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 conversation-groupsgit 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/conversation-groups)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/conversation-groups"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/conversation-groups/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/conversation-groups"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/conversation-groups.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00024 | $0.00470 |
| Opus 5 | $0.00012 | $0.00235 |
| Sonnet 5 | $0.00005 | $0.00094 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
conversation-groups 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 today.
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.
What it actually says
Organize the user's conversations into sidebar groups. Groups are the sections shown in the conversation sidebar; each conversation belongs to exactly one group.
Groups
- Custom groups are user-defined sections (e.g. "Work", "Travel planning"). Create them with
conversation_group_createand file conversations withconversation_move_to_group. - System groups are built in and cannot be created, renamed, or deleted:
system:pinned(Pinned) — moving a conversation here pins it; moving it elsewhere unpins it.system:all(Recents) — the default ungrouped section. Move a conversation here to "remove" it from a custom group.system:scheduled(Scheduled) andsystem:background(Background) — hold automated conversations. Moving a conversation into these demotes it out of the Recents listing; avoid unless the user explicitly asks.
Usage
- When mentioning a conversation in Vellum chat, link it as
[Title](/assistant/conversations/<id>). Use that path only in Vellum chat. Do not use it in Slack, Telegram, Discord, email, or notifications. conversation_move_to_groupdefaults to the current conversation, so "file this chat under Work" needs no conversation id.- Groups can be referenced by name (case-insensitive) or id. Prefer names; fall back to ids when names are ambiguous.
- When the user asks to organize their conversations, check the existing groups first (
conversation_group_list) and reuse a fitting group rather than creating near-duplicates ("Work" vs "Work stuff"). - Creating a group whose name already exists reuses the existing group instead of creating a duplicate.
- Moves only affect sidebar organization — no conversation content changes, and every move is reversible.
- Subagent and background conversations are hidden from the sidebar regardless of group; moving them has no visible effect.
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.
- today Changed · +1 lines 4744fcac9408
- 10d ago First seen · 30 lines · 24 tokens per session scan A e994c90c0c41
conversation-groups is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,225 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 470 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 2026-08-30.
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…
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.