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-workspace-themegit 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-workspace-theme)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/vellum-workspace-theme"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/vellum-workspace-theme/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-workspace-theme"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/vellum-workspace-theme.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 9 findings, up to high
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 →
- high Tool Misuse · line 115 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Prompt Injection · line 47 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
- medium Prompt Injection · line 50 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
- medium Prompt Injection · line 51 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
- medium Prompt Injection · line 56 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
- medium Prompt Injection · line 52 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
- medium Prompt Injection · line 53 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
- medium Prompt Injection · line 54 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
- medium Prompt Injection · line 55 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 | $0.00072 | $0.01665 |
| Opus 5 | $0.00036 | $0.00833 |
| Sonnet 5 | $0.00014 | $0.00333 |
| Haiku 4.5 | $0.00007 | $0.00167 |
Grade A, and why
vellum-workspace-theme 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.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are customizing the visual theme of the app you and your user share. The theme lives in one file — $VELLUM_WORKSPACE_DIR/ui/theme.json — which the assistant runtime validates and serves to every connected client. Valid changes apply live, layered on top of the built-in light/dark/velvet base theme: open windows re-color within a few seconds of the file being saved. No restart, no build step.
All commands in this skill use the bash tool. $VELLUM_WORKSPACE_DIR is available in the sandbox environment.
Inspect current state
Always check what's there before changing it:
cat "$VELLUM_WORKSPACE_DIR/ui/theme.json" 2>/dev/null || echo "No theme yet — clients render the built-in theme"
The file
A complete example (all eleven token slots — you rarely need all of them):
{
"version": 1,
"tokens": {
"accent": "#e8a04c",
"background": "#1c1512",
"surface": "#2b2018",
"surfaceRaised": "#332619",
"border": "#43301f",
"text": "#f2e4d4",
"textMuted": "#a68d75",
"userBubbleBackground": "#26201a",
"userBubbleText": "#efe3d2",
"assistantBubbleBackground": "#33202a",
"assistantBubbleText": "#ffd7e4"
}
}
| Token | What it controls |
|---|---|
accent |
Primary buttons, highlights, active states. The button-label color is derived automatically so it stays readable on any accent. |
background |
The page background and base surfaces. |
surface |
Panels, popovers, and overlays. |
surfaceRaised |
Elevated cards. |
border |
Borders and dividers. |
text |
Main copy. |
textMuted |
Secondary labels and captions. |
userBubbleBackground / userBubbleText |
The user's chat message bubble. |
assistantBubbleBackground / assistantBubbleText |
Accepted and validated, but not yet rendered — assistant messages don't have a themeable container yet. Safe to set now; they light up when the surface ships. |
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.
- 8d ago First seen · 121 lines · 72 tokens per session scan A 15292a759d05
vellum-workspace-theme is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,225 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 1,665 once invoked, about $0.0004 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
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 saveplan, 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.
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.
plan-review-experience
Experience-dimension reviewer for written plans (UX + DX). Use when running plan-review or directly when an experience review is wanted. Activate for keywords like "UX review", "DX review", "experience review", "error states", "API ergonomics", "developer experience", "user states". Scores 5 sub-dimensions 0-10…
remote-screenshot
Take a real screenshot of a running Neovim from inside the Claude Code on the web container, which has no X server. Use when asked to show what a UI change looks like, or to attach an image of the chat buffer, a split layout, an approval prompt or a picker. Requires CLAUDECODEREMOTE=true — on a local machine there is…