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 silvioventre/lovable-skills --skill deploy-externalgit clone --depth 1 https://github.com/silvioventre/lovable-skillsWrote 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/silvioventre/lovable-skills/deploy-external)<a href="https://agentmods.dev/skills/silvioventre/lovable-skills/deploy-external"><img src="https://agentmods.dev/badge/skills/silvioventre/lovable-skills/deploy-external/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/silvioventre/lovable-skills/deploy-external"><img src="https://agentmods.dev/badge/skills/silvioventre/lovable-skills/deploy-external.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 | $0.00155 | $0.01041 |
| Opus 5 | $0.00077 | $0.00521 |
| Sonnet 5 | $0.00031 | $0.00208 |
| Haiku 4.5 | $0.00015 | $0.00104 |
Grade A, and why
deploy-external 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploy external
Running the app somewhere other than Lovable Cloud. The technical work is mostly routine; the decision and the transfer of responsibility are where this goes wrong.
First: is this the right move?
The default answer is no, and saying so is more useful than a migration plan the user did not need.
The apps are standard Vite + React projects on open technologies, synced to GitHub, with a PostgreSQL-based backend. Nothing is locked in, which means moving later costs the same as moving now — so there is no deadline forcing an early decision, and no reason to pay the operating cost before something requires it.
Move a component when a real constraint demands it:
- Compliance or data residency tied to specific infrastructure
- Networking the platform does not support, such as VPC peering or private endpoints
- Organisational policy requiring self-managed or audited hosting
Do not move for a hypothetical: "we might need to scale", "we want more control", "it feels safer to own it". Each of those trades a managed platform for an operational burden that has to be carried indefinitely.
If the user has not named a constraint, ask what is driving this before planning anything. The honest answer is frequently that nothing is, and the conversation ends there — which is the correct outcome, not a failure to help.
The three parts move independently
| Part | Default | Can move to |
|---|---|---|
| Code | Managed in Lovable, syncs to GitHub | Any Git workflow |
| Frontend | Lovable Cloud | Managed hosts, object storage plus CDN, containers, VMs |
| Backend and data | Lovable Cloud | Managed or self-hosted Supabase, or equivalent services |
You do not move all three at once, and most who move anything move only the frontend. Moving frontend hosting requires no architectural change and the backend can stay where it is.
Sync to GitHub first, regardless. It costs nothing, secures code ownership, and every external hosting path builds from the repository.
What ships with it
4 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 First seen · 64 lines · 155 tokens per session scan A 19c5c0e7f4e2
deploy-external is a skill published in the GitHub repository silvioventre/lovable-skills (2 stars, last pushed 15d ago), licensed MIT. It adds 155 tokens to every session and 1,041 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
vercel-deploy
Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.
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.
moai-platform-deployment
Deployment and hosting platform specialist covering Vercel, Railway, and Convex. Use when deploying applications, configuring edge functions, setting up continuous deployment, or managing serverless infrastructure.
multi-service-orchestration
PM2 process management, backend/frontend cascade execution, parallel worktree builds, and cross-service integration testing.
moai-platform-database-cloud
Cloud database platform specialist covering Neon (serverless PostgreSQL), Supabase (PostgreSQL 16 with real-time), and Firebase Firestore (NoSQL with offline sync). Use when choosing or setting up cloud databases.
agentsop-selfhost-decision
Project-kickoff rubric for the self-host vs managed-cloud decision — when is running your own inference engine / LLM platform worth the ops cost vs paying per-token for a managed API? Decide on two axes — VOLUME (a cost-crossover slider) and COMPLIANCE (a hard gate). Use at kickoff when choosing where to run…