Vellum Assistant is a personal AI assistant that remembers information about users, learns their preferences, and takes actions across connected apps. It is intended for people who want an assistant that can manage conversations, unfinished work, and proactive notifications over time. The catalogue skills, hooks, instruction, and setting configure or extend how the assistant works.
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 vellum-ai/vellum-assistant --skill telegram-setupgit clone --depth 1 https://github.com/vellum-ai/vellum-assistantWrote 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/vellum-ai/vellum-assistant/telegram-setup)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/telegram-setup"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/telegram-setup/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/vellum-ai/vellum-assistant/telegram-setup"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/telegram-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00022 | $0.02562 |
| Opus 5.5 | $0.00009 | $0.01025 |
| Sonnet 5.5 | $0.00004 | $0.00512 |
| Haiku 4.5 | $0.00002 | $0.00256 |
Grade A, and why
telegram-setup 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 1mo 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are helping your user connect a Telegram bot. The wizard collects the token, the rest of setup runs automatically, and you confirm it worked.
DO NOT use this skill for runtime Telegram operations (sending, replying, reading). That is the separate messaging skill.
Supported chats
Telegram works in private chats and in groups and supergroups. In a private chat the assistant answers every message. In a group it answers only a message that addresses it: an @mention of the bot's username, a command such as /summary@botname, or a reply to one of its posts. Every other group message is dropped on purpose and never reaches the assistant; the gateway log records each drop with the reason bot_not_mentioned. Broadcast channels are not supported.
Telegram's privacy mode (on by default) already delivers only mentions, replies, and commands to a bot. The assistant applies the same rule itself, so promoting the bot to admin or turning privacy mode off does not make it answer unaddressed messages.
Tell the user this during setup and in the Step 5 summary. When a group message got no reply, first check that it mentioned the bot or replied to it, before diagnosing webhook or credential failures. Forum topics work: a reply lands in the topic the message was in.
What happens without you
Saving the token in the wizard triggers all of this:
| Step | Runs |
|---|---|
Validate the token against getMe |
Automatically, on save |
Store telegram.botId and telegram.botUsername |
Automatically, on save |
| Generate the webhook secret | Automatically, on save |
| Register the platform callback route | Automatically, on save |
Tell Telegram where to send updates (setWebhook) |
Automatically, after the save |
Install the bot commands (setMyCommands) |
Automatically, after the save |
What ships with it
1 file 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.
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.
- 1mo ago Changed · +2 lines 039af550ec95
- 1mo ago Changed · +7 lines ffb115721494
- 1mo ago First seen · 182 lines · 22 tokens per session scan A d935af91eff3
telegram-setup is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,448 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 2,562 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
lictor-security-check
Pre-release security audit for ANY project — AI-built or hand-written, web or mobile. Scans the codebase for the full range of real-world risks that get apps breached: leaked API & AI-provider keys, exposed configs/secrets, broken auth & access control (IDOR), injection (SQL/XSS/command), SSRF, open databases & cloud…
lictor-rotate
Walks the user through rotating a leaked API key — step by step, provider-specific. Knows the exact URL to visit, the exact button to click, and how to verify the rotation worked. Supports Stripe, OpenAI, Anthropic, Google Cloud / AI Studio, GitHub, AWS, Slack, Supabase, Firebase, Postmark, and generic OAuth providers.
lictor-explain
Takes any security finding, error message, or jargon-heavy security advice and explains it in plain English. Use this when someone is confused by what /lictor-security-check found, or when they got a security warning from another tool and don't understand it.
lictor-fix-it
Applies the fixes recommended by /lictor-security-check, with the user's explicit permission for each change. Walks through findings one at a time, shows the proposed change, gets approval, applies, runs tests if available, and moves on. Some fixes (rotating leaked credentials) require the user to act outside Claude …
ha-logs
A read-only troubleshooting skill for querying Hope Agent’s local SQLite databases, which store logs, conversations, and background-job status.
getting-started
Interactive post-onboarding tour that adapts to whatever data exists (calendar, Granola, or none). Use right after onboarding, or when the user says 'show me around', 'how do I start'. Also use proactively when the vault is < 7 days old. Not for the initial setup itself; use setup.