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 notificationsgit 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/notifications)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/notifications"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/notifications/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/notifications"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/notifications.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 10 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 Prompt Injection · line 173 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 Prompt Injection · line 32 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 Prompt Injection · line 36 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 Prompt Injection · line 37 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 Prompt Injection · line 101 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 Prompt Injection · line 111 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 Prompt Injection · line 166 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 Prompt Injection · line 179 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 Prompt Injection · line 181 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 Prompt Injection · line 183 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
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 | $0.00009 | $0.03208 |
| Opus 5.5 | $0.00004 | $0.01283 |
| Sonnet 5.5 | $0.00002 | $0.00642 |
| Haiku 4.5 | $0.00001 | $0.00321 |
Grade A, and why
notifications 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 12d 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Call this when something happened that the user would want to know about — a completed task with a notable outcome, an interesting observation, a positive trend you noticed in monitored data, useful research worth surfacing, a workflow that got blocked, a credential or token failure, etc. Do not call it for routine task completions where nothing notable happened. When in doubt and you have a real observation to share, share it.
Exception: you are running a schedule. The "was this notable?" test does not apply to a scheduled run. The user picked the cadence; the run happening at all is what they asked to see. A scheduled run that produces any user-facing output (a briefing, a digest, a report, or a check whose answer is "nothing changed") ends by sending that output as a notification. Writing it into the conversation and stopping does not reach the user: nobody is looking at a scheduled run's conversation.
That does not license noise. Judgment moves from whether to notify to what to say: a run with a genuinely empty result says so in one line rather than padding it, and a run that only did silent housekeeping (rotating a cache, syncing a file) with nothing to report stays quiet.
Watcher ticks are not scheduled runs. A watcher stays quiet unless its action prompt says this event is worth surfacing. Unmatched events and polls with nothing new must not produce a notification.
Sending Notifications
Always pass --title. Skipping it triggers a fallback that just truncates --message to 60 chars and shows it as the title — the user sees the same text twice with no scannability gained.
assistant notifications send \
--title "Short headline" \
--message "Your verbatim observation in your own words"
For time-sensitive items:
assistant notifications send --title "..." --message "..." --urgent
Command Reference
| Flag | Required | Description |
|---|---|---|
--message <message> |
Yes | Notification body. Markdown (GFM) renders in the detail panel; the OS banner shows plain text. |
--title <title> |
Yes in practice | Short headline (≤ 8 words). Omitting it triggers a body-truncation fallback that shows up as a duplicate of --message — always write a real title. |
--urgent |
No | Mark as needing attention now/soon |
--quiet |
No | Keep it quiet: no OS banner even when the user banners every notification, and no From me mobile push. Still lands in the conversation and Home. |
--preferred-channels |
No | Additive channel hints. Vellum stays selected. |
--channels |
No | Exclusive allowlist (e.g. telegram). Replaces the default set. Urgent delivery does not add vellum or platform. Wins over --preferred-channels. |
--json |
No | Output machine-readable JSON |
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.
- 12d ago Changed · +3 lines b6e1f8290301
- 1mo ago Changed · +15 lines 4d04baa17dd4
- 1mo ago Changed · +1 lines ac1ed29ebf0a
- 1mo ago Changed 8f5e1487a550
- 1mo ago Changed · +2 lines 1ebf4dd59a4f
- 1mo ago Changed · +4 lines 13f0b9d2234c
- 1mo ago First seen · 231 lines · 9 tokens per session scan A ac4f6d8444fb
notifications is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,450 stars, last pushed 2d ago), licensed MIT. It adds 9 tokens to every session and 3,208 once invoked, about $0.0000 per session on Opus 5.5. 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.
career-coach
Personal career coach with 4 modes: weekly reports, monthly reflections, self-reviews, promotion assessments.
career-setup
Initialize career development system (job description, ladder, reviews, goals).
daily-review
Close out the day: what got done vs planned, meeting follow-ups, learnings, and tomorrow's focus. Use when the user says 'review my day', 'wrap up', 'end of day', or it's evening. Also use proactively when the day's work is clearly done. Not for setting up the morning; use daily-plan.
week-review
Review the week with concrete accomplishments (not fake percentages), pattern detection and goal tracking. Use when the user says 'how was my week', 'week review', or it's their last working day. Also use proactively when a week's priorities are largely resolved. Not for planning the coming week; use week-plan.
diff-adopt
Adopt one shared DexDiff methodology — reads a workflow description, adapts it to your role and vault, and walks you through setup. Use when the user says 'adopt this workflow', 'set me up like this doc'. Not for a full published profile by handle; use diff-adopt-profile.