Borrowing it
Nothing to install: this file belongs to popstas/telegram-download-chat. 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/popstas/telegram-download-chat/master/AGENTS.mdgit clone --depth 1 https://github.com/popstas/telegram-download-chatWrote 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/popstas/telegram-download-chat/agents-md)<a href="https://agentmods.dev/instructions/popstas/telegram-download-chat/agents-md"><img src="https://agentmods.dev/badge/instructions/popstas/telegram-download-chat/agents-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/popstas/telegram-download-chat/agents-md"><img src="https://agentmods.dev/badge/instructions/popstas/telegram-download-chat/agents-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 | $0.06591 | $0.06591 |
| Opus 5.5 | $0.02636 | $0.02636 |
| Sonnet 5.5 | $0.01318 | $0.01318 |
| Haiku 4.5 | $0.00659 | $0.00659 |
Grade A, and why
telegram-download-chat AGENTS.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 28d 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.
How it starts
The opening of the file, as written. The whole thing — 210 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 Download Chat is a Python CLI utility that downloads and analyzes Telegram chat history. It provides both command-line and GUI interfaces for downloading messages from chats, groups, channels, or archived exports and saving them in JSON/TXT formats.
Key Components
- Core Engine (
core/package): ContainsTelegramChatDownloaderplus helper modules (auth,config,download,entities,media,messages,context,render,progress,comments,citations,reactions,update_checker) built on Telethon - CLI Interface (
cli.py): Command-line interface with argument parsing and async message processing - GUI Interface (
gui_app.py): PySide6-based graphical interface with threading for async operations - MCP Server (
mcp/package): Model Context Protocol server exposing Telegram chat tools for AI assistants - Configuration (
paths.py): Handles config file management and application directories
Architecture
The application follows a modular design:
- Configuration Layer: YAML-based config with API credentials and user settings
- Telegram Client Layer: Telethon wrapper for authenticated API communication
- Processing Layer: Message filtering, date splitting, format conversion
- Interface Layer: CLI and GUI frontends sharing the same core functionality
Development Commands
Use .venv virtual environment.
Setup Development Environment
# Install in development mode with all dependencies
pip install -e ".[dev,gui]"
# Or install from requirements
pip install -r requirements.txt
Testing
# Run tests
pytest
# Run tests with async support
pytest -v
# Run specific test
pytest tests/test_telegram_download_chat.py::TestClass::test_method
# Opt-in end-to-end export tests against a live Telegram group (skipped by default).
# Requires an authenticated session and membership in the test group.
TG_E2E=1 pytest -m e2e # override the group via TG_E2E_GROUP
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.
- 28d ago Changed · +11 lines · +1,371 tokens per session 959abe5f8d4f
- 1mo ago Changed · +2 lines · +120 tokens per session 036b6962c016
- 2mo ago First seen · 197 lines · 5,100 tokens per session scan A 230c1a726bd5
telegram-download-chat AGENTS.md is an instructions file published in the GitHub repository popstas/telegram-download-chat (226 stars, last pushed 11d ago), licensed MIT. It adds 6,591 tokens to every session, about $0.0264 per session on Opus 5.5. 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.
telegram-download-chat AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| telegram-download-chat AGENTS.mdpopstas/telegram-download-chat | Instructions file | 226 | 11d ago | MIT | A | 6,591 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |