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 stripe-app-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/stripe-app-setup)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/stripe-app-setup"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/stripe-app-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/stripe-app-setup"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/stripe-app-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 9 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 86 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 86 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 114 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 128 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 134 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 140 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 146 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 157 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 | $0.00029 | $0.01593 |
| Opus 5.5 | $0.00012 | $0.00637 |
| Sonnet 5.5 | $0.00006 | $0.00319 |
| Haiku 4.5 | $0.00003 | $0.00159 |
Grade C, and why
stripe-app-setup scanned grade C with 2 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 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
### Step 2: Collect the API Key Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s https://api.stripe.com/v1/balance How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Set up a Stripe restricted API key so the assistant can interact with a Stripe account — querying customers, managing subscriptions, processing refunds, reading invoices, and monitoring payments as a scoped entity.
Restricted API keys (RAKs) limit access to only the specific Stripe resources the assistant needs, reducing the blast radius if a key is ever compromised. RAKs are drop-in replacements for secret keys — they work identically with every Stripe API.
Total manual effort: ~2 interactions — create the restricted key in the Dashboard and hand it over via secure prompt.
Prerequisites
- User must have admin or developer access to the Stripe account
- User must be logged into the Stripe Dashboard in their browser
Setup Flow
Step 0: Check Existing Configuration
Before starting, check whether Stripe is already configured by running the check script:
bun skills/stripe-app-setup/scripts/check-config.ts
The script outputs JSON: { "configured": boolean, "details": string }.
- If
configuredistrue— Stripe is already set up. Offer to verify the connection or reconfigure. - If
configuredisfalse— continue to Step 1.
Step 1: Create the Restricted API Key
Direct the user to create a new restricted key:
Open https://dashboard.stripe.com/apikeys and click + Create restricted key.
When Stripe asks "How will you use this API key?", select Providing this key to another website and enter the assistant's name.
Guide them through the permissions. A good default for managing payments, customers, and subscriptions:
| Resource | Access Level |
|---|---|
| Customers | Read & Write |
| Charges | Read & Write |
| Invoices | Read & Write |
| Payment Intents | Read & Write |
| Subscriptions | Read & Write |
| Products | Read |
| Prices | Read |
| Balance | Read |
| Disputes | Read |
| Payouts | Read |
What ships with it
3 files 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.
- 1mo ago Changed · +2 lines 57eea1049cc6
- 1mo ago First seen · 192 lines · 29 tokens per session scan C ee2ecc19b014
stripe-app-setup is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,454 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 1,593 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 2 findings (harvests environment variables, 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
subscription-scanner
Scans Gmail for active paid subscriptions and tracks them over time. Surfaces additions / cancellations between scans.
liter-llm-running-the-proxy
Use when running the liter-llm api OpenAI-compatible gateway — virtual keys, per-key rate limits, budgets, cost tracking, and model routing. Covers the TOML config and the 22 REST endpoints.
board-prep
Use when preparing a finance draft for a board or leadership review from dated actuals, budgets, forecasts, cash data, and decision context. Not for detailed line-item variance analysis; use variance-analysis.
close-status
Use when reporting the evidence-backed status of a named month-end or quarter-end close, its blockers, counted completion, and dependency path. Not for explaining budget variances; use variance-analysis.
variance-analysis
Use when explaining a dated actual-versus-budget or actual-versus-forecast variance for a comparable finance period. Not for tracking close checklist completion; use close-status.
stock-analysis-lead
Orchestrate a US-stock investment analysis — classify sector archetype, fetch SEC filings, dispatch a tiered fan-out of six vertical equity-research agents (business model, earnings quality, balance sheet, management, industry, peer comparison) over a validated JSON findings contract, then synthesize a buy/hold/sell…