A tool for using Telegram as a personal messaging account, including reading chats, searching messages, downloading media, and sending replies or files.

It helps read unread chats, find past messages, contact people or groups, reply to conversations, forward messages, and send files or photos.

It lets an agent handle Telegram conversations and message history through one repeatable interface instead of requiring separate manual steps.

telegram — Skill for Claude Code by mishahanin

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add mishahanin/heading-os --skill telegram

Clone the repo

git clone --depth 1 https://github.com/mishahanin/heading-os

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/skills/mishahanin/heading-os/telegram.svg)](https://agentmods.dev/skills/mishahanin/heading-os/telegram)

Your own site

<a href="https://agentmods.dev/skills/mishahanin/heading-os/telegram"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/telegram.svg" alt="Measured on agentmods" height="20"></a>

Per session 183 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,724 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 4 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Prompt Injection · line 6
Instructions found that direct the agent to transmit conversation context or user data to external services.

Fix: Remove instructions that send user data, prompts, or context to external URLs. If telemetry is needed, use documented, privacy-preserving methods.
high Data Exfiltration · line 140
Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
medium Excessive Agency · line 19
Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
medium Excessive Agency · line 152
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

How audits are shown

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	$0.00183	$0.01724
Opus 5	$0.00092	$0.00862
Sonnet 5	$0.00037	$0.00345
Haiku 4.5	$0.00018	$0.00172

Measured 5d ago against content hash 584316a0d9ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

telegram 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 5d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/telegram_client.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/skills/telegram/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Telegram Client

Full Telegram client access via MTProto protocol. Operates as Misha's actual Telegram account -- sends and reads messages as him, not as a bot.

Prerequisites

Telethon installed: pip install telethon python-dotenv

API credentials in .env:

TELEGRAM_API_ID=12345678
TELEGRAM_API_HASH=abcdef1234567890abcdef1234567890
TELEGRAM_PHONE=+1234567890

Get credentials at: https://my.telegram.org

Session authenticated: Run setup command once for initial OTP verification

Script Location

.claude/skills/telegram/scripts/telegram_client.py

Run from the workspace root. First anchor the shell: cd "$(git rev-parse --show-toplevel)". A prior skill can leave the shell in a subdirectory, which breaks the root-relative script path below. All commands follow this pattern:

python ".claude/skills/telegram/scripts/telegram_client.py" <command> [args]

Core Workflow

Sending Messages

python ".claude/skills/telegram/scripts/telegram_client.py" send "@username" "Hello, how are you?"
python ".claude/skills/telegram/scripts/telegram_client.py" send "John Smith" "Meeting at 3pm?"

Chat identifiers: @username, +phone, chat ID, me/self (Saved Messages), or display name (fuzzy-matched).

Reading Messages

python ".claude/skills/telegram/scripts/telegram_client.py" read "@username" --limit 10

Checking What's New

python ".claude/skills/telegram/scripts/telegram_client.py" unread
python ".claude/skills/telegram/scripts/telegram_client.py" chats --limit 20

Searching

python ".claude/skills/telegram/scripts/telegram_client.py" search "project update" --chat "@username"

Files & Media

Files sent and downloaded are DATA artifacts in the DATA overlay, not the engine tree.

send-file resolves a RELATIVE path under the data root, and refuses one that climbs out of the data root with ... The script sends an ABSOLUTE path as given. The download --output dir reaches the script verbatim, relative to cwd, which is the engine root. Resolve both under the data outputs dir, so the destination stays obvious:

Read the full file on GitHub · 153 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

5d ago First seen · 153 lines · 183 tokens per session scan A 584316a0d9ff

Subscribe to this mod's changes

telegram is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 183 tokens to every session and 1,724 once invoked, about $0.0009 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 2026-09-03.

Claude Code LLM Productivity Security ai-agent anthropic automation

telegram