d22ba6b

Subscribe to this mod's changes

telegram-notification-mcp CLAUDE.md is an instructions file published in the GitHub repository ilya24b/telegram-notification-mcp (0 stars, last pushed 8d ago), licensed MIT. It adds 4,388 tokens to every session, about $0.0219 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

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.

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

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).

microsoft/vscode · 5,001 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

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