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 skills/punkadillo/figma-code-composer/component-architecturenpx skills add punkadillo/figma-code-composer --skill component-architecturegit clone --depth 1 https://github.com/punkadillo/figma-code-composerWrote 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/skills/punkadillo/figma-code-composer/component-architecture)<a href="https://agentmods.dev/skills/punkadillo/figma-code-composer/component-architecture"><img src="https://agentmods.dev/badge/skills/punkadillo/figma-code-composer/component-architecture.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 | $0.00094 | $0.05053 |
| Opus 5 | $0.00047 | $0.02527 |
| Sonnet 5 | $0.00019 | $0.01011 |
| Haiku 4.5 | $0.00009 | $0.00505 |
Grade A, and why
component-architecture 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 827 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resources
scripts/
validate-components.sh
references/
component-patterns.md
Component Architecture
This skill guides you through designing and implementing UI components using GoodVibes precision and analysis tools. Use this workflow when building React, Vue, or Svelte components with proper composition, state management, and performance optimization.
When to Use This Skill
Load this skill when:
- Building new UI components or component libraries
- Refactoring component hierarchies or composition patterns
- Optimizing component render performance
- Organizing component file structures
- Implementing design systems or atomic design patterns
- Migrating between component frameworks
- Reviewing component architecture for maintainability
Trigger phrases: "build component", "create UI", "component structure", "render optimization", "state lifting", "component composition".
Core Workflow
Phase 1: Discovery
Before building components, understand existing patterns in the codebase.
Step 1.1: Map Component Structure
Use discover to find all component files and understand the organization pattern.
discover:
queries:
- id: react_components
type: glob
patterns: ["**/*.tsx", "**/*.jsx"]
- id: vue_components
type: glob
patterns: ["**/*.vue"]
- id: svelte_components
type: glob
patterns: ["**/*.svelte"]
verbosity: files_only
What this reveals:
- Framework in use (React, Vue, Svelte, or mixed)
- Component file organization (feature-based, atomic, flat)
- Naming conventions (PascalCase, kebab-case)
- File colocation patterns (components with tests, styles)
Step 1.2: Analyze Component Patterns
Use discover to find composition patterns, state management, and styling approaches.
discover:
queries:
- id: composition_patterns
type: grep
pattern: "(children|render|slot|as\\s*=)"
glob: "**/*.{tsx,jsx,vue,svelte}"
- id: state_management
type: grep
pattern: "(useState|useReducer|reactive|writable|createSignal)"
glob: "**/*.{ts,tsx,js,jsx,vue,svelte}"
- id: styling_approach
type: grep
pattern: "(className|styled|css|tw`|@apply)"
glob: "**/*.{tsx,jsx,vue,svelte}"
- id: performance_hooks
type: grep
pattern: "(useMemo|useCallback|memo|computed|\\$:)"
glob: "**/*.{ts,tsx,js,jsx,vue,svelte}"
verbosity: files_only
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 827 lines · 94 tokens per session scan A 4b6c7938b32d
component-architecture is a skill published in the GitHub repository punkadillo/figma-code-composer (3 stars, last pushed 15d ago), licensed MIT. It adds 94 tokens to every session and 5,053 once invoked, about $0.0005 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.
Other skills, from other repositories
figma-codegen
Generate framework-aware code from a Figma design. Reads the project's stack profile and emits code matching the existing framework (React/Vue/Svelte/Next/etc.) and styling (Tailwind/CSS/CSS-in-JS), reusing existing components and design tokens instead of regenerating from scratch. Triggers whenever the user wants a…
from-intake
다른 워크스페이스에서 넘겨받은 자료에서 브랜드 근거를 뽑아 에셋에 반영한다.
accessibility-fundamentals
Reviews accessibility including WCAG, ARIA, keyboard navigation. Use when junior builds forms, buttons, modals, interactive elements, or asks "is this accessible", "a11y", "screen reader".
dpf-writing-plans
Use when a filed DPF backlog item needs an implementation plan before code is written.
aesthetic
Create aesthetically beautiful interfaces following proven design principles. Use when building UI/UX, analyzing designs from inspiration sites, generating design images with ai-multimodal, implementing visual hierarchy and color theory, adding micro-interactions, or creating design documentation. Includes workflows…
shadscan
Audit a React/shadcn app for missing UI fundamentals — accessibility, interaction, empty/error/loading states, form wiring, responsive shell, production polish — with the shadscan CLI, then route each real fix to the dev-flow skill that owns it. The third pre-deploy gate, alongside compliance-audit (legal) and…