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 computer-usegit 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/computer-use)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/computer-use"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/computer-use/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/computer-use"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/computer-use.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 | $0.00007 | $0.01316 |
| Opus 5.5 | $0.00003 | $0.00526 |
| Sonnet 5.5 | $0.00001 | $0.00263 |
| Haiku 4.5 | $0.00001 | $0.00132 |
Grade A, and why
computer-use 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 28d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill provides the computer_use_* action tools for controlling a connected desktop. CU tools run through the main agent loop via HostCuProxy.
The skill is internally preactivated for conversations with a connected desktop client.
Tools in this skill are proxy tools. Execution is forwarded to a connected desktop client or handled by the assistant's virtual desktop.
Observations
Every computer-use step returns the accessibility tree. Every action also
returns a screenshot taken after it ran (one at the end of a
computer_use_sequence), so check it to see what your action did. An
observation comes with a screenshot on a desktop's first look, when it is
window-scoped, or when you pass include_screenshot: true. Ask for one whenever
the tree is not enough to act on: a canvas, a game, a custom-drawn view, few or
unlabeled controls, or a layout question.
The tree is walked to a limited depth to keep steps fast, and says when it was
cut off. If the element you need is not in it, call computer_use_observe with
full_tree: true.
Coordinates and live editing
Prefer element IDs from the latest observation. Click, scroll and drag coordinates are screen points, not screenshot pixels. For a desktop screenshot, use the per-axis conversion in its observation metadata. If you crop or resize the image, map back to the original screenshot first. Observe again after the layout changes; an older image is not a current target.
During live editing, use the app's zoom and track-height controls, then inspect the fresh screenshot. Avoid installing image libraries or repeatedly cropping and measuring screenshot pixels just to locate a UI control or waveform. Reserve scripted image or media analysis for tasks that actually require it. If an action does not produce the expected visible result, check focus and the coordinate mapping before repeating it.
Waveform pixels do not reveal spoken words. If an edit depends on audio you cannot hear or a boundary you cannot see, ask for a timestamp, a user-positioned playhead, or the source media. Do not guess the cut point or claim an edit succeeded without observing its result.
What ships with it
13 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.
- TOOLS.json 27 KB
- tools/computer-use-click.ts 714 B runs code
- tools/computer-use-done.ts 386 B runs code
- tools/computer-use-drag.ts 386 B runs code
- tools/computer-use-key.ts 385 B runs code
- tools/computer-use-observe.ts 389 B runs code
- tools/computer-use-open-app.ts 390 B runs code
- tools/computer-use-respond.ts 389 B runs code
- tools/computer-use-run-applescript.ts 414 B runs code
- tools/computer-use-scroll.ts 388 B runs code
- tools/computer-use-sequence.ts 390 B runs code
- tools/computer-use-type-text.ts 391 B runs code
- tools/computer-use-wait.ts 386 B runs code
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.
- 28d ago Changed · +20 lines ab840ea49879
- 1mo ago Changed 4d24c3f821ec
- 1mo ago Changed · +19 lines 7f19d29f8244
- 1mo ago Changed · +20 lines ad8179cdb78b
- 1mo ago Changed · +18 lines ca594975800b
- 1mo ago Changed · +21 lines b2dc092dca6f
- 1mo ago First seen · 25 lines · 7 tokens per session scan A 0389441d5383
computer-use is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,448 stars, last pushed 2d ago), licensed MIT. It adds 7 tokens to every session and 1,316 once invoked, about $0.0000 per session on Opus 5.5. 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
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 …
ha-logs
A read-only troubleshooting skill for querying Hope Agent’s local SQLite databases, which store logs, conversations, and background-job status.
getting-started
Interactive post-onboarding tour that adapts to whatever data exists (calendar, Granola, or none). Use right after onboarding, or when the user says 'show me around', 'how do I start'. Also use proactively when the vault is < 7 days old. Not for the initial setup itself; use setup.