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 mcp-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/mcp-setup)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/mcp-setup"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/mcp-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/mcp-setup"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/mcp-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 62 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Prompt Injection · line 64 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Excessive Agency · line 116 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium MCP Rug Pull · line 123 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00035 | $0.01457 |
| Opus 5 | $0.00017 | $0.00728 |
| Sonnet 5 | $0.00007 | $0.00291 |
| Haiku 4.5 | $0.00003 | $0.00146 |
Grade A, and why
mcp-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 2d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configure MCP servers to give the assistant access to any external tool or service that publishes an MCP endpoint.
DO NOT run exploratory commands. Do not check available CLI commands, search for bun/npx/node, or investigate transport types. Follow the steps below exactly and stop when done. (Looking up a service's MCP endpoint URL in its own documentation is allowed when the service is not in the recipe table, per Step 3.)
When to Use
USE THIS SKILL WHEN:
- User asks to connect any external tool or service via MCP
- User asks "what MCP servers / integrations do I have?"
- An MCP tool returns an auth error → run
assistant mcp auth <name> - User wants to disconnect an integration
Prefer Native OAuth Integration (check this first)
Many services have built-in OAuth integrations that are simpler and more reliable than MCP. Before setting up MCP, check whether the service already has a native OAuth provider:
assistant oauth providers list
If the service appears in that list, connect it natively instead of using MCP:
assistant oauth connect <provider>
Only use MCP when:
- The service is not in
assistant oauth providers list - The user explicitly asks to use MCP for a specific service
- The native OAuth integration fails or lacks features the user needs
Step 1 — Detect your environment
Before doing anything else, determine which environment you are in.
Try host_bash:
echo "desktop ok"
- If it succeeds → you are on the desktop app. Use
host_bashfor all commands, includingauth(opens a local browser). - If it is unavailable → you are on the web app (or a cloud-hosted session). Use
bashfor all commands, includingauth(the platform handles the browser redirect).
Both environments fully support MCP. The only difference is which tool runs the commands.
Step 2 — Check the recipe table
Check this table before doing anything else. If the service is listed, run the command shown and do nothing else — no exploration, no checking available commands, no looking up documentation.
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.
- 2d ago Changed · -8 lines e235c2e41dfa
- 9d ago First seen · 174 lines · 35 tokens per session scan A db97e80e4a78
mcp-setup is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,234 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 1,457 once invoked, about $0.0002 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 2026-09-03.
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 …
continual-learning
Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…
ha-logs
A read-only troubleshooting skill for querying Hope Agent’s local SQLite databases, which store logs, conversations, and background-job status.