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 daily-briefinggit 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/daily-briefing)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/daily-briefing"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/daily-briefing/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/daily-briefing"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/daily-briefing.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 Excessive Agency · line 12 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00075 | $0.00676 |
| Opus 5 | $0.00037 | $0.00338 |
| Sonnet 5 | $0.00015 | $0.00135 |
| Haiku 4.5 | $0.00007 | $0.00068 |
Grade A, and why
daily-briefing 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 13d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Send yourself a structured morning briefing every day — without asking for it. The briefing pulls your recent memory, decisions, and workspace context, composes a concise summary, and delivers it to all your active channels (Slack, Telegram, macOS, etc.).
Setup
Enable the briefing by telling your assistant:
"Set up my daily briefing at 9am"
The assistant will create a recurring schedule. On first run you will receive a briefing in all connected channels.
You can also say:
- "Set my daily briefing to 7:30am"
- "What time is my daily briefing?"
- "Pause my daily briefing"
- "Turn off my morning briefing"
What the briefing covers
Each briefing is structured into up to four sections, each capped at 3–5 bullets:
Action Items — Unresolved tasks, pending decisions, or commitments due today.
Progress — Notable completions or milestones from the past 24 hours.
On Your Radar — Anything flagged as important, upcoming, or worth watching.
Suggested Next Steps — 2–3 concrete actions ranked by impact.
Sections with nothing to report are omitted entirely.
How to enable
Run this skill and follow the prompts, or tell your assistant directly:
bun scripts/setup.ts
The setup script asks for your preferred delivery time and timezone, then creates the schedule.
Managing the schedule
Once enabled, all management is conversational — just tell your assistant:
| What you want | Say |
|---|---|
| Change time | "Move my briefing to 8am" |
| Check status | "When is my next briefing?" |
| Pause | "Pause my daily briefing" |
| Resume | "Resume my daily briefing" |
| Disable | "Turn off my morning briefing" |
How it works
Setup runs scripts/setup.ts via bash, which calls assistant schedules create to register a recurring execute-mode schedule. When the schedule fires each day:
- The scheduler boots a background conversation with the briefing prompt as the initial message.
- The agent runtime injects your recent memory, decisions, and workspace context automatically.
- The agent composes the briefing and runs
assistant notifications sendto deliver it. - The notification routes to all your connected channels — the same pipeline as any other Vellum notification.
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.
- 13d ago First seen · 79 lines · 75 tokens per session scan A dab3b66d8b22
daily-briefing is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,234 stars, last pushed today), licensed MIT. It adds 75 tokens to every session and 676 once invoked, about $0.0004 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
identity-snapshot
Generate a living profile of the user's working patterns, decision tendencies and quality preferences from their Dex data. Use when the user says 'what are my patterns', 'how do I work', or during week-review. Also use proactively when the model (older than 7 days) is stale. Not for planning a week; use week-plan.
capture
Captures ideas, notes, links, and thoughts quickly. Use when the user says 'note', 'idea', 'capture', 'save this', 'remember', or wants to save something for later.
productivity-update
Sync tasks and refresh memory from your current activity.
hibernate
Save comprehensive state snapshot before extended travel or breaks - enables context recovery weeks/months later.
research-assistant
Deep vault search and synthesis - find what's known before searching externally.
weekly-hygiene
Vault structural maintenance - broken links, stale items, folder mismatches, hygiene report.