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 geo-auditgit 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/geo-audit)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/geo-audit"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/geo-audit/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/geo-audit"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/geo-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Excessive Agency · line 30 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 | $0.00068 | $0.01962 |
| Opus 5 | $0.00034 | $0.00981 |
| Sonnet 5 | $0.00014 | $0.00392 |
| Haiku 4.5 | $0.00007 | $0.00196 |
Grade A, and why
geo-audit 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEO Audit
A fast, real technical audit of how AI-ready a website is. Type a domain, get a streaming scorecard back in under 30 seconds, ending with the three things most worth fixing.
This is the operator-side companion to writing content. It tells you whether your site is even legible to AI agents before you spend a quarter producing for them.
RUNNING AN AUDIT
Extract the domain from the user's message and run the script without asking clarifying questions first. Stream the terminal output back as it happens. When the HTML report opens, mention that it just popped up in their browser and summarize the score in one sentence.
WHEN TO USE THIS SKILL
Use this when someone wants to:
- Quickly understand how AI-friendly a site is
- Diagnose why a site they've written for isn't getting picked up by ChatGPT, Perplexity, Gemini, or Claude
- Produce a demo-able audit on any domain on the fly
- Triage technical GEO issues before kicking off a content program
Do not use this skill for writing articles, comparison pages, or topical hubs. Route those to geo-article-writer.
USAGE
python3 {baseDir}/scripts/audit.py <domain>
Examples:
python3 {baseDir}/scripts/audit.py vellum.ai
python3 {baseDir}/scripts/audit.py https://stripe.com
python3 {baseDir}/scripts/audit.py example.com --json
The script accepts a bare domain (vellum.ai), a full URL (https://vellum.ai), or anything in between. It normalizes.
If the script runs cleanly → stream the output and summarize (default).
If the domain is unreachable / DNS fails / times out → report the specific failure plainly, suggest the user double-check the domain or bump --timeout, and do not invent a score.
If python3 is unavailable or blocked in this session → say so directly. Do not fabricate a scorecard or paraphrase what the audit "would" find — the numbers only exist if the script ran.
Flags:
--json— emit the report as JSON instead of streaming markdown (for piping into other tools)--no-color— strip ANSI color codes (for logs / CI)--no-html— skip the HTML report (default: writes one to a temp file and auto-opens it in your browser)--no-open— write the HTML report but don't auto-open it--timeout N— per-request timeout in seconds (default: 10)
What ships with it
1 file 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.
- 8d ago Changed · -7 lines b1345efa15b7
- 12d ago First seen · 190 lines · 68 tokens per session scan A eca678468774
geo-audit is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,234 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 1,962 once invoked, about $0.0003 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
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.
lictor-explain
Takes any security finding, error message, or jargon-heavy security advice and explains it in plain English. Use this when someone is confused by what /lictor-security-check found, or when they got a security warning from another tool and don't understand it.
lictor-fix-it
Applies the fixes recommended by /lictor-security-check, with the user's explicit permission for each change. Walks through findings one at a time, shows the proposed change, gets approval, applies, runs tests if available, and moves on. Some fixes (rotating leaked credentials) require the user to act outside Claude …
continual-learning
Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…
ha-logs
A read-only troubleshooting skill for querying Hope Agent’s local SQLite databases, which store logs, conversations, and background-job status.