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 oura-setupgit 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/oura-setup)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/oura-setup"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/oura-setup/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/oura-setup"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/oura-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 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 Data Exfiltration · line 74 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 115 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 120 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 139 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 139 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00022 | $0.01607 |
| Opus 5 | $0.00011 | $0.00804 |
| Sonnet 5 | $0.00004 | $0.00321 |
| Haiku 4.5 | $0.00002 | $0.00161 |
Grade A, and why
oura-setup 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 7d 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.
from urllib.parse import urlparse, parse_qs, urlencode How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Oura Ring Integration
Connect the user's Oura Ring to pull sleep, heart rate, readiness, activity, and other health data via the Oura Cloud API V2.
Prerequisites
- An Oura Ring (Gen 3 or Ring 4) with an active Oura Membership ($6/mo required for API access)
- The Oura app installed and paired with the ring
- An Oura Cloud account at https://cloud.ouraring.com
Setup
1. Register a Developer Application
Have the user go to https://developer.ouraring.com/applications and create a new application:
- Display Name: The user's preferred name for the integration
- Description: Brief description of the integration
- Contact Email: User's email
- Website: Any valid URL (e.g. a personal website)
- Privacy Policy / Terms of Service: Any valid URLs (required fields, not enforced for personal apps)
- Redirect URIs:
http://localhost:3000/callback - Scopes: Enable all scopes needed. Recommended:
personal,daily,heartrate,sleep,workout,spo2,stress,heart_health,session,ring_configuration
Save the Client ID and Client Secret.
2. Run the OAuth Flow
Store the client secret securely using assistant credentials prompt, then write and run the OAuth helper script on the user's machine:
#!/usr/bin/env python3
"""Oura Ring OAuth2 helper — catches auth code and exchanges for tokens instantly."""
from http.server import HTTPServer, BaseHTTPRequestHandler
from urllib.parse import urlparse, parse_qs, urlencode
import urllib.request, json, webbrowser, ssl
CLIENT_ID = 'YOUR_CLIENT_ID'
CLIENT_SECRET = 'YOUR_CLIENT_SECRET'
REDIRECT_URI = 'http://localhost:3000/callback'
SCOPES = 'email personal daily heartrate workout tag session spo2 ring_configuration stress heart_health'
class Handler(BaseHTTPRequestHandler):
def do_GET(self):
parsed = urlparse(self.path)
if parsed.path == '/':
params = urlencode({
'response_type': 'code', 'client_id': CLIENT_ID,
'redirect_uri': REDIRECT_URI, 'scope': SCOPES, 'state': 'assistant'
})
self.send_response(302)
self.send_header('Location', f'https://cloud.ouraring.com/oauth/authorize?{params}')
self.end_headers()
elif parsed.path == '/callback':
code = parse_qs(parsed.query).get('code', [''])[0]
if code:
token_data = urlencode({
'grant_type': 'authorization_code', 'code': code,
'redirect_uri': REDIRECT_URI, 'client_id': CLIENT_ID,
'client_secret': CLIENT_SECRET,
}).encode()
try:
req = urllib.request.Request('https://api.ouraring.com/oauth/token',
data=token_data,
headers={'Content-Type': 'application/x-www-form-urlencoded'},
method='POST')
resp = urllib.request.urlopen(req, context=ssl.create_default_context())
result = json.loads(resp.read())
with open('/tmp/oura_tokens.json', 'w') as f:
json.dump(result, f, indent=2)
self.send_response(200)
self.send_header('Content-Type', 'text/html')
self.end_headers()
self.wfile.write(b'<html><body><h1>Connected! You can close this tab.</h1></body></html>')
print(f'\nTokens saved to /tmp/oura_tokens.json')
except Exception as e:
self.send_response(500)
self.end_headers()
self.wfile.write(f'Token exchange failed: {e}'.encode())
def log_message(self, *a): pass
print('Opening browser for Oura authorization...')
webbrowser.open('http://localhost:3000')
HTTPServer(('localhost', 3000), Handler).serve_forever()
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.
- 7d ago First seen · 152 lines · 22 tokens per session scan A 8f2f0c0b70a8
oura-setup is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,225 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 1,607 once invoked, about $0.0001 per session on Opus 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 2026-09-03.
Other skills, from other repositories
bee-actions
Act back on the owner's Bee wearable — the TOOL half of the Bee integration (channels-vs-tools split). The Bee CHANNEL (ag2-sparrow's sources/bee.py watcher) pushes captured events AT the agent as ambient tasks; this skill is what the agent CALLS to read Bee's data surfaces and mutate them.
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.
c-bluetooth
Manage Bluetooth devices on macOS using the blucli (blu) CLI. List paired and available devices, connect to headphones/speakers/keyboards, and disconnect devices by name or MAC address.
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 …