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 meme-generatorgit 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/meme-generator)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/meme-generator"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/meme-generator/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/meme-generator"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/meme-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 14 findings, up to high
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 →
- high Supply Chain · line 4 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- medium Data Exfiltration · line 33 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 47 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 92 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 117 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 121 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 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 153 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 160 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 167 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 176 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 185 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 Rogue Agent · line 202 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00039 | $0.02612 |
| Opus 5 | $0.00019 | $0.01306 |
| Sonnet 5 | $0.00008 | $0.00522 |
| Haiku 4.5 | $0.00004 | $0.00261 |
Grade C, and why
meme-generator 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 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s "https://api.memegen.link/templates" | python3 - "SEARCH_TERM" <<'PYEOF' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
compatibility: "Requires curl and python3. Works on macOS and Linux." How it starts
The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Generate classic memes using the Memegen.link API — a free, open-source, stateless meme generator. No API key, no auth, no rate limits. Just URLs.
The API has 170+ templates covering all the classics: Drake, Distracted Boyfriend, This is Fine, Change My Mind, Always Has Been, etc.
How It Works
The API is entirely URL-based. Every meme is a deterministic URL:
https://api.memegen.link/images/{template_id}/{top_text}/{bottom_text}.{format}
No POST requests needed for basic generation — just construct the URL and fetch it.
Tools
All operations use bash with curl and python3.
Search Templates
Find a template by keyword:
curl -s "https://api.memegen.link/templates" | python3 - "SEARCH_TERM" <<'PYEOF'
import json, sys
templates = json.load(sys.stdin)
query = sys.argv[1].lower()
matches = [t for t in templates if query in t['name'].lower() or query in t['id'].lower() or any(query in k.lower() for k in t.get('keywords', []))]
for t in matches[:15]:
print(f"{t['id']:25s} | {t['name']:45s} | {t['lines']} lines | Keywords: {', '.join(t.get('keywords', []))}")
print(f'\n{len(matches)} matches')
PYEOF
Browse Popular Templates
Quick reference for the most Twitter-worthy templates:
| ID | Name | Lines | Best For |
|---|---|---|---|
drake |
Drakeposting | 2 | "This not that" comparisons |
db |
Distracted Boyfriend | 3 | Three-way tension (boyfriend, girlfriend, other) |
fine |
This is Fine | 2 | Denial of obvious problems |
cmm |
Change My Mind | 1 | Hot takes, controversial opinions |
astronaut |
Always Has Been | 4 | "Wait it was X?" / "Always has been" |
pigeon |
Is This a Pigeon? | 2 | Misidentifying something obvious |
exit |
Left Exit 12 Off Ramp | 3 | Choosing the wrong/chaotic option |
gru |
Gru's Plan | 4 | Plan that backfires in step 3-4 |
pooh |
Tuxedo Winnie the Pooh | 2 | Basic vs. sophisticated version |
rollsafe |
Roll Safe | 2 | Galaxy-brain "logic" |
chair |
American Chopper Argument | 6 | Multi-panel heated debate |
ds |
Daily Struggle | 3 | Two-button dilemma |
same |
They're The Same Picture | 3 | Two things that are identical |
midwit |
Midwit | 3 | Beginner and expert agree, midwit overthinks |
gb |
Galaxy Brain | 4 | Escalating "big brain" ideas |
right |
Anakin and Padme | 3 | "Right...?" meme — dawning realization |
harold |
Hide the Pain Harold | 2 | Suffering in silence |
vince |
Vince McMahon Reaction | 4 | Escalating excitement |
home |
We Have Food at Home | 2 | Wanting X, getting budget X |
panik-kalm-panik |
Panik Kalm Panik | 3 | Emotional rollercoaster |
woman-cat |
Woman Yelling at a Cat | 2 | Accusation vs. unbothered response |
spiderman |
Spider-Man Pointing | 2 | Two identical things |
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.
- 9d ago First seen · 238 lines · 39 tokens per session scan C 912708f071d5
meme-generator is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,234 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 2,612 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, 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
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.
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 …
continual-learning
Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…
ha-logs
A read-only troubleshooting skill for querying Hope Agent’s local SQLite databases, which store logs, conversations, and background-job status.