channel-bot

channel-bot is a skill for Claude Code from vstorm-co/full-stack-ai-agent-template. It costs 53 tokens per session (532 once invoked), scanned A, original, MIT.

A guide for connecting AI-agent conversations to Telegram and Slack bots. It covers receiving messages, sending replies, managing sessions, and choosing between webhooks and polling.

In plain words
What is it for?
Use it to register or manage a bot, route Telegram or Slack messages through the agent, add a channel adapter, configure development polling, or set up production webhooks.
Why use it?
It removes the need to design separate message-handling flows for each platform. It also explains how bot identities, conversations, encrypted tokens, and delivery methods fit together.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to register or manage a bot, route Telegram or Slack messages through the agent, add a channel adapter, configure development polling, or set up production webhooks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vstorm-co/full-stack-ai-agent-template/channel-bot
About the project

Full-Stack AI Agent Template generates full-stack AI applications with a FastAPI backend and Next.js frontend, including agents, retrieval-augmented generation, streaming, authentication, and integrations. It is for building AI products with features such as chat, conversation sharing, administration, and multiple agent or vector-database choices. Catalogue add-ons support the generated applications and their agent workflows.

vstorm-co/full-stack-ai-agent-template · 1,879 stars · on GitHub · vstorm-co.github.io

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 vstorm-co/full-stack-ai-agent-template --skill channel-bot
Clone the repo
git clone --depth 1 https://github.com/vstorm-co/full-stack-ai-agent-template

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 channel-bot

README.md
[![agentmods](https://agentmods.dev/badge/skills/vstorm-co/full-stack-ai-agent-template/channel-bot.svg)](https://agentmods.dev/skills/vstorm-co/full-stack-ai-agent-template/channel-bot)
Your own site
<a href="https://agentmods.dev/skills/vstorm-co/full-stack-ai-agent-template/channel-bot"><img src="https://agentmods.dev/badge/skills/vstorm-co/full-stack-ai-agent-template/channel-bot.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 532 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 pass 7 Sept 2026
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00053 $0.00532
Opus 5 $0.00026 $0.00266
Sonnet 5 $0.00011 $0.00106
Haiku 4.5 $0.00005 $0.00053

Measured 8d ago against content hash 7c48eeabd221, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

channel-bot 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 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.

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.

template/{{cookiecutter.project_slug}}/.claude/skills/channel-bot/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Messaging Channels (Telegram / Slack)

Channels are a thick service at backend/app/services/channels/: per-platform adapters plus a router that funnels inbound messages into the same agent pipeline as the web chat.

Layout

File Responsibility
base.py Shared channel adapter interface
telegram.py Telegram adapter (aiogram v3)
slack.py Slack adapter (Events API + Socket Mode)
router.py Maps an inbound platform message → conversation/session → agent run → reply
chart_render.py Renders chart tool output as PNG for channels

Bots are stored in the DB (channel_bot), with per-user identity (channel_identity) and per-thread session (channel_session) tables. Bot tokens are encrypted at rest with CHANNEL_ENCRYPTION_KEY (Fernet).

Register / manage a bot

uv run {{ cookiecutter.project_slug }} cmd channel ...   # see `cmd channel --help`

Webhook vs polling

  • Polling (dev): the adapter long-polls the platform — no public URL needed.
  • Webhook (prod): the platform POSTs to POST /api/v1/telegram/{bot_id}/webhook / the Slack events endpoint. Verify the signature/secret (HMAC for Telegram, signing secret for Slack) before processing.

Add a new channel adapter

  1. Implement an adapter in services/channels/<platform>.py against the base.py interface (parse inbound → normalized message; send outbound).
  2. Wire it into router.py so inbound messages reach the agent and replies stream back.
  3. Add a webhook route under api/routes/v1/ (signature-verified) and/or a polling entrypoint.
  4. Reuse the existing conversation/session model — don't fork the agent pipeline.

Rules

  • Inbound messages flow through router.py into the same agent/session pipeline as web chat — don't duplicate agent logic per platform.
  • Always verify webhook signatures before acting on a payload.
  • Store tokens encrypted (CHANNEL_ENCRYPTION_KEY); never log or echo them.
  • Respect per-group/per-thread concurrency controls already in the adapters.

Read the full file on GitHub · 46 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 · 46 lines · 53 tokens per session scan A 7c48eeabd221

Subscribe to this mod's changes

channel-bot is a skill published in the GitHub repository vstorm-co/full-stack-ai-agent-template (1,879 stars, last pushed 3d ago), licensed MIT. It adds 53 tokens to every session and 532 once invoked, about $0.0003 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 2026-08-30.