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 discord-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/discord-app-setup)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/discord-app-setup"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/discord-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/discord-app-setup"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/discord-app-setup.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 216 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 | $0.00023 | $0.03735 |
| Opus 5 | $0.00012 | $0.01868 |
| Sonnet 5 | $0.00005 | $0.00747 |
| Haiku 4.5 | $0.00002 | $0.00374 |
Grade A, and why
discord-app-setup 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 9d 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are helping your user create a Discord application and connect a Discord bot to the assistant via the Discord Gateway. Walk through each step below.
CRITICAL: Follow these steps strictly in order. Do NOT combine steps, skip ahead, or ask for the bot token before the bot user has been configured. The token is shown only once after reset — collect it the moment the user generates it, never before.
Value Classification
| Value | Type | Secret? |
|---|---|---|
| Bot Token | Credential | Yes |
The Bot Token is the only value that needs to be persisted. Always collect it via the assistant's secure credential prompt — never accept it pasted in plaintext chat.
The Application ID and Public Key are derivable from the bot token at any time via Discord's API and do not need to be stored separately.
Setup Steps
Step 0: Check Existing Configuration
Before starting, run the check script:
bun skills/discord-app-setup/scripts/check-config.ts
The script outputs JSON: { "configured": boolean, "details": string, "error"?: string }.
- If
erroris present, stop. The check could not run, so the credential state is unknown, andconfigured: falsehere does not mean "not set up". Do not start the setup walkthrough. It will not fix this, and re-running setup on an app that already has a token forces a needless token reset that breaks any other deployment using it.cli_not_foundmeans theassistantcommand is missing from this environment's PATH. That is an installation problem. Report it as one, quotedetails, and stop.cli_failedorunparseable_outputmeans the CLI ran but did not answer usefully. Reportdetailsverbatim and stop.
- If
configuredistrue— Discord is already set up. Offer to verify the connection or reconfigure. - If
configuredisfalsewith noerror, the check ran and found no token. Continue to Step 0.5.
Step 0.5: Prefer the In-Product Wizard
If an interactive client is connected, call ui_show with surface_type: "channel_setup" and data: { channel: "discord" }. This opens the Discord setup wizard in the side panel: create the app, connect the token through a masked field, add the bot to a server, and finish with a hand-back to identity verification, all without the token entering chat. The wizard is non-blocking and auto-notifies you when it is closed.
What ships with it
7 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.
- 9d ago Changed · +2 lines 20b761723256
- 11d ago First seen · 229 lines · 23 tokens per session scan A 823338dc731b
discord-app-setup is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,225 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 3,735 once invoked, about $0.0001 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
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.
kafka-event-driven-design
Kafka event-driven architecture designer and reviewer, at the application/client layer. ALWAYS use when designing, reviewing, or troubleshooting how a service produces or consumes Kafka events — topic and partition-key design, producer and consumer client configuration, consumer group topology, event schema definition…