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 skills add san-npm/skills-ws --skill telegram-mini-appsgit clone --depth 1 https://github.com/san-npm/skills-wsWrote 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.
[](https://agentmods.dev/skills/san-npm/skills-ws/telegram-mini-apps)<a href="https://agentmods.dev/skills/san-npm/skills-ws/telegram-mini-apps"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/telegram-mini-apps/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.
<a href="https://agentmods.dev/skills/san-npm/skills-ws/telegram-mini-apps"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/telegram-mini-apps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00088 | $0.01285 |
| Opus 5.5 | $0.00035 | $0.00514 |
| Sonnet 5.5 | $0.00018 | $0.00257 |
| Haiku 4.5 | $0.00009 | $0.00128 |
Grade A, and why
telegram-mini-apps 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 2mo 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Telegram Mini Apps with Stars Payments — Expert Skill
A production-grade reference for building Telegram Mini Apps (TWA) on Next.js:
@telegram-apps/sdkv3 init, native capabilities (CloudStorage, biometry, fullscreen, shareStory), server-side initData HMAC validation, grammY bot webhooks, Stars (XTR) payments, and serverless deployment. Scope is the bot + Mini App + Stars billing stack; for advanced BotFather configuration and Bot API specifics, cross-check core.telegram.org/bots/webapps and docs.telegram-mini-apps.com.
Tested version matrix (as of Jun 2026)
These versions were verified to work together. Always confirm latest at each package's releases page before pinning.
| Package / runtime | Pin used here | Notes |
|---|---|---|
| Node.js | 22 LTS or 24 LTS | Node 18 and 20 are both EOL, do not target them for new deploys. |
@telegram-apps/sdk |
^3 |
v2 → v3 renamed several mount/signal APIs (see migration note below). |
@telegram-apps/sdk-react |
^3 |
React bindings (useSignal, useLaunchParams). |
grammy |
^1.30 |
Verify method signatures at grammy.dev; sendInvoice dropped positional provider_token in 1.24+ (Bot API 7.4 support). |
next |
^15 (App Router) |
Next.js 16 is current — verify at nextjs.org; RSC/route-handler APIs unchanged for this skill. |
react / react-dom |
^19 |
|
@libsql/client (Turso) |
^0.15 |
Verify at github.com/tursodatabase/libsql-client-ts. |
typescript |
^5.6+ |
|
| Telegram Bot API | 7.x+ | Stars/XTR, refundStarPayment, getStarTransactions. |
| Telegram WebApp platform | 8.0+ | requestFullscreen, shareStory, home-screen shortcuts require 8.0+. |
Do not confuse the two "versions". The npm package
@telegram-apps/sdk(major v3 in mid-2026) is independent of the Telegram WebApp platform version (e.g.8.0) reported in launch params. Older docs/skills saying "TMA SDK 7.x" conflated the two — there is no npm SDK 7.x.
What ships with it
19 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.
- agents/openai.yaml 207 B
- references/1-overview-architecture.md 2.3 KB
- references/10-markdownv2-escaping.md 2.1 KB
- references/11-database-options.md 4.0 KB
- references/12-next-js-deployment.md 3.5 KB
- references/13-security-hardening.md 4.4 KB
- references/14-complete-example-app.md 2.6 KB
- references/15-troubleshooting.md 3.0 KB
- references/2-twa-sdk-setup-v3-v2-v3-migration.md 9.8 KB
- references/3-native-capabilities-cloudstorage-biometry-fullscreen-sharestory.md 7.4 KB
- references/4-initdata-hmac-validation.md 6.2 KB
- references/5-bot-setup-with-grammy.md 2.0 KB
- references/6-webhook-handlers.md 2.9 KB
- references/7-stars-payments-xtr.md 12 KB
- references/8-deep-linking.md 2.4 KB
- references/9-telegram-theme-css-variables.md 5.2 KB
- references/quick-reference.md 2.7 KB
- references/rules-for-the-agent.md 1.5 KB
- references/table-of-contents.md 817 B
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.
- 2mo ago First seen · 50 lines · 88 tokens per session scan A 2a34d97e2084
telegram-mini-apps is a skill published in the GitHub repository san-npm/skills-ws (4 stars, last pushed 1mo ago), licensed MIT. It adds 88 tokens to every session and 1,285 once invoked, about $0.0004 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 2026-09-07.
telegram-mini-apps compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| telegram-mini-appssan-npm/skills-ws | Skill | 4 | 1mo ago | MIT | A | 88 | Codex |
| agent-spec-mobile-react-nativeruvnet/ruflo | Skill | 81k | yesterday | MIT | A | 22 | Claude Code |
| expo-native-uiexpo/skills | Skill | 4.1k | yesterday | MIT | A | 63 | Claude Code, Codex |
| expo-brownfieldexpo/skills | Skill | 4.1k | yesterday | MIT | A | 70 | Claude Code, Codex |
| react-native-testingcallstack/react-native-testing-library | Skill | 3.4k | yesterday | MIT | A | 134 | Claude Code, Codex |
| truesheet-usagelodev09/react-native-true-sheet | Skill | 2.1k | yesterday | MIT | A | 171 | Claude Code, Codex |
| vercel-react-native-skillsfcakyon/claude-codex-settings | Skill | 1.2k | yesterday | Apache-2.0 | A | 57 | Claude Code |