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 mailgun-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/mailgun-setup)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/mailgun-setup"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/mailgun-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/mailgun-setup"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/mailgun-setup.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 Data Exfiltration · line 51 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 101 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 132 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 151 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 54 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 152 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 | $0.00024 | $0.01572 |
| Opus 5 | $0.00012 | $0.00786 |
| Sonnet 5 | $0.00005 | $0.00314 |
| Haiku 4.5 | $0.00002 | $0.00157 |
Grade C, and why
mailgun-setup scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
Run the store script to securely collect the API key: Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Note:** Mailgun uses HTTP Basic Auth with username `api` and the API key as the password. The credential proxy cannot construct Basic Auth headers automatically. Instead, use `curl -u "api:$KEY"` in bash commands — ret How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Send emails through the user's own Mailgun account. The user provides their Mailgun API key and domain, and you send via their infrastructure.
Setup
Step 0: Check Existing Configuration
Before starting, check whether Mailgun is already configured:
bun skills/mailgun-setup/scripts/check-config.ts
The script outputs JSON: { "configured": boolean, "hasApiKey": boolean, "hasWebhookKey": boolean, "details": string }.
- If
configuredistrue— Mailgun is already set up. Offer to verify the connection or reconfigure. - If
configuredisfalse— continue to Step 1.
Step 1: Store the API Key
Run the store script to securely collect the API key:
bun skills/mailgun-setup/scripts/store-api-key.ts
The script opens a secure credential prompt, stores the key, and exits. If it exits 0, the key is stored. Exit code 130 means the user cancelled the prompt — nothing was stored; that's a valid choice, not an error, so ask whether they'd like to try again rather than treating it as a failure. Any other non-zero exit is a real failure. Never ask for the key in chat.
Note: Mailgun uses HTTP Basic Auth with username api and the API key as the password. The credential proxy cannot construct Basic Auth headers automatically. Instead, use curl -u "api:$KEY" in bash commands — retrieve the key from the vault at runtime. See the sending examples below.
Step 2: Detect the Domain
After storing the API key, automatically detect the user's domain — don't ask them for it. Retrieve the API key from the vault and call the Mailgun Domains API:
curl -s --user "api:$MAILGUN_API_KEY" \
https://api.mailgun.net/v4/domains?state=active
The response contains an items array of domain objects with name and state fields. Pick the first domain with "state": "active". If no active domains are found, try the EU endpoint (https://api.eu.mailgun.net/v4/domains?state=active). If still none, tell the user they need to verify a domain in their Mailgun dashboard first.
What ships with it
4 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.
- 7d ago First seen · 163 lines · 24 tokens per session scan C 043d6fc064d4
mailgun-setup is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,225 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 1,572 once invoked, about $0.0001 per session on Opus 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
web-deserialization
Insecure deserialization to RCE for web apps. Use when the app deserializes attacker-controlled data - cookies/tokens/hidden fields/params that are serialized blobs, VIEWSTATE, Java/PHP/.NET/Python/Node apps. Triggers - base64 starting rO0AB or hex AC ED 00 05 (Java), PHP serialize O-prefix, VIEWSTATE, python pickle…
ms365-connect
Connect to Microsoft 365 (OneDrive, Outlook mail, Calendar, Teams) via Microsoft Graph using the open-source python-o365 (O365) library. Use when the user wants to list/download OneDrive files, read or send Outlook email, list calendar events, or post a message to a Teams channel from a Sutando workflow.
calling-llms
Use when sending chat completions through liter-llm and routing to a specific provider via the provider/model prefix. Covers the chat call shape, provider routing, modelhint, message roles, and error categories.
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.
streaming-responses
Use when streaming tokens incrementally from an LLM via liter-llm over SSE or async iterators. Covers chatstream, delta handling, and null-content chunks.
api-design
REST API contract designer and reviewer. ALWAYS use when designing new endpoints, reviewing existing API contracts, planning API versioning, or standardizing error models. Covers resource modeling (URL/naming), HTTP method semantics, status code selection, error model consistency, pagination/filtering/sorting…