vellum-avatar

vellum-avatar is a skill for Claude Code, Codex from vellum-ai/vellum-assistant. It costs 24 tokens per session (1,399 once invoked), scanned A, original, MIT.

A guide for changing an assistant’s avatar, either by choosing a built-in character, uploading an image, or generating one with AI. An avatar is the picture or character used to represent the assistant.

In plain words
What is it for?
Use it to create, upload, generate, or restore an assistant avatar.
Why use it?
It gives the user clear ways to change the assistant’s visual identity while preserving or replacing its character settings as appropriate.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to create, upload, generate, or restore an assistant avatar.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vellum-ai/vellum-assistant/vellum-avatar
About the project

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.

vellum-ai/vellum-assistant · 1,225 stars · on GitHub · vellum.ai

Install

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.

Any agent
npx skills add vellum-ai/vellum-assistant --skill vellum-avatar
Clone the repo
git clone --depth 1 https://github.com/vellum-ai/vellum-assistant

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for vellum-avatar

README.md
[![agentmods](https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/vellum-avatar/github.svg)](https://agentmods.dev/skills/vellum-ai/vellum-assistant/vellum-avatar)
Your own site
<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.

agentmods 80×15 button for vellum-avatar

Your own site · 80×15
<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>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,399 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.01399
Opus 5 $0.00012 $0.00700
Sonnet 5 $0.00005 $0.00280
Haiku 4.5 $0.00002 $0.00140

Measured 8d ago against content hash 6c1928d28c84, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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 8d 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.

skills/vellum-avatar/SKILL.md · 141 lines

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 at data/avatar/avatar-image.png is 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 via assistant 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

Read the full file on GitHub · 141 lines

Changes

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.

  1. 8d ago First seen · 141 lines · 24 tokens per session scan A 6c1928d28c84

Subscribe to this mod's changes

vellum-avatar is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,225 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. 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.

Related

Other skills, from other repositories

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…

nodetool-ai/nodetool · 97 tokens

motion-principles

Decide how something should move before you animate it — durations, easing curves, stagger offsets, weight, anticipation and follow-through, given as numbers ready to paste into a NodeTool timeline animation. Use when motion feels stiff, floaty, robotic or cheap, when picking a duration or an easing for an entrance…

nodetool-ai/nodetool · 94 tokens

logo-reveal

Animate a brand mark on a NodeTool timeline — stroke draw-on, mask wipe, staggered build, wordmark type, an idle loop, and landing the settle on a sound logo. Use for an intro sting, a sign-off, an end card, a splash, or a loader loop. Not for designing the mark itself.

nodetool-ai/nodetool · 71 tokens

motion-background

Build an ambient looping backdrop on a NodeTool timeline — gradient beds from shape clips, slow loop animations, layered drift, and a generated video bed — that moves without stealing focus. Use for a title card backdrop, a hero bed behind text, an end card, a lower-third plate, or a loop behind a talking head. Not…

nodetool-ai/nodetool · 78 tokens

motion-direction

Set the motion language for a piece before anything is animated — one easing family, one timing unit, one transition family, one stagger rhythm — and audit a timeline against it. Use when starting a title pass or a whole cut, when animation feels busy, cheap or inconsistent across shots, or when turning a brand or…

nodetool-ai/nodetool · 87 tokens

anthropic-canvas-design

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

davekilleen/Dex · 62 tokens