agentic-webdesign-framesmith

An open-source visual design canvas for AI coding agents. It renders interface plans as HTML and CSS screenshots in a browser, so designs can be reviewed before framework code is written.

In plain words
What is it for?
Use it to sketch interfaces, set design tokens such as colors and spacing, render screenshots, score designs, detect clichés, and apply or review fixes.
Why use it?
Agents can produce technically valid interfaces that are hard to judge from code alone. A rendered canvas makes layout and design problems visible and supports evaluation and revisions.

Skill for Claude CodeCodex

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/s3yed/appie-kit/agentic-webdesign-framesmith
Any agent
npx skills add S3YED/appie-kit --skill agentic-webdesign-framesmith
Clone the repo
git clone --depth 1 https://github.com/S3YED/appie-kit

Made for: Claude Code, Codex.

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 869 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 $0.00053 $0.00869
Opus 5 $0.00026 $0.00434
Sonnet 5 $0.00011 $0.00174
Haiku 4.5 $0.00005 $0.00087

Measured 3d ago against content hash bb5677f51cb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentic-webdesign-framesmith 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 3d 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.

skills/agentic/agentic-webdesign-framesmith/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Framesmith — Visual Design Canvas for AI Agents

What it is

Open-source MCP server (MIT) that gives AI coding agents a visual design canvas. Agents author UI via a scene graph, rendered as HTML/CSS through headless Chromium to PNG screenshots. Includes a standalone browser viewer, design evaluation, pattern library, and auto-fix.

Quick start

# Start the viewer in a terminal
npx -p framesmith framesmith-viewer

# Add to Claude Code
claude mcp add framesmith -- npx framesmith

MCP Tools

Canvas Management

  • canvas_create — Create a new canvas
  • canvas_bind — Bind workspace/repo to framesmith
  • init — Idempotent onboarding: bind repo, scaffold conventions, return workflow cheatsheet

Design

  • batch_design — Build UI with frames, text, icons, components, gradients. Returns { varName: nodeId } map
  • apply_preset — Apply a design preset
  • set_variables — Set design tokens (colors, spacing, fonts)

Evaluation & Fixing

  • canvas_evaluate — Score 0-100 across 6 categories + cliché detection. Returns READY/NOT READY
  • canvas_autofix — Mechanical fixes for flagged issues
  • canvas_revise — Targeted revision for specific issues

Export & Comparison

  • screenshot_responsive — Preview at mobile/tablet/desktop
  • canvas_diff — Visual before/after comparison
  • export — Save to PNG/PDF

Import

  • canvas_import_html — Import existing HTML/CSS for inspection
  • canvas_import_url — Import from live URL with drift detection
  • import_design_md — Import DESIGN.md for token extraction

Workflow

1. canvas_create → get canvas ID
2. apply_preset or set_variables → design tokens
3. batch_design → build the UI
4. canvas_evaluate → score the result
5. If < 95: canvas_autofix or canvas_revise → re-evaluate
6. screenshot_responsive → preview at breakpoints
7. canvas_diff → compare iterations
8. export → save final design

Design System Support

  • Workspace → project → canvas token inheritance
  • DESIGN.md import
  • Style presets (Material, glassmorphism, etc.)

Read the full file on GitHub · 92 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. 3d ago First seen · 92 lines · 53 tokens per session scan A bb5677f51cb6

Subscribe to this mod's changes

agentic-webdesign-framesmith is a skill published in the GitHub repository S3YED/appie-kit (6 stars, last pushed 7d ago), licensed MIT. It adds 53 tokens to every session and 869 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

deck-open-slide-canvas

锁死 1920×1080 画布, React 组件级自由组合, 不绑模板.

nexu-io/html-anything · 28 tokens

hr-onboarding

A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".

nexu-io/open-design · 62 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

deck-course-module

暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.

nexu-io/html-anything · 25 tokens