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 agentmods add agents/pmdevsolutions/aurelius/canva-react-convertergit clone --depth 1 https://github.com/PMDevSolutions/AureliusWrote 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/agents/pmdevsolutions/aurelius/canva-react-converter)<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>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 | $0.00039 | $0.02462 |
| Opus 5 | $0.00019 | $0.01231 |
| Sonnet 5 | $0.00008 | $0.00492 |
| Haiku 4.5 | $0.00004 | $0.00246 |
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.
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:
- Canva screenshots — exported PNGs at 2x resolution
- Locked design tokens —
design-tokens.lock.json(already confirmed by user) - 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:
- Load the relevant screenshot from
canva.exportedScreenshots[]or section crops - Reference
design-tokens.lock.jsonfor 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
- 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)
- 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
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.
- today First seen · 232 lines · 39 tokens per session scan A 6c29b886fc9d
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.
Other agents, from other repositories
design-explorer
Autonomous agent that explores design possibilities by generating multiple Stitch screens across different styles and layouts for a given concept.
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
genpage-edit-planner
Plans edits to an existing generative page. Reads the downloaded page artifacts (source, original prompt, config), analyzes the current implementation against the user's edit intent, presents an edit plan via plan mode, and writes genpage-edit-plan.md for the orchestrator to execute. Called by the genpage skill — not…
docs-reviewer
Lean docs reviewer that dispatches reviews docs for a particular skill.
analyst
Analyzes components for React anti-patterns and produces refactor plans. Use when starting a new refactor subtask.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".