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-link-walletgit 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-link-wallet)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/stripe-link-wallet"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/stripe-link-wallet/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-link-wallet"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/stripe-link-wallet.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 Prompt Injection · line 298 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 | $0.00052 | $0.05047 |
| Opus 5 | $0.00026 | $0.02524 |
| Sonnet 5 | $0.00010 | $0.01009 |
| Haiku 4.5 | $0.00005 | $0.00505 |
Grade A, and why
stripe-link-wallet 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 today.
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 — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stripe Link Wallet
Spend on the user's behalf using the Stripe Link CLI. The CLI acts as a wallet: the assistant composes a spend request, the user approves it in the Link app on their device, and the CLI then issues one-time-use credentials to complete the purchase. Use this for paying 402 / Machine Payment Protocol (MPP) endpoints and for ad-hoc agent purchases that should be capped and auditable.
When the user has connected Stripe Link to the assistant, the CLI reaches Link through the assistant's own OAuth connection: it is pointed at a local passthrough proxy and never holds a Link credential, so no device login is needed. The CLI's own device login remains as a fallback.
Required tools
bashfor alllink-cliinvocations. Usehost_bashonly if a specific flow genuinely requires host-level access (e.g. reading a local file the user has on their machine).
Hard constraints
- Always pass
--request-approvalonspend-request create. The Link app approval is the consent surface — it is non-negotiable. No spending happens without it. - Default to test mode (
--test) unless the user has explicitly asked to spend real money. When unsure, ask in chat before dropping--test. - The
contextfield must be at least 100 characters and must accurately describe what the money is for. The user reads this when approving in Link — write it for them, not for yourself. - Always use
--format jsonon every command. The default interactive Ink output is for humans, not agents. Onauth loginit is worse than noise: without--format jsonthe command enters the interactive Ink UI and blocks until someone approves in the Link app, which nobody can do because the URL never reaches the user. Exception:demoandonboardrequire a TTY and have no JSON mode. - Amount is in cents. $10.00 =
--amount 1000. Maximum is 50,000 cents ($500). - Never log or repeat raw card credentials (PAN, CVC) in the conversation. Always use
--output-filewhen retrieving card credentials, and delete that file once the checkout is done. - Never print the proxy grant. Only
evalthe--exportoutput ofassistant oauth proxy-url; do not run it without--export, do notechoorenvtheLINK_*orVELLUM_OAUTH_PROXY_*variables, and do not write them to a file.
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.
- today Changed · +14 lines 00bc884c9954
- 2d ago Changed · +50 lines 30f92a80316f
- 3d ago Changed · +4 lines · -81 tokens per session 255276e317c3
- 7d ago Changed · +25 lines fe368c73a1f1
- 9d ago First seen · 291 lines · 133 tokens per session scan A 3a71230b6e95
stripe-link-wallet is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,234 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 5,047 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 2026-09-03.
Other skills, from other repositories
subscription-scanner
Scans Gmail for active paid subscriptions and tracks them over time. Surfaces additions / cancellations between scans.
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…
stock-business-review
Review a US-listed company's business model and revenue structure for an equity-research workup. Covers product/service mix, customer concentration, geographic exposure, industry position, revenue-growth decomposition (organic vs acquired vs price vs volume), and information-tier discipline (which numbers are facts vs…
stock-earnings-quality-review
Review a US-listed company's earnings quality, cash-flow integrity, and operating leverage for an equity-research workup. Covers operating cash flow vs net income drift, free cash flow trajectory, capex character (maintenance vs expansion), equity issuance / shareholder-return yield, revenue-quality signals…
stock-balance-sheet-review
Review a US-listed company's balance sheet health for an equity-research workup. Covers net-debt/EBITDA leverage, current ratio, cash runway, goodwill concentration and impairment history, DSO trend, inventory days, off-balance-sheet items (operating leases, contingent liabilities), and pension underfunding. Trigger…
stock-industry-review
Review a US-listed company's industry position and competitive moat for an equity-research workup. Covers Porter Five Forces scan, market-share trend (absolute and relative to industry growth), TAM size and trajectory, unit economics where disclosed (LTV/CAC, unit gross margin), moat classification (network / brand /…