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 gmail-triggergit 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/gmail-trigger)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/gmail-trigger"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/gmail-trigger.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.01538 |
| Opus 5 | $0.00018 | $0.00769 |
| Sonnet 5 | $0.00007 | $0.00308 |
| Haiku 4.5 | $0.00004 | $0.00154 |
Grade A, and why
gmail-trigger 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gmail Triggers (Beta)
Polls the user's Gmail inbox on a cron and escalates to the assistant only when a new message arrives — an empty poll spends zero LLM tokens. Installing it means creating a script-mode schedule that runs the schedule's own copy of the shipped poll script. Schedule mechanics (script mode, the schedules/<id>/ convention, waking the agent loop) are documented in the included schedule skill.
Why this instead of a watcher
A watcher could only be configured through its prompt and its cadence. This one is a script that belongs to the schedule, so the assistant can change anything about how it behaves by simply editing the script. And because it runs as a schedule, its runs, errors, and cost all show up on the Schedules page in the app.
Setup
1. Ensure Google is connected
The trigger reads Gmail through the user's Google OAuth connection with Gmail read access. Check with:
assistant oauth status google
If no connection is found, load the vellum-oauth-integrations skill — it evaluates whether managed or your-own mode is appropriate and guides the user through connecting. Managed (proxy) and your-own OAuth both work — poll.ts calls Gmail via assistant oauth request, which resolves either automatically.
2. Choose the accounts to watch
If oauth status shows more than one active Google connection, ask the user which inboxes to watch and pass one --account <email> flag per chosen inbox. With a single connection the flag can be omitted. One schedule watches all chosen accounts and delivers one combined digest.
3. Collect the action prompt
Ask the user what should happen when new email arrives — e.g. "notify me only about emails needing a reply" or "summarize newsletters, flag anything from my boss". If the user doesn't care, omit the flag and the default applies: summarize what's new and flag anything urgent.
4. Ask about the first sync
By default the trigger starts from now and never escalates pre-existing email. Ask the user whether the first sync should instead include recent mail; if yes, append --lookback <duration> (90m/4h/2d/1w).
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 · 104 lines · 37 tokens per session scan A dd53529d2e44
gmail-trigger is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,204 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 1,538 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 2026-08-30.
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.