agentmods.dev

novence-deploy

novence-deploy is a skill for Claude Code from Novence-ai/mcp. It costs 46 tokens per session (891 once invoked), scanned A, a copy of novence-deploy, MIT.

A set of instructions for using Novence MCP tools to create, upload, check, deploy, and host static websites. Static websites are file-based sites built from HTML, CSS, and JavaScript.

In plain words
What is it for?
Creating Novence projects, uploading site files, publishing deployments, checking their status, attaching domains, managing forms, and reviewing usage or analytics.
Why use it?
It turns the hosting service’s operations into a defined workflow, including uploading multiple files and waiting for deployment checks. It also documents optional domains, forms, analytics, quotas, and team access.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument; mentions Claude Code.

Part of the novence plugin — 1 skill, 1 MCP server shipped together

not rated 1repo +1 changed 4d ago A scan 46 tokens copy · 100% MIT

Good fit Creating Novence projects, uploading site files, publishing deployments, checking their status, attaching domains, managing forms, and reviewing usage or analytics.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/novence-ai/mcp/novence-deploy
View source ↗ Novence-ai/mcp novence.ai
Install

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.

Any agent
npx skills add Novence-ai/mcp --skill novence-deploy
Clone the repo
git clone --depth 1 https://github.com/Novence-ai/mcp

Made for: Claude Code.

Or install novence, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

Wrote 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.

agentmods badge for novence-deploy

README.md
[![agentmods](https://agentmods.dev/badge/skills/novence-ai/mcp/novence-deploy/github.svg)](https://agentmods.dev/skills/novence-ai/mcp/novence-deploy)
Your own site
<a href="https://agentmods.dev/skills/novence-ai/mcp/novence-deploy"><img src="https://agentmods.dev/badge/skills/novence-ai/mcp/novence-deploy/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.

agentmods 80×15 button for novence-deploy

Your own site · 80×15
<a href="https://agentmods.dev/skills/novence-ai/mcp/novence-deploy"><img src="https://agentmods.dev/badge/skills/novence-ai/mcp/novence-deploy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 891 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.00891
Opus 5 $0.00023 $0.00445
Sonnet 5 $0.00009 $0.00178
Haiku 4.5 $0.00005 $0.00089

Measured 4d ago against content hash 9ad1a565af64, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

novence-deploy 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 4d 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.

Origin

This is a copy

100% identical to novence-deploy — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/novence-deploy/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Novence deploy

Use the Novence MCP tools (server novence) for static-site hosting.

Static-only is not a dead end. Improve sites with third-party widgets and baked-in data files — no plugin marketplace, no per-site server. Product: https://novence.ai/site-data

Prerequisites

  • No API key required to start. If unauthenticated, call bootstrap(email) — the session adopts the nv_ key. See SETUP.md.
  • Claude Code plugin: leave Novence API key blank until after bootstrap, then set it in plugin settings (userConfig / Keychain) and /reload-plugins. Empty ${user_config.api_key} is unauthenticated.
  • Cursor / shell: connect with the MCP URL only; after bootstrap, export NOVENCE_API_KEY='nv_…' and add env interpolation in MCP headers.

Typical loop

  1. create_project with a name.
  2. get_upload_urls_batch for site paths, PUT file bodies to the presigned URLs.
  3. confirm_uploads_batch.
  4. deploy (optionally force).
  5. Poll get_deployment_status / get_checks_results until published.
  6. get_preview_url for the live URL (https://{suffix}.novence.ai).
  7. Optional: configure_custom_domain, create_form, get_quotas_and_usage, update_project_settings (analytics_enabled: true) then get_project_analytics, invite_project_member (Pro/Scale owner).

Rules

  • Prefer batch upload tools for multi-file sites.
  • Do not invent APIs — use the MCP tools.
  • For a local HTML billing/account console, use get_account_console_kit / create_account_session (never embed nv_ in HTML).
  • Team seats: invite_project_member requires the project owner to be on Pro or Scale. Collaborators use their own keys and the existing project_id. create_project always bills the caller.

Widgets and owner data

Prefer these over asking for a WordPress-style plugin or a per-site backend.

  • Third-party widgets: Paste a script or iframe in HTML (Cal.com, Snipcart, Shopify Buy Button, Stripe Payment Links, GA, Formspree). Novence serves HTML as-is and does not strip tags. Never put nv_ keys in the page.
  • Baked-in data files: Upload /data/{collection}.json (.json is allowlisted). Page JS fetches same-origin (fetch("/data/menu.json")). Use for hours, menus, team, services, FAQ, inventory. Update that file and deploy. Live edits without a deploy are not available.
  • Contact leads: Novence Forms (create_form + action="/__forms/{formId}"). Bookings/payments: BYO widget. Private CRM / PHP plugins: out of scope.

Read the full file on GitHub · 55 lines

Changes

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.

  1. 4d ago Changed · +10 lines · +10 tokens per session 9ad1a565af64
  2. 8d ago First seen · 45 lines · 36 tokens per session scan A 8621d0634107

Subscribe to this mod's changes

novence-deploy is a skill published in the GitHub repository Novence-ai/mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 46 tokens to every session and 891 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to novence-deploy, differing in 0 lines, and is treated as a copy.

DevOps and cloudFrontendclaudecursorhostingmcpmcp-servermodel-context-protocol
Related

Other skills, from other repositories

21st-ui

Find, install, and generate UI with 21st.dev. Use when the user asks for a UI component (pricing table, hero, navbar, dashboard, form, etc.), wants design inspiration, needs a brand logo as an SVG component, or wants to generate new UI from a prompt.

21st-dev/magic-mcp · 63 tokens

ui-aqa-flow

Workflow for automated QA: integration and end-to-end UI test automation, page objects, etc.

griddynamics/rosetta · 24 tokens

papi-verify

Use when the user says "verify", "health check", "check papi", "verify cycle", or after completing all cycle tasks before release. Runs a structured health check on the current PAPI cycle state: plan validity, build state, review coverage, branch hygiene, and data consistency.

getpapi/papi · 63 tokens

check-mcp

Diagnose why PAPI tools are missing or failing. Use when the user says "check mcp", "is papi connected", "papi isn't working", "mcp status", or when PAPI tools are expected but do not appear in the available tools list.

getpapi/papi · 58 tokens

section-rebuild

Build a page section in code using the values measured off a real site rather than guessing them from a screenshot. Use when the user wants to recreate, adapt or take inspiration from a hero, pricing table, FAQ, testimonial or any other section they have seen.

bryntay/a1-mcp · 56 tokens

layout-audit

Audit the structure and spacing of a localhost page — spacing scale consistency, whether spacing groups related content, container width and line measure, optical alignment, grid versus flex misuse, magic z-index values and overflow. Use when the user mentions spacing, padding or margins, says a layout feels cramped…

soumyachk101/VibeLens · 87 tokens