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 vellum-avatargit 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/vellum-avatar)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/vellum-avatar"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/vellum-avatar/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/vellum-avatar"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/vellum-avatar.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 | $0.01399 |
| Opus 5.5 | $0.00010 | $0.00560 |
| Sonnet 5.5 | $0.00005 | $0.00280 |
| Haiku 4.5 | $0.00002 | $0.00140 |
Grade A, and why
vellum-avatar 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 1mo 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are helping the user customize their assistant's avatar. There are three ways to set an avatar: building a native character from traits, uploading a custom image, or generating one with AI. When the user says they want to change their avatar, present all three options and ask which they prefer.
Avatar Modes
The avatar system supports two representations:
- Native character - Defined by
data/avatar/character-traits.json(body shape, eye style, color). Rendered client-side as an animated character. A static PNG atdata/avatar/avatar-image.pngis auto-generated for use by other clients and the dock icon. - Custom image - A static PNG at
data/avatar/avatar-image.png. Used for uploaded or AI-generated avatars. When set via upload (assistant avatar set), character traits are preserved so the native character can be restored later viaassistant avatar remove. When AI-generated (assistant avatar generate), character trait files are removed.
Mode 1: Native Character Traits
The user picks a body shape, eye style, and color. Present the options conversationally - describe what each looks like so the user can choose without seeing a preview.
Body shapes
| Value | Description |
|---|---|
| blob | Soft, amorphous rounded shape |
| cloud | Puffy cloud silhouette |
| sprout | Small plant-like form with a stem |
| star | Five-pointed star |
| ghost | Classic ghost silhouette |
| urchin | Spiky sea-urchin shape |
| stack | Stacked rounded rectangles |
| flower | Flower with petals |
| burst | Spiky starburst |
| ninja | Stealthy masked figure |
Eye styles
| Value | Description |
|---|---|
| grumpy | Furrowed, slightly annoyed look |
| angry | Sharp, intense expression |
| curious | Wide, inquisitive eyes |
| goofy | Playful, off-kilter expression |
| surprised | Big round eyes, startled look |
| bashful | Shy, half-closed eyes looking to the side |
| gentle | Soft, kind expression |
| quirky | Asymmetric, offbeat look |
| dazed | Unfocused, dreamy stare |
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.
- 1mo ago First seen · 141 lines · 24 tokens per session scan A 6c1928d28c84
vellum-avatar is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,452 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 1,399 once invoked, about $0.0001 per session on Opus 5.5. 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
html-artifacts
Author the HTML for a plan artifact, dashboard iframe, or Slack attachment — structure, design plan, available runtime, theming, and craft. Read this before writing HTML for publishartifact, outputiframe, or slackattachhtml.
mermaid-diagram
Use when the user asks for a flowchart, architecture diagram, sequence diagram, ER diagram, state machine, gantt chart, or any visual that fits Mermaid syntax. Hope Agent's chat renders Mermaid blocks natively, so the diagram appears inline.
design-review
Use when a design artifact or revision needs a prepared review packet or an evidence-backed record of a review outcome, requirements, and decisions.
generative-ui
Use when presenting information already in hand as a small, static structured panel in the conversation — status, results, comparisons, or a compact summary — rather than prose, a markdown table, a widget, or an app.
st-widget-builder
Use when the user asks to render, build, visualise, mock up, or show a widget (chart, dashboard, card, table, graph) in the Mewbo Console. Teaches how to delegate the work to the st-widget-builder sub-agent instead of writing HTML or inline code yourself.
frame-composition
Stage the frame on a NodeTool timeline — grids, focal placement, safe areas per aspect ratio, depth layers and parallax, camera moves, and where elements enter and leave. Use when placing titles, lower thirds, shapes or overlays, when a layout must survive 16:9 and 9:16, when adding a push or a parallax move, or when…