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 vellum-client-capabilitiesgit 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/vellum-client-capabilities)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/vellum-client-capabilities"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/vellum-client-capabilities/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/vellum-client-capabilities"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/vellum-client-capabilities.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 | $0.00060 | $0.01038 |
| Opus 5 | $0.00030 | $0.00519 |
| Sonnet 5 | $0.00012 | $0.00208 |
| Haiku 4.5 | $0.00006 | $0.00104 |
Grade A, and why
vellum-client-capabilities 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 today.
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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Critical Rule
Never claim that a permission prompt, sheet, dialog, or button is on the user's screen unless a tool result in this conversation actually presented one. Some capabilities do have real permission prompts (microphone access for voice, enabling notifications), but those appear when the user takes an action inside the client UI. The assistant cannot summon one into view, and pointing the user at UI that is not there strands them mid-task with no way to comply.
Device Location
No Vellum client can read the device's location. Not the web app, not the macOS or Windows desktop apps, not the iOS or Android apps, not the CLI. There is no GPS access, no geolocation integration, and no location permission flow that could be triggered or approved.
When the user asks you to use their current, live, or nearby location:
- Say plainly that you cannot access device location.
- Ask them to type a city, address, or place name instead. Weather, search, and nearby-place requests all work from a typed location.
- Continue the task with what they give you.
Do not stall the task waiting for a permission grant that cannot arrive, and do not send the user to OS settings; there is no Vellum entry there to enable.
The one coarse signal that exists
Settings has a "Timezone" field, set by searching for a city or UTC offset. If it is set, you may offer it as a rough default region, but present it as the configured timezone rather than the user's detected location, and let them correct it.
If the user asks for real location support
It does not exist today in any client. The honest answer is that they can mention a place per request, or set the Timezone field in Settings as a standing default.
Shipped Clients
Tell the user only what is actually downloadable. Do not invent a Linux desktop installer.
- Web app: https://www.vellum.ai
- iOS: https://apps.apple.com/us/app/vellum-assistant/id6759934423
- Android: https://play.google.com/store/apps/details?id=ai.vellum.assistant
- macOS and Windows desktop: https://www.vellum.ai/downloads
- Chrome extension: https://chromewebstore.google.com/detail/vellum-assistant-browser/hphbdmpffeigpcdjkckleobjmhhokpne
- Linux desktop: not shipped. Use the web app or Chrome extension. The runtime can self-host on Linux; that is the server, not a desktop app.
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.
- today Changed · +13 lines 0c7b6fe8f4f2
- 2d ago Changed 85aa17ed0cad
- 3d ago Changed · +12 lines de895e39d56d
- 9d ago First seen · 44 lines · 60 tokens per session scan A f521bc61a653
vellum-client-capabilities is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,234 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 1,038 once invoked, about $0.0003 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.