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 inbox-managementgit 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/inbox-management)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/inbox-management"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/inbox-management/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/inbox-management"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/inbox-management.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 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
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 | $0.00050 | $0.04259 |
| Opus 5 | $0.00025 | $0.02129 |
| Sonnet 5 | $0.00010 | $0.00852 |
| Haiku 4.5 | $0.00005 | $0.00426 |
Grade A, and why
inbox-management 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 7d 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 — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inbox Management Skill
Companion to inbox-cleanup. Cleanup drains the backlog once. Management keeps the inbox clean on a schedule: archiving noise, flagging urgents, drafting replies, and catching stale follow-ups.
Runs as a script-mode schedule. Each fire polls Gmail deterministically. An empty poll (no new inbox mail and no due follow-up) exits without waking the assistant, so leftover Stage 0 mail is not re-judged every few hours. The assistant runs only when the poll attaches a digest.
Default posture: high recall on noise archiving, high precision on user interruption. Archive aggressively on known-safe patterns. Ping sparingly. Never auto-send a reply. When unsure, flag instead of archiving.
Trust Ladder
A single wrong archive of an important email kills trust. Earn autonomy in stages:
| Stage | Archive behavior | Draft behavior | Alerts |
|---|---|---|---|
| 0. Flag-only (default) | Nothing archived. All archive calls use --dry-run. Summary shows what would be archived for user review. |
Drafts created in-thread, listed in summary. | Urgent scan active. |
| 1. Standard | Silent archive of known-safe categories only (calendar responses, no-reply, newsletters). Cold outreach still flagged. Batches > 1,000 ops auto-dry-run. | Drafts created in-thread, summarized per run. | Urgent scan active. |
| 2. Aggressive | Above + cold outreach archived by LLM judgment (default archive, flag only when relevant to user). All ops logged for reversal. | Same as Stage 1. | Urgent scan active. |
What ships with it
4 files 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.
- 7d ago Changed · +18 lines 3215c7b67d14
- 8d ago First seen · 307 lines · 50 tokens per session scan A cd4ef2db6d7b
inbox-management is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,225 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 4,259 once invoked, about $0.0003 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.