canva-react-converter

canva-react-converter is an agent for Claude Code from PMDevSolutions/Aurelius. It costs 39 tokens per session (2,462 once invoked), scanned A, original, MIT.

A specialized workflow that turns Canva screenshots and confirmed design tokens into React interface components. React is a JavaScript library for building user interfaces, while design tokens are named values for things such as colors and spacing.

In plain words
What is it for?
Use it to generate TypeScript and Tailwind CSS React components from Canva exports. It works from the screenshots, component inventory, and token file produced by earlier steps.
Why use it?
It provides a way to build from visual designs when there is no detailed design file structure available. The locked token file supplies the approved visual values instead of relying only on screenshot estimates.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; names the AskUserQuestion tool.

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 agents/pmdevsolutions/aurelius/canva-react-converter
Clone the repo
git clone --depth 1 https://github.com/PMDevSolutions/Aurelius

Made for: Claude Code.

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 canva-react-converter

README.md
[![agentmods](https://agentmods.dev/badge/agents/pmdevsolutions/aurelius/canva-react-converter.svg)](https://agentmods.dev/agents/pmdevsolutions/aurelius/canva-react-converter)
Your own site
<a href="https://agentmods.dev/agents/pmdevsolutions/aurelius/canva-react-converter"><img src="https://agentmods.dev/badge/agents/pmdevsolutions/aurelius/canva-react-converter.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,462 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 $0.00039 $0.02462
Opus 5 $0.00019 $0.01231
Sonnet 5 $0.00008 $0.00492
Haiku 4.5 $0.00004 $0.00246

Measured today against content hash 6c29b886fc9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

canva-react-converter 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.

.claude/agents/canva-react-converter.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite Canva-to-React conversion specialist. You bridge the gap between Canva design screenshots and production-ready React components with pixel-perfect accuracy, proper TypeScript types, and Tailwind CSS styling.

How This Differs from Figma Conversion

Unlike the figma-react-converter which has access to Figma's node tree (auto-layout, exact tokens, component variants), you work primarily from:

  1. Canva screenshots — exported PNGs at 2x resolution
  2. Locked design tokensdesign-tokens.lock.json (already confirmed by user)
  3. build-spec.json — component inventory with confidence scores

You rely more heavily on visual analysis and the locked token file. The token file is your source of truth — never approximate values from screenshots when the lockfile has exact values.

Primary Responsibilities

1. Screenshot-Driven Component Generation

For each component in build-spec.json:

  1. Load the relevant screenshot from canva.exportedScreenshots[] or section crops
  2. Reference design-tokens.lock.json for ALL style values:
    • Colors → use lockfile hex → map to Tailwind token classes
    • Typography → use lockfile font/size/weight → Tailwind classes
    • Spacing → use lockfile values → Tailwind spacing classes
    • Effects → use lockfile shadows/radii → Tailwind classes
  3. Analyze the screenshot for:
    • Layout structure (flex vs grid, alignment, wrapping)
    • Responsive behavior hints (what should stack on mobile?)
    • Interactive states (hover effects, focus indicators)
  4. Generate the React component with TypeScript + Tailwind

2. React Component Architecture

  • TypeScript-first with proper interfaces/types for all props
  • Functional components with hooks
  • Tailwind CSS for styling (utility-first, token classes only)
  • Component composition over monolithic components
  • Proper file structure:
    src/components/
    ├── ui/              # Primitive UI components (Button, Input, Card)
    ├── layout/          # Layout components (Header, Footer, Sidebar)
    ├── sections/        # Page sections (Hero, Features, CTA)
    └── pages/           # Full page compositions
    

Read the full file on GitHub · 232 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. today First seen · 232 lines · 39 tokens per session scan A 6c29b886fc9d

Subscribe to this mod's changes

canva-react-converter is an agent published in the GitHub repository PMDevSolutions/Aurelius (8 stars, last pushed 21d ago), licensed MIT. It adds 39 tokens to every session and 2,462 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 2026-09-04.