claude-telegram-upgrade: Instructions file for Claude Code

CLAUDE.md

claude-telegram-upgrade CLAUDE.md is an instructions file for Claude Code from egerev/claude-telegram-upgrade. It costs 1,761 tokens per session, scanned C, original, MIT.

Setup instructions for upgrading Claude Code's Telegram integration. They describe fixes for stale bot processes, local voice-message transcription, and optional separate bots for different projects.

In plain words
What is it for?
Use them to configure the Telegram plugin, repair stale processes, transcribe voice messages with locally running Whisper, and set up project-specific bots.
Why use it?
They address restart conflicts, make voice messages available as text, and prevent messages from multiple projects from being mixed together.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions Claude Code.

This is egerev/claude-telegram-upgrade's own configuration. It tells Claude Code how to work on claude-telegram-upgrade 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 claude-telegram-upgrade configures →

Reuse

Borrowing it

Nothing to install: this file belongs to egerev/claude-telegram-upgrade. 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/egerev/claude-telegram-upgrade/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/egerev/claude-telegram-upgrade

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 claude-telegram-upgrade CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/egerev/claude-telegram-upgrade/claude-md/github.svg)](https://agentmods.dev/instructions/egerev/claude-telegram-upgrade/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/egerev/claude-telegram-upgrade/claude-md"><img src="https://agentmods.dev/badge/instructions/egerev/claude-telegram-upgrade/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 claude-telegram-upgrade CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/egerev/claude-telegram-upgrade/claude-md"><img src="https://agentmods.dev/badge/instructions/egerev/claude-telegram-upgrade/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,761 This file is loaded in full into every session.
When invoked 1,761 The same file — it is already loaded in full.
Security scan C 3 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 $0.01761 $0.01761
Opus 5 $0.00881 $0.00881
Sonnet 5 $0.00352 $0.00352
Haiku 4.5 $0.00176 $0.00176

Measured 8d ago against content hash ec3b7d37efee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

claude-telegram-upgrade CLAUDE.md scanned grade C with 3 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 8d 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.

chmod 600 ~/.claude/channels/telegram-<project-name>/.env

Reads agent configuration directoriesmediumAgent snooping

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

find ~/.claude/plugins -path '*/telegram/server.ts' -o -path '*/telegram/*/server.ts' 2>/dev/null

Makes network callslowCapability

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

curl -L -o ~/.local/share/whisper-models/ggml-small.bin \
CLAUDE.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Telegram Upgrade — Setup Guide

You are helping the user set up and configure upgrades for Claude Code's Telegram plugin.

First Interaction

When the user opens this repo or asks to set up / install / configure, start by explaining what you're going to do in plain language. The user should understand the full picture before anything happens.

Say something like:


This is an upgrade pack for Claude Code's Telegram integration. Here's what I can set up for you:

  1. Zombie Process Fix — the official Telegram plugin has a known bug where old bot processes don't get killed on restart, causing 409 errors and 100% CPU usage. I'll patch the plugin to automatically detect and kill stale processes.

  2. Voice Transcription — right now, when you send a voice message to your bot, Claude just sees "(voice message)" and can't listen to the audio. This patch auto-transcribes voice messages to text using Whisper running locally on your machine — no API keys, no cloud, everything stays private.

  3. Multi-Bot Setup (optional) — if you work on multiple projects, you can have a separate Telegram bot for each one. Messages from different projects won't mix, and each bot has its own access list. I'll create the directories, save tokens, and wire up the per-project config.

All changes are patches on top of the official plugin. Nothing gets forked or replaced — you keep using the official plugin, just with fixes applied. If the official plugin updates, patches can be re-applied.

Shall I proceed? I'll go step by step and ask before making any changes.


Wait for the user's confirmation before proceeding.

What This Repo Contains

  • patches/zombie-fix.patch — kills zombie bot processes (409 Conflict / 100% CPU fix)
  • patches/voice-transcription.patch — auto-transcribes voice messages via local Whisper - Multi-bot setup instructions (below)

Setup Task

After the user confirms, follow these steps in order. Explain what each step does before doing it. Ask for confirmation before making changes.

Read the full file on GitHub · 184 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. 8d ago First seen · 184 lines · 1,761 tokens per session scan C ec3b7d37efee

Subscribe to this mod's changes

claude-telegram-upgrade CLAUDE.md is an instructions file published in the GitHub repository egerev/claude-telegram-upgrade (2 stars, last pushed 5mo ago), licensed MIT. It adds 1,761 tokens to every session, about $0.0088 per session on Opus 5. A static security scan graded it C with 3 findings (asks for root, reads agent configuration directories, 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