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.
npx agentmods add skills/skills-il/developer-tools/telegram-bot-buildernpx skills add skills-il/developer-tools --skill telegram-bot-buildergit clone --depth 1 https://github.com/skills-il/developer-toolsWhat 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 | $0.00131 | $0.08812 |
| Opus 5 | $0.00066 | $0.04406 |
| Sonnet 5 | $0.00026 | $0.01762 |
| Haiku 4.5 | $0.00013 | $0.00881 |
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.
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:
- 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.
- 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.
- Hebrew/RTL corruption - bidirectional text breaks in inline keyboards, callback data and formatted messages when Unicode direction marks are ignored.
- Payment gaps - Telegram Stars has invoice rules that differ from fiat providers, and agents generate deprecated payment code.
- Mini App data exchange - the WebApp-to-bot channel depends on how the app was launched, and
sendDatais unavailable from inline-keyboard launches. - 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 |
What ships with it
15 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.
- CHANGELOG.md 3.9 KB
- evidence.json 35 KB
- metadata.json 2.1 KB
- optimization-log.json 10 KB
- references/.gitkeep 0 B
- references/conversations.md 2.6 KB
- references/deployment.md 3.3 KB
- references/domain-checklist.md 16 KB
- references/examples.md 14 KB
- references/framework-comparison.md 8.8 KB
- references/middleware.md 1.2 KB
- references/mini-apps.md 4.9 KB
- references/quickstarts.md 3.8 KB
- scripts/.gitkeep 0 B
- SKILL_HE.md 48 KB
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.
- 3d ago First seen · 596 lines · 131 tokens per session scan A ee08f073cce0
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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.
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.
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.
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…