agentmods.dev

telegram

telegram is a skill for Claude Code, Codex from aspasskiy/GoGogot. It costs 45 tokens per session (682 once invoked), scanned A, original, MIT.

A Telegram connection that relays messages between a Telegram bot and the agent. It receives text, media, buttons, and other Telegram updates, and only accepts messages from the configured owner.

In plain words
What is it for?
Use it to troubleshoot Telegram messages, uploads, formatting, missing updates, or button presses. It supports media downloads, albums, locations, contacts, polls, and other Telegram content as described by the channel.
Why use it?
It provides a defined way for the agent to receive and send Telegram messages without mixing channel-specific handling into the core. It also limits access and handles Telegram's message and download constraints.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 264repo +44 10d ago A scan 45 tokens original MIT

Good fit Use it to troubleshoot Telegram messages, uploads, formatting, missing updates, or button presses. It supports media downloads, albums, locations, contacts, polls, and other Telegram content as described by the channel.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aspasskiy/gogogot/telegram
View source ↗ aspasskiy/GoGogot go-go-got.com
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 aspasskiy/GoGogot --skill telegram
Clone the repo
git clone --depth 1 https://github.com/aspasskiy/GoGogot

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.

agentmods badge for telegram

README.md
[![agentmods](https://agentmods.dev/badge/skills/aspasskiy/gogogot/telegram/github.svg)](https://agentmods.dev/skills/aspasskiy/gogogot/telegram)
Your own site
<a href="https://agentmods.dev/skills/aspasskiy/gogogot/telegram"><img src="https://agentmods.dev/badge/skills/aspasskiy/gogogot/telegram/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 telegram

Your own site · 80×15
<a href="https://agentmods.dev/skills/aspasskiy/gogogot/telegram"><img src="https://agentmods.dev/badge/skills/aspasskiy/gogogot/telegram.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 682 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.
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 $0.00045 $0.00682
Opus 5.5 $0.00018 $0.00273
Sonnet 5.5 $0.00009 $0.00136
Haiku 4.5 $0.00005 $0.00068

Measured 10d ago against content hash fb4483a16723, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 10d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (bridge.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.

internal/data/skills/bundled/telegram/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Telegram channel

This skill is a channel (see the add-channel skill for the protocol): the core runs bridge.py, which long-polls the Telegram Bot API and relays messages. Only the owner (TELEGRAM_OWNER_ID) can talk to you; the core enforces it.

It starts by itself whenever TELEGRAM_BOT_TOKEN and TELEGRAM_OWNER_ID are set in the container.

Files

  • channel.json — manifest: needs TELEGRAM_BOT_TOKEN and TELEGRAM_OWNER_ID, Telegram HTML format, 4000-char messages, editing and inline buttons.
  • bridge.py — the bridge, Python standard library only.

What the bridge does

  • getUpdates long polling for messages and button presses (callback queries) from the owner; everyone else is ignored.
  • Albums (media groups) are collected for a second and forwarded as one message.
  • Downloads photos (largest size), documents, audio, voice, video, video notes, GIFs and static stickers into GOGOGOT_CHANNEL_INBOX. Limits: text files 512 KB, images 10 MB, everything else 20 MB (the Bot API cannot download more than 20 MB). Text-like documents are sent as text/plain.
  • Locations, venues, contacts, polls and dice become text like [Location: lat=..., lon=...].
  • Requests: send/edit use parse_mode=HTML unless plain; status messages are sent silently; send_file picks sendPhoto/Video/Audio/Voice/ Animation by extension and falls back to sendDocument; ask shows inline buttons. Rate limits (429) are retried after retry_after.
  • TELEGRAM_API_BASE overrides https://api.telegram.org (used by tests, or a local Bot API server, which lifts the 20 MB limit).

Changing it

Copy bridge.py to bridge.py.bak first, edit, then channel_restart telegram and check channel_logs telegram. If you are talking through this bridge right now, a mistake can cut the conversation, so ask the owner first.

Safety net: if the bridge crashes 3 times in a row right after starting, the core restores the stock files of this skill and moves yours to .broken/ (this shows up in channel_logs). It does not catch a bridge that runs but misbehaves — test with the owner after every change. The owner can also delete /data/skills/telegram and restart the container to get the stock skill back.

Read the full file on GitHub · 60 lines

Files

What ships with it

2 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.

  1. 10d ago First seen · 60 lines · 45 tokens per session scan A fb4483a16723

Subscribe to this mod's changes

telegram is a skill published in the GitHub repository aspasskiy/GoGogot (264 stars, last pushed 10d ago), licensed MIT. It adds 45 tokens to every session and 682 once invoked, about $0.0002 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 2026-10-29.

Building agentsagenticai-agentai-assistantautomationbashclaude
Related

telegram compared with skills from other repositories

telegram next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
telegramaspasskiy/GoGogotSkill26410d agoMITA45Claude Code, Codex
agmsgfujibee/agmsgSkill1.6ktodayMITB52Claude Code
proactive-agentMerkyorLynn/LynnSkill677d agoApache-2.0A46Claude Code, Codex
novel-workshopMerkyorLynn/LynnSkill677d agoApache-2.0A90Claude Code
agent-personalityMerkyorLynn/LynnSkill677d agoApache-2.0A114Claude Code, Codex
image-lightboxMerkyorLynn/LynnSkill677d agoApache-2.0A108Claude Code, Codex
memory-recallMerkyorLynn/LynnSkill677d agoApache-2.0A104Claude Code, Codex