agentmods.dev

webflow-mcp:safe-publish

webflow-mcp:safe-publish is a skill for Claude Code from webflow/webflow-skills. It costs 43 tokens per session (3,974 once invoked), scanned A, original, MIT.

A controlled publishing workflow for Webflow, a service for building and hosting websites. It reviews the selected site, pages, and content before publishing changes and asks for confirmation before making them live.

In plain words
What is it for?
Use it to select a Webflow site, review changes, check pages and content collections, run pre-publish checks, and publish only after explicit confirmation.
Why use it?
It helps prevent accidental or unchecked website changes from being published.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the webflow-skills plugin — 32 skills shipped together

not rated 119 +2 4d ago A scan 43 tokens original MIT
View the source file webflow/webflow-skills
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.

agentmods
npx agentmods add skills/webflow/webflow-skills/safe-publish
Any agent
npx skills add webflow/webflow-skills --skill safe-publish
Clone the repo
git clone --depth 1 https://github.com/webflow/webflow-skills

Made for: Claude Code.

Or install webflow-skills, the plugin that ships this one along with the rest of its 32 skills.

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 webflow-mcp:safe-publish

README.md
[![agentmods](https://agentmods.dev/badge/skills/webflow/webflow-skills/safe-publish.svg)](https://agentmods.dev/skills/webflow/webflow-skills/safe-publish)
Your own site
<a href="https://agentmods.dev/skills/webflow/webflow-skills/safe-publish"><img src="https://agentmods.dev/badge/skills/webflow/webflow-skills/safe-publish.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,974 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 $0.00043 $0.03974
Opus 5 $0.00022 $0.01987
Sonnet 5 $0.00009 $0.00795
Haiku 4.5 $0.00004 $0.00397

Measured 6d ago against content hash 7194434e9f6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

webflow-mcp:safe-publish 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 6d 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.

plugins/webflow-skills/skills/safe-publish/SKILL.md · 534 lines

How it starts

The opening of the file, as written. The whole thing — 534 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Safe Publish

Publish a Webflow site with comprehensive preview, validation, and explicit confirmation workflow.

Important Note

ALWAYS use Webflow MCP tools for all operations:

  • Use Webflow MCP's data_sites_tool with action list_sites for listing available sites
  • Use Webflow MCP's data_sites_tool with action get_site for detailed site information
  • Use Webflow MCP's data_pages_tool with action list_pages for retrieving all pages
  • Use Webflow MCP's data_cms_tool with action get_collection_list for listing CMS collections
  • Use Webflow MCP's data_cms_tool with action list_collection_items for checking draft items
  • Use Webflow MCP's data_sites_tool with action publish_site for publishing the site
  • Use Webflow MCP's webflow_guide_tool to get best practices before starting
  • DO NOT use any other tools or methods for Webflow operations
  • All tool calls must include the required context parameter (15-25 words, third-person perspective)

Instructions

Phase 1: Site Selection & Status Check

  1. Get site: Identify the target site. If user does not provide site ID, ask for it.
  2. Fetch site details: Use Webflow MCP's data_sites_tool with action get_site to retrieve:
    • Last published date
    • Last updated date
    • Custom domains configured
    • Locale settings
  3. Check publish status: Determine if site has unpublished changes:
    • Compare lastUpdated vs lastPublished timestamps
    • If lastPublished is null, site has never been published
    • If lastUpdated > lastPublished, site has unpublished changes

Phase 2: Change Detection & Analysis

  1. List all pages: Use Webflow MCP's data_pages_tool with action list_pages
  2. Identify modified pages:
    • Compare each page's lastUpdated with site's lastPublished
    • Flag pages modified after last publish
    • Categorize by type (static, CMS template, archived, draft)
  3. List all collections: Use Webflow MCP's data_cms_tool with action get_collection_list
  4. Check for draft items:
    • For each collection, use Webflow MCP's data_cms_tool with action list_collection_items
    • Count items where isDraft: true
    • Count items modified since last publish
  5. Detect issues:
    • Draft items that won't be published unless explicitly included
    • Pages missing SEO metadata
    • Broken references (if detectable)

Read the full file on GitHub · 534 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. 6d ago First seen · 534 lines · 43 tokens per session scan A 7194434e9f6c

Subscribe to this mod's changes

webflow-mcp:safe-publish is a skill published in the GitHub repository webflow/webflow-skills (119 stars, last pushed 4d ago), licensed MIT. It adds 43 tokens to every session and 3,974 once invoked, about $0.0002 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 2026-08-30.

Frontendagentskills
Related

Other skills, from other repositories

web-design-engineer

Build or redesign polished browser-rendered visual artifacts with HTML/CSS/JavaScript/React: pages, dashboards, prototypes, slide decks, animations, UI mockups, and data visualizations. Use for visual front-end creation, design-system exploration, design critique, or explicit browser acceptance / QA of a web artifact.…

ConardLi/garden-skills · 96 tokens

beautiful-article

把用户提供的素材（网页 URL / PDF / DOCX / Markdown / 纯文本 / 截图 / 粘贴材料）编辑、设计成一篇美丽的、可离线打开和分享的单文件 HTML 网页文章。基于 reacticle 组件协议：不手写裸 HTML/CSS，而用语义组件 + 受主题约束的 Raw 自由层；按 source→规划→双确认→生成→终审→修复的小型 harness 流程推进，默认 100% 信息保留的长文。触发场景：把 URL/PDF/DOCX/文章做成网页文章 / 长文 / briefing / 解释文 / 视觉文章 / 教程 / 审阅复盘 / 方案分析，'render this as a beautiful web…

ConardLi/garden-skills · 226 tokens

gpt-image-2

面向 GPT Image 2 的图像生成 / 编辑技能。可在 3 种环境下使用：(A) Garden 本地模式，通过 OpenAI 兼容接口直接出图并落盘；(B) Host-Native 模式，把本 Skill 当作提示词工程指引，把渲染好的 prompt 交给宿主 Agent 自带的图像工具出图；(C) Advisor 模式，宿主无任何图像工具时退化为高质量 prompt 顾问。涵盖 18 大类、80+ 个结构化模板，覆盖海报 / UI / 产品 / 信息图 / 学术图 / 技术架构图 / 漫画 / 头像 / 流程板 / 电影分镜 / IP 周边 / 编辑工作流等场景。.

ConardLi/garden-skills · 177 tokens

personal-website

Generate a beautiful personal homepage (linktree-style) and publish it online for the user. Reads user info from /.clacky/agents/USER.md and AI info from /.clacky/agents/SOUL.md. Returns a public URL the user can share. Trigger on: "profile card", "homepage", "personal page", "generate my card", "make my card"…

clacky-ai/openclacky · 123 tokens

winui-design

Use when designing, reviewing, or fixing WinUI 3: sample and control discovery with winapp find-ui, layout planning, control choice, Fluent Design alignment, Light/Dark/High Contrast theming, typography, spacing, brushes, accessibility, and XAML data-binding design. Load before authoring new XAML, reviewing UI PRs…

microsoft/win-dev-skills · 119 tokens

winui-wpf-migration

Migrate WPF applications to WinUI 3 — namespace replacement (System.Windows → Microsoft.UI.Xaml), control mapping (DataGrid→ListView, WrapPanel→ItemsRepeater, TabControl→TabView), threading (Dispatcher→DispatcherQueue), imaging (System.Drawing→BitmapImage), MVVM conversion to CommunityToolkit.Mvvm, and…

microsoft/win-dev-skills · 100 tokens