What is design-to-code?

A process for turning Figma designs into organised Flutter code, including reusable assets and project-specific UI structure. Flutter is a toolkit for building apps from one codebase across platforms.

Extracting and organising SVGs, icons, photos, and other images from Figma for a Flutter app. It also covers checking for existing assets, handling missing files, and regenerating the app's asset references.

It reduces guesswork when transferring designs into code, especially around asset locations, missing exports, and generated asset references. This helps the implementation match the project's expected structure.

design-to-code — Skill for Claude Code and Codex by anoopsg

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/anoopsg/agent_rules

agentmods

npx agentmods add skills/anoopsg/agent_rules/design-to-code

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/anoopsg/agent_rules/design-to-code/github.svg)](https://agentmods.dev/skills/anoopsg/agent_rules/design-to-code)

Your own site

<a href="https://agentmods.dev/skills/anoopsg/agent_rules/design-to-code"><img src="https://agentmods.dev/badge/skills/anoopsg/agent_rules/design-to-code/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/anoopsg/agent_rules/design-to-code"><img src="https://agentmods.dev/badge/skills/anoopsg/agent_rules/design-to-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,389 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 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.

Model	Per session	Once invoked
Fable 5.1	$0.00022	$0.02389
Opus 5.5	$0.00009	$0.00956
Sonnet 5.5	$0.00004	$0.00478
Haiku 4.5	$0.00002	$0.00239

Measured 5d ago against content hash d3e707da8d6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

design-to-code 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 5d 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.

src/exclusive/skills/design-to-code/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design-to-Code Skill

1. Asset Management

1.1 Organization

All assets must be placed in the packages/app_ui/assets/ directory following this structure:

Icons: assets/icons/ (SVG)
Images: assets/images/ (SVG illustrations and PNG, JPEG, WebP — e.g., photos, hero banners)
Animations: assets/animations/
No Feature Folders: Do not create feature-specific subfolders (e.g., login/, auth/) within these asset directories. Keep the structure flat by asset type to avoid issues if an asset is later reused in another feature.

1.2 Verification & Generation

Verify: Before adding an asset, check packages/app_ui/assets/ to see if it already exists.
Add: Place the new asset in the appropriate folder.
Generate: Run melos run generate to update the AppAssets class.
Usage: Use AppAssets to reference the asset in code:
```
AppAssets.icons.google.svg();
```

1.3 Handling Missing or Unplaced Assets

When extracting from Figma via the MCP server, assets might not be marked for export or could be missing entirely:

Detection: If the MCP server cannot locate or export an expected visual asset.
Placeholders: Use a standardized placeholder widget to maintain layout integrity. Always include a TODO comment for traceability:
```
const SizedBox(width: 120, height: 120); // TODO(design): Replace with exported asset. @Source: <Page> > <Frame> > <Element>
```
Notification: Explicitly notify the user that the asset was missing from the exportable Figma assets and request they mark it for export or provide it manually. NEVER use the Figma MCP API asset URL (https://www.figma.com/api/mcp/asset/...) directly in the code (e.g. via Image.network).

1.4 Asset Usage

No package: Argument: Generated asset widgets already resolve to app_ui. Never pass package: or define a package constant.
Tint Icons: Use colorFilter: ColorFilter.mode(context.$.colors.x, BlendMode.srcIn); never edit the SVG or hardcode colors.
Material Icons: Use Icon(Icons.x) for stock Material icons instead of exporting SVGs.

Read the full file on GitHub · 136 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.

5d ago Changed · +7 lines d3e707da8d6e
12d ago Changed dea1bc87c9ff
2mo ago First seen · 129 lines · 22 tokens per session scan A 8abe7a9fe700

Subscribe to this mod's changes

design-to-code is a skill published in the GitHub repository anoopsg/agent_rules (2 stars, last pushed 5d ago), licensed MIT. It adds 22 tokens to every session and 2,389 once invoked, about $0.0001 per session on Opus 5.5. 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.

Design and UX Mobile agent-rules agent-skills

display-glasses-with-jetpack-compose-glimmer

Provides guidelines for developing projected Android XR apps for display glasses using the Jetpack Compose Glimmer UI toolkit. Covers Glimmer design principles, workflows, and interaction models for the glasses form factor. Use this skill to build an Android XR Augmented Experience app with Jetpack Compose Glimmer.…

android/skills · 112 tokens

glance-canonical-layouts

Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).

android/skills · 56 tokens

expo-design-system

Build and maintain a design system inside an Expo app - a reusable theme of design tokens (color, spacing, typography, radius, shadow, motion), reusable component structure with variant/size/state prop conventions, and rules for when to extract a repeated view into a shared component. Use when creating or organizing…

expo/skills · 197 tokens

design-to-code