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 watchergit 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/watcher)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/watcher"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/watcher/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/watcher"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/watcher.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 | $0.00035 | $0.01361 |
| Opus 5 | $0.00017 | $0.00681 |
| Sonnet 5 | $0.00007 | $0.00272 |
| Haiku 4.5 | $0.00003 | $0.00136 |
Grade A, and why
watcher 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 5d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create and manage watchers that poll external services for events and process them with an action prompt.
Concepts
- Provider - The external service to poll (e.g. "gmail"). Each provider defines how to fetch and parse events.
- Action prompt - LLM instructions for handling detected events. Sent along with event data to a background conversation.
- Poll interval - How often to check for new events (minimum 15 seconds, default 60 seconds).
- Digest - Summary of recent watcher activity, grouped by watcher with time-based filtering.
Lifecycle
- Create a watcher with
assistant watchers create, specifying a name, provider, and action prompt. - The system polls the provider at the configured interval.
- Detected events are processed according to the action prompt.
- Use
assistant watchers digestto review recent activity.
Available Commands
Create a watcher
assistant watchers create \
--name <name> \
--provider <provider> \
--action-prompt <prompt> \
[--poll-interval <ms>] \
[--config <json>] \
[--credential-service <service>]
| Flag | Required | Description |
|---|---|---|
--name |
Yes | A human-readable name for this watcher (e.g. "My Gmail") |
--provider |
Yes | The provider to poll (see Available Providers below) |
--action-prompt |
Yes | Instructions for the LLM on how to handle detected events |
--poll-interval |
No | How often to poll in milliseconds. Defaults to 60000 (1 minute). Minimum 15000 |
--config |
No | Provider-specific configuration as JSON (e.g. filter criteria) |
--credential-service |
No | Override the credential service to use. Defaults to the provider's required service |
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.
- 5d ago First seen · 165 lines · 35 tokens per session scan A 63cc160bdf39
watcher is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,204 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 1,361 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
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.