telegram-bot-builder

Guidance for building Telegram bots with grammY, Telegraf, or python-telegram-bot. Telegram bots are programs that receive messages or commands and respond through Telegram.

In plain words
What is it for?
Use it to build bots for Israeli users, configure polling or webhooks, add buttons and commands, handle Hebrew messages, support Telegram payments, or connect Mini Apps.
Why use it?
It helps avoid framework mismatches, broken production webhooks, Hebrew right-to-left text problems, and incorrect payment or Mini App integrations.

Skill for Claude CodeCodex

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/skills-il/developer-tools/telegram-bot-builder
Any agent
npx skills add skills-il/developer-tools --skill telegram-bot-builder
Clone the repo
git clone --depth 1 https://github.com/skills-il/developer-tools

Made for: Claude Code, Codex.

Per session 131 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,812 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.

ModelPer sessionOnce invoked
Fable 5 $0.00131 $0.08812
Opus 5 $0.00066 $0.04406
Sonnet 5 $0.00026 $0.01762
Haiku 4.5 $0.00013 $0.00881

Measured 3d ago against content hash ee08f073cce0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

telegram-bot-builder 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 3d 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.

telegram-bot-builder/SKILL.md · 596 lines

How it starts

The opening of the file, as written. The whole thing — 596 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Telegram Bot Builder

Build production-ready Telegram bots for the Israeli market using grammY, Telegraf, or python-telegram-bot. Covers Bot API v10.3 (24 August 2026), webhooks vs polling, inline keyboards, Hebrew/RTL text, Telegram Stars + Gifts payments, Mini Apps 2.0, Bot Business mode, and serverless deployment.

Problem

Building Telegram bots for Israeli users involves several things agents consistently get wrong:

  1. Framework confusion - grammY, Telegraf and python-telegram-bot sit on different Bot API versions and mix badly. Agents blend their APIs or emit deprecated patterns.
  2. Webhook misconfiguration - agents default to polling and then set webhooks up wrong for production, missing the port restriction (443, 80, 88, 8443 only), SSL, and secret-token verification.
  3. Hebrew/RTL corruption - bidirectional text breaks in inline keyboards, callback data and formatted messages when Unicode direction marks are ignored.
  4. Payment gaps - Telegram Stars has invoice rules that differ from fiat providers, and agents generate deprecated payment code.
  5. Mini App data exchange - the WebApp-to-bot channel depends on how the app was launched, and sendData is unavailable from inline-keyboard launches.
  6. Version drift - the Bot API ships several times a year and models learn a frozen snapshot. This skill was last verified against Bot API 10.3 on 2026-08-27; check the changelog before trusting any version-specific claim here.

Framework Selection

Choose by runtime, deployment target and Bot API version:

Feature grammY v1.46.0 Telegraf v4.16.3 python-telegram-bot v22.8
Language TypeScript/JS TypeScript/JS Python 3.10+
Bot API version Latest (v10.3) v7.1 v10.0
Install npm install grammy npm install telegraf pip install python-telegram-bot
Plugin ecosystem Rich (sessions, menus, conversations, i18n) Moderate (scenes, sessions) Extensions (JobQueue, persistence)
Serverless Vercel, CF Workers, Deno Deploy, Supabase Edge, Fly.io Express/Fastify/Lambda adapters ASGI adapters, manual handlers
Middleware Composer (Koa-style) Composer (Koa-style) Handler groups with filters
Long polling bot.start() bot.launch() application.run_polling()
Webhook webhookCallback() bot.launch({ webhook }) application.run_webhook()
Recommended for New projects, serverless, latest API Existing Express/Fastify apps Python and ML shops

Read the full file on GitHub · 596 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. 3d ago First seen · 596 lines · 131 tokens per session scan A ee08f073cce0

Subscribe to this mod's changes

telegram-bot-builder is a skill published in the GitHub repository skills-il/developer-tools (10 stars, last pushed 6d ago), licensed MIT. It adds 131 tokens to every session and 8,812 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens