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 deploy-fullstack-vercelgit 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/deploy-fullstack-vercel)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/deploy-fullstack-vercel"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/deploy-fullstack-vercel/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/deploy-fullstack-vercel"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/deploy-fullstack-vercel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, 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 Prompt Injection · line 61 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 66 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 67 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 69 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 70 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 Excessive Agency · line 262 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 | $0.00041 | $0.02486 |
| Opus 5.5 | $0.00016 | $0.00994 |
| Sonnet 5.5 | $0.00008 | $0.00497 |
| Haiku 4.5 | $0.00004 | $0.00249 |
Grade A, and why
deploy-fullstack-vercel 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**The stored Vercel API token is reserved for brokered `publish_page` and `unpublish_page` actions only.** Do not pass it to `bash`, `curl`, Vercel CLI commands, or proxy credential injection. Do not use `network_mode: " How it starts
The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploy Fullstack to Vercel
Deploy a full-stack app with a React/Vite frontend and Python/FastAPI backend to Vercel as a serverless demo, OR deploy a Vellum-built app from the library. No auth required - meant for demos, portfolio pieces, and quick showcases.
When to Use
- User says "deploy this to Vercel", "host this", "publish this"
- User has a project with a frontend + backend they want live
- User wants to deploy a Vellum app that uses backend features (data store, custom routes)
- User wants a quick demo deployment (no persistent database needed)
Authentication
Vellum App Publishing
For publishing Vellum apps from the library, use the built-in publish_page tool. This is the preferred path — it uses the stored Vercel API token (vercel/api_token) via the brokered publish flow without exposing the token to shell commands.
The stored Vercel API token is reserved for brokered publish_page and unpublish_page actions only. Do not pass it to bash, curl, Vercel CLI commands, or proxy credential injection. Do not use network_mode: "proxied" with credential_ids for Vercel deployments.
Custom Full-Stack Deployments
For custom projects that need Vercel deployment (not Vellum app publishing):
- Install the Vercel CLI with
bun install -g vercel(not npm — npm is not available in the sandbox). - Use
vercel loginto authenticate interactively (opens browser for the user). - If the user does not want to use CLI auth, stop and ask them for an approved deployment path. Do not extract, inject, or shell with the stored API token.
Deploying a Vellum App
When the user asks to deploy a Vellum app from their library (from /workspace/data/apps/<app-name>/):
1. Detect Vellum Bridge Usage
Check the compiled app for Vellum bridge API usage:
grep -l "window\.vellum\.\|vellum\.fetch\|vellum\.data\|vellum\.sendAction" /workspace/data/apps/<app-name>/dist/*.js /workspace/data/apps/<app-name>/dist/*.html 2>/dev/null
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 · 265 lines · 41 tokens per session scan A 53c7708f1e95
deploy-fullstack-vercel is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,444 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 2,486 once invoked, about $0.0002 per session on Opus 5.5. 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
deploy
Deploy an application to a configured environment.
monitoring-alerting
Monitoring and alerting design reviewer for production backend services. ALWAYS use when writing Prometheus alerting rules, designing Grafana dashboards, defining SLI/SLO, configuring alert routing (PagerDuty/OpsGenie/Slack), or reviewing existing monitoring setups. Covers SLI/SLO definition, alert rule quality…
sandbox-aws
Sign AWS requests (S3 and every other SigV4 service) in a Code node or CodeAct action, with NodeTool's signer running on the host.
playbook-cloud
Cloud IAM privesc paths and metadata endpoints per provider. Load when the target is cloud or you obtain cloud creds/metadata. Triggers - AWS/GCP/Azure, IAM, S3/blob, 169.254.169.254, access key.
lictor-security-check
Pre-release security audit for ANY project — AI-built or hand-written, web or mobile. Scans the codebase for the full range of real-world risks that get apps breached: leaked API & AI-provider keys, exposed configs/secrets, broken auth & access control (IDOR), injection (SQL/XSS/command), SSRF, open databases & cloud…
lictor-rotate
Walks the user through rotating a leaked API key — step by step, provider-specific. Knows the exact URL to visit, the exact button to click, and how to verify the rotation worked. Supports Stripe, OpenAI, Anthropic, Google Cloud / AI Studio, GitHub, AWS, Slack, Supabase, Firebase, Postmark, and generic OAuth providers.