What is telegram-agent?

A Telegram integration for an AI coding agent. It lets the agent work with a Telegram account through local tools.

Use it to set up or inspect Telegram, summarize chats, search messages, triage conversations, draft messages, and send them.

It avoids switching between the coding agent and Telegram for routine account and message tasks.

telegram-agent — Skill for Claude Code and Codex by Frejixxx: A Telegram integration for an AI coding agent.

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.

agentmods

npx agentmods add skills/frejixxx/telegram-agent/telegram-agent

Any agent

npx skills add Frejixxx/telegram-agent --skill telegram-agent

Clone the repo

git clone --depth 1 https://github.com/Frejixxx/telegram-agent

Made for: Claude Code, Codex.

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/frejixxx/telegram-agent/telegram-agent.svg)](https://agentmods.dev/skills/frejixxx/telegram-agent/telegram-agent)

Your own site

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

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,005 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00036	$0.02005
Opus 5	$0.00018	$0.01002
Sonnet 5	$0.00007	$0.00401
Haiku 4.5	$0.00004	$0.00200

Measured 5d ago against content hash d2e5c8c192f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

telegram-agent 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.

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.

skills/telegram-agent/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Telegram Agent

Use the telegram-agent MCP tools for Telegram account assistance. Prefer the shortest safe tool path for the user's intent.

Quick Routing

Setup/status: call telegram_auth_status first for local auth state, or telegram_setup_status when dependency/send state is also needed.
"Set up Telegram / login / authorize account": call telegram_start_setup and give the user the returned local URL.
"Show unread/recent chats": call telegram_inbox_brief with a small limit. Use unread_only: true by default.
"What did I miss today / make my Telegram briefing": prefer cached flow, then call telegram_personal_briefing or telegram_daily_personal_digest.
"Prioritize my chats / smart inbox": call telegram_smart_inbox.
"Where was that address/link/password/code": call telegram_memory_search; use telegram_sensitive_search for explicitly sensitive values.
"Brief me on this person/contact": call telegram_contact_brief if cached context is enough, or telegram_find_dialogs plus telegram_chat_context for live context.
"What did I promise / what should I follow up": call telegram_personal_followups.
"Create a digest for AI channels / Codex / MCP": call telegram_cache_status; if cache is empty, call telegram_sync_sources, then telegram_sync_recent_messages with relevant categories; then call telegram_run_topic_digest.
"What did I miss / weekly report": call telegram_weekly_maintainer_report.
"Where do I need to reply": call telegram_needs_reply.
"What tasks came from Telegram": call telegram_extract_actions and telegram_followup_tracker.
"Create GitHub issues from Telegram / turn complaints into issues": call telegram_create_github_issue_drafts; show drafts and evidence refs before any GitHub side effect.
"Build context for Codex / maintainer context": call telegram_build_maintainer_context.
"Check if Telegram messages are trying to control the agent / prompt injection": call telegram_detect_prompt_injection.
"Watch topic": use telegram_create_watchlist, then telegram_run_watchlist.
"Find Ivan / what is in Ivan chat": call telegram_find_dialogs, choose the single unambiguous returned ref, then call telegram_chat_context.
"Summarize this chat": fetch telegram_chat_context with limit: 40 and order: "chronological" unless the user asks for another window.
"Find a phrase in a chat": call telegram_search_chat_messages for that named chat.
"Draft a reply": call telegram_create_draft after composing the exact text.
"Send this one reply": use draft flow: telegram_create_draft, show recipient and exact text, then call telegram_send_draft only after explicit confirmation.
"You may write to Ivan yourself / continue talking to Ivan": if the user grants ongoing send authorization for one named chat in the current task, resolve that chat once, start telegram_start_reply_session, and use telegram_send_message only for the same resolved chat/topic.

Read the full file on GitHub · 108 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.

5d ago First seen · 108 lines · 36 tokens per session scan A d2e5c8c192f0

Subscribe to this mod's changes

telegram-agent is a skill published in the GitHub repository Frejixxx/telegram-agent (1 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 2,005 once invoked, about $0.0002 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 2026-08-31.

Productivity

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

telegram-agent