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 screen-recordinggit 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/screen-recording)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/screen-recording"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/screen-recording/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/screen-recording"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/screen-recording.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00012 | $0.00680 |
| Opus 5 | $0.00006 | $0.00340 |
| Sonnet 5 | $0.00002 | $0.00136 |
| Haiku 4.5 | $0.00001 | $0.00068 |
Grade A, and why
screen-recording 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 8d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capture screen recordings as video files attached to the conversation.
Activation
The user asks to start, stop, pause, resume, or restart a screen recording. Routing does not depend on matching phrases: see Routing below.
Routing
Recording is managed through dedicated HTTP endpoints (/v1/recordings/*) rather than text-based intent detection. Two routing mechanisms exist:
1. commandIntent (structured command) - highest priority
The macOS client can send structured intents with domain: 'screen_recording' and action: 'start' | 'stop' | 'restart' | 'pause' | 'resume'. These bypass text parsing entirely. The assistant checks for commandIntent before any text analysis.
2. HTTP endpoints
Clients call the recording HTTP endpoints directly:
POST /v1/recordings/start- start a screen recordingPOST /v1/recordings/stop- stop the active recordingPOST /v1/recordings/pause- pause the active recordingPOST /v1/recordings/resume- resume a paused recordingGET /v1/recordings/status- get current recording statusPOST /v1/recordings/status- recording lifecycle callback from the client
3. Normal processing
If no recording intent is detected, the message flows to the classifier and computer-use session as usual.
Behavior Rules
- Do not invoke computer use for recording-only requests. The assistant handles these directly.
- One recording at a time. If a recording is already active, starting another returns an "already recording" message.
- Conversation-linked. Each recording is linked to the conversation that started it for attachment purposes. However, since only one recording can be active at a time, stop commands from any conversation will stop the active recording regardless of which conversation started it.
- Permission required. Screen recording requires macOS Screen Recording permission. If denied, the user sees actionable guidance to enable it in System Settings.
- Mixed-intent prompts (recording + other task) are NOT intercepted by the standalone route - the recording action is deferred and executed alongside the task.
- Restart always reopens the source picker and requires source reselection.
- Restart cancel (user closes the source picker) leaves state idle - no false "recording started" message.
- Pause/resume toggle the recording without stopping it. The HUD shows paused state.
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.
- 8d ago Changed · -35 lines 528c1dee3dc9
- 9d ago First seen · 96 lines · 12 tokens per session scan A 68dea5641872
screen-recording is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,234 stars, last pushed today), licensed MIT. It adds 12 tokens to every session and 680 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 2026-09-03.
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.