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 macos-automationgit 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/macos-automation)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/macos-automation"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/macos-automation/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/macos-automation"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/macos-automation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 19 Subtle instructions detected that may alter agent decision-making or introduce hidden biases.Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.
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 | $0.00022 | $0.00767 |
| Opus 5 | $0.00011 | $0.00383 |
| Sonnet 5 | $0.00004 | $0.00153 |
| Haiku 4.5 | $0.00002 | $0.00077 |
Grade A, and why
macos-automation 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 9d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use this skill to interact with native macOS apps and system-level features via osascript (AppleScript) through host_bash. Always prefer osascript over browser automation or computer-use for anything involving a native macOS app.
Supported Apps
Communication: Messages, Mail, Microsoft Outlook, FaceTime Contacts & Calendar: Contacts, Calendar, Reminders Notes & Writing: Notes, TextEdit, Pages, BBEdit, CotEditor Files: Finder, Path Finder Browsers: Safari, Google Chrome Music & Media: Music (iTunes), Spotify, VLC, Podcasts, TV Productivity: OmniFocus, Things 3, OmniOutliner, OmniPlan, OmniGraffle Office: Microsoft Word, Microsoft Excel, Numbers, Keynote Developer tools: Xcode, Terminal, iTerm2, Script Editor System: System Events (UI scripting for any app), System Settings Automation: Keyboard Maestro, Alfred, Automator Creative: Adobe Photoshop, Final Cut Pro
For any unlisted app, check scriptability first:
osascript -e 'tell application "AppName" to get name'
Examples
# Send an iMessage
osascript -e 'tell application "Messages" to send "Hello!" to buddy "[email protected]"'
# Look up a contact
osascript -e 'tell application "Contacts" to get {name, phones} of every person whose name contains "Marina"'
# Read upcoming calendar events
osascript -e 'tell application "Calendar" to get summary of every event of calendar "Home" whose start date > (current date)'
# Create a reminder
osascript -e 'tell application "Reminders" to make new reminder with properties {name:"Buy milk", due date:((current date) + 1 * hours)}'
# Send an email
osascript -e 'tell application "Mail" to send (make new outgoing message with properties {subject:"Hi", content:"Hello", visible:true})'
# Create a note
osascript -e 'tell application "Notes" to make new note at folder "Notes" with properties {body:"My note"}'
# Open a URL in Safari
osascript -e 'tell application "Safari" to open location "https://example.com"'
# Play/pause Music
osascript -e 'tell application "Music" to playpause'
# Display a system notification
osascript -e 'display notification "Done!" with title "Vellum"'
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.
- 9d ago First seen · 78 lines · 22 tokens per session scan A ad9bb6de9e2b
macos-automation is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,238 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 767 once invoked, about $0.0001 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…
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.
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.
x-twitter
Post to X via a signed-in browser session (live method — no API keys); API v2 path for search/read/engagement.