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 gmailgit 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/gmail)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/gmail"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/gmail.svg" alt="Measured on agentmods" 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 192 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 | $0.00020 | $0.07590 |
| Opus 5 | $0.00010 | $0.03795 |
| Sonnet 5 | $0.00004 | $0.01518 |
| Haiku 4.5 | $0.00002 | $0.00759 |
Grade A, and why
gmail scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. **Never try alternative approaches.** Don't use curl, browser automation, or any workaround. If the scripts can't do it, the reconnection flow is the answer. How it starts
The opening of the file, as written. The whole thing — 470 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill provides Gmail-specific operations beyond the shared messaging skill. For cross-platform messaging (send, read, search, reply), use the messaging skill. Gmail operations depend on the messaging skill's provider infrastructure - load messaging first if Gmail is not yet connected.
Script Reference
All operations use CLI scripts that return JSON:
- Success:
{ "ok": true, "data": ... } - Failure:
{ "ok": false, "error": "..." }
| Script | Operation | Description |
|---|---|---|
gmail-email.ts |
draft |
Create email drafts in the Drafts folder (including reply drafts) |
gmail-email.ts |
send-draft |
Send an existing draft (requires explicit user confirmation) |
gmail-email.ts |
forward |
Create forward drafts, preserving attachments |
gmail-email.ts |
trash |
Move messages to Trash |
gmail-manage.ts |
label |
Add or remove labels on messages |
gmail-manage.ts |
follow-up |
Track/untrack messages for follow-up using a dedicated "Follow-up" label |
gmail-manage.ts |
attachments |
List and download email attachments |
gmail-manage.ts |
filters |
Create, list, and delete Gmail filters |
gmail-manage.ts |
vacation |
Get, enable, or disable the vacation auto-responder |
gmail-manage.ts |
unsubscribe |
Unsubscribe from mailing lists (requires explicit user confirmation) |
gmail-scan.ts |
sender-digest |
Scan inbox and group messages by sender for declutter workflows |
gmail-scan.ts |
outreach-scan |
Identify cold outreach senders (no List-Unsubscribe header) |
gmail-archive.ts |
archive |
Archive messages (single, batch message_ids, cache_key+sender-emails, query) |
gmail-archive.ts |
archive --dry-run |
Preview what would be archived without executing (writes staged ops to log) |
gmail-archive.ts |
archive --resume |
Resume an interrupted archive run from its last checkpoint |
gmail-commit.ts |
commit |
Execute all staged ops from a dry-run |
gmail-commit.ts |
cancel |
Delete a run log without executing anything |
gmail-runs.ts |
list |
List recent operation runs with status summaries |
gmail-runs.ts |
inspect |
Show detailed log entries for a specific run |
gmail-runs.ts |
prune |
Delete operation logs older than 30 days |
gmail-reverse.ts |
--run-id |
Reverse all committed ops in a run (un-archive, un-label, un-trash) |
gmail-reverse.ts |
--run-id --thread |
Reverse a specific message within a committed run |
gmail-prefs.ts |
list |
List blocklist and safelist preferences |
gmail-prefs.ts |
add-blocklist |
Add sender emails to the blocklist |
gmail-prefs.ts |
add-safelist |
Add sender emails to the safelist |
gmail-prefs.ts |
remove-blocklist |
Remove sender emails from the blocklist |
gmail-prefs.ts |
remove-safelist |
Remove sender emails from the safelist |
gmail-prefs.ts |
get-management-config |
Get inbox management config (stage, interrupt threshold, last run) |
gmail-prefs.ts |
set-management-config |
Update inbox management config (--stage, --interrupt-threshold, --last-run) |
What ships with it
14 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.
- assets/icon.svg 355 B
- scripts/gmail-archive.ts 16 KB runs code
- scripts/gmail-auto-filters.ts 17 KB runs code
- scripts/gmail-commit.ts 6.4 KB runs code
- scripts/gmail-email.ts 12 KB runs code
- scripts/gmail-manage.ts 26 KB runs code
- scripts/gmail-prefs.ts 8.5 KB runs code
- scripts/gmail-reverse.ts 9.5 KB runs code
- scripts/gmail-runs.ts 2.1 KB runs code
- scripts/gmail-scan.ts 23 KB runs code
- scripts/lib/common.ts 1.9 KB runs code
- scripts/lib/gmail-client.ts 8.2 KB runs code
- scripts/lib/mime-builder.ts 2.7 KB runs code
- scripts/lib/op-log.ts 12 KB runs code
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.
- 4d ago Changed · -9 lines 6a433a38e178
- 8d ago First seen · 479 lines · 20 tokens per session scan A 11d94796e28c
gmail is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,204 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 7,590 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.