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 saski/arnesto --skill deploy-with-vercelgit clone --depth 1 https://github.com/saski/arnestoWrote 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/saski/arnesto/deploy-with-vercel)<a href="https://agentmods.dev/skills/saski/arnesto/deploy-with-vercel"><img src="https://agentmods.dev/badge/skills/saski/arnesto/deploy-with-vercel/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/saski/arnesto/deploy-with-vercel"><img src="https://agentmods.dev/badge/skills/saski/arnesto/deploy-with-vercel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00025 | $0.01828 |
| Opus 5.5 | $0.00010 | $0.00731 |
| Sonnet 5.5 | $0.00005 | $0.00366 |
| Haiku 4.5 | $0.00003 | $0.00183 |
Grade A, and why
deploy-with-vercel 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 today.
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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploy with Vercel
Link the current repository to a Vercel project and deploy it, using the Vercel MCP tools.
- Confirm the Vercel MCP connection first. If the Vercel MCP is not connected or needs authentication, surface the sign-in so the user can authenticate, and continue once connected. If the user signed in but did not grant enough Vercel permissions to see the right team(s) — for example
get_git_deployment_contextor the project-listing tools omit a team you need, or Vercel returns a permissions/forbidden error for that team — and thecursor-cloud-set-publish-button-visibilitytool is available, call it withvisible: trueandreconnect: trueso Cursor shows "Reconnect to Vercel" instead of Publish. Clicking that pill starts the same Vercel MCP reauth flow as Publish's MCP auth, so the user can grant the missing team access. Once they have reconnected (or you can see the right team(s)), call the tool again withvisible: trueand omitreconnect(or passreconnect: false) to restore the Publish label. - Call the Vercel MCP's
get_git_deployment_contexttool (fall back to the project-listing tools if it is unavailable). It reports, per Vercel team: the plan, the projects with their git links, and the Origin namespaces the team is connected to (originConnections). If the user named a team, look for an existing project linked to this repository only within that team. Otherwise, reuse an existing linked project when exactly one team has a matchingcursor-originlink; ask the user to choose when several teams do. If several projects match within the selected team, ask which project to use. Skip to deployment only on an unambiguously selected matching project; if that team has no matching project, continue to step 3. - Otherwise create or link the Vercel project for this repository with the Vercel MCP's
create_git_projecttool: setprovidertocursor-origin; default the project name to the repo name. Use the team explicitly named by the user. When the user has not named a team, prefer a team whoseoriginConnectionsinclude this repository's Origin namespace, then prefer the best plan (enterprise over pro over hobby). If several teams remain equally plausible, ask the user rather than guessing. - Trigger a deployment of the repository's default branch to the linked project.
create_git_projectalready does this when it creates the project. Subsequent deploys are triggered by commits to the default branch. Calling the tool again will not trigger a new deploy. - Report back the project name and scope, the deployment URL, and its status. If
create_git_project(or another required Vercel tool) is not available on the connected Vercel MCP, say exactly which capability is missing and stop — never fake a deployment or invent a URL.
Never print tokens or secrets. If there's uncommitted work that would affect the deploy, ask before deploying.
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.
- today Changed 2c2321dcb890
- 21d ago First seen · 45 lines · 25 tokens per session scan A 30cb8ca5b3f6
deploy-with-vercel is a skill published in the GitHub repository saski/arnesto (5 stars, last pushed yesterday), licensed Unlicense. It adds 25 tokens to every session and 1,828 once invoked, about $0.0001 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 2026-09-26.
Other skills, from other repositories
eng-runbook
A one-page engineering runbook: a practical guide for operating a software service. It includes alerts, dashboards, procedures, on-call information, and an incident checklist.
terraform-skill
Use when working with Terraform or OpenTofu - creating modules, writing tests (native test framework, Terratest), setting up CI/CD pipelines, reviewing configurations, choosing between testing approaches, debugging state issues, implementing security scanning (trivy, checkov), or making infrastructure-as-code…
terraform-cli-setup
A setup guide for installing and initializing Terraform, a tool for managing infrastructure from configuration files. It also covers basic provider downloads and mirror settings, but not cloud-provider credentials.
alicloud_cli
A Chinese-language reference for the Alibaba Cloud command-line tool, which lets developers manage Alibaba Cloud services from a terminal. It uses an offline copy of the documentation as its main source.
aiq-deploy
Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure.
dynamo-recipe-runner
Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. Use for model/backend/GPU/deployment-mode recipe bring-up; use router-starter for router-only mode work and troubleshoot for broken deployments.