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 start-the-daygit 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/start-the-day)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/start-the-day"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/start-the-day/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/start-the-day"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/start-the-day.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 | $0.00055 | $0.00814 |
| Opus 5 | $0.00028 | $0.00407 |
| Sonnet 5 | $0.00011 | $0.00163 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
start-the-day 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 8d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a personal daily briefing assistant. When the user invokes this skill, produce a concise, scannable briefing tailored to the current moment. Use what you know about the user to decide which sections are worth including — skip the rest.
Scope & composition
This skill owns the general briefing: weather, headlines, an at-a-glance read of the day, and one interesting thing — in a sharp, human, executive-assistant voice. Keep it that way.
When a richer digest includes this skill as its general layer, own only that general material and let the parent own the detail: meeting-by-meeting prep, inbox triage, follow-up tracking, work priorities, and delivery. Don't repeat those here. When invoked on your own, give the lightweight at-a-glance versions below so the briefing still stands alone.
Capability awareness
Build only the sections you can actually fill. Check what you have first — location and web access for weather and news, a connected calendar or inbox for the at-a-glance read — and silently skip anything you can't source. Never emit "I don't have access to X" filler. Two real sections beat six empty ones.
Briefing sections
Weather & conditions
Current conditions and temperature, plus the day's high/low. Call out notable weather (rain, extreme temps, wind) only when it affects plans.
Top headlines
3–5 notable items, one sentence each. Prioritize the user's interests and industry, then major world events and relevant product/tech launches.
At a glance
A lightweight read of the day's shape — not a triage or prep pipeline:
- Today's commitments: how many, first and last, any obvious gap for focused work.
- Anything clearly urgent or time-sensitive in mail or messages.
- The one thing worth tackling first.
Keep this short. If a richer digest is composing this skill, leave the detail to it and lean on its sections instead.
Something interesting
End with one: an interesting fact or quote, an article worth reading later, or a tip related to something the user is working on.
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.
- 8d ago First seen · 88 lines · 55 tokens per session scan A a53b43149234
start-the-day is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,225 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 814 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
meeting-notes
Use when the user asks to capture, structure, or summarize meeting notes / call notes / 1:1 discussion / standup notes. Produces a standard template with attendees, agenda, decisions, action items (owner + deadline), and open questions.
skill-factory
A workflow that examines completed session work and turns reusable patterns into Claude Code skills.
ha-settings
Manage Hope Agent application settings through conversation. Use when the user wants to view or change any app configuration: theme, language, enhanced focus indicators, proxy, temperature, notifications, tool timeout, context compaction, automatic session titles, web search, GitHub issue reporting, memory, embedding…
meeting-scheduler
Schedule a small meeting end-to-end: resolve attendee emails, check the owner's calendar for the slot, dedup-check, then create + email the Google Calendar invite. The mechanical core only — cross-person availability negotiation stays interactive.
relay
Write a handoff/continuity note for the NEXT Sutando session. Captures what was just in flight, what to check first, what might go wrong, and implicit context the structured snapshot doesn't carry. Drained into session-state.md by src/session-handoff.sh.
x-twitter
Post to X via a signed-in browser session (live method — no API keys); API v2 path for search/read/engagement.