design systems agents

68 tagged design systems, measured the same way as everything else here.

Browse within: design-engineering 18npm-package 15hackathon 11claude-design 7claude-plugin 7design handoff 7

synthesis-master

01

HermeticOrmus/LibreUIUX-Claude-Code

Agent Claude Code

Grand orchestrator of all LibreUIUX plugins. Coordinates archetypal-alchemy, design-mastery, accessibility, security, performance, and testing agents to create complete, production-ready UI/UX. The conductor of the plugin symphony. Use PROACTIVELY for any comprehensive UI/UX work.

100 3mo ago A 65 tokens original MIT

HermeticOrmus/LibreUIUX-Claude-Code

Agent

Master of Jungian archetypes + Tarot symbolism for UI/UX design. Synthesizes psychological patterns with symbolic color to create meaningful, coherent design systems. Use PROACTIVELY for any UI work involving archetypal themes, symbolic meaning, or when the user wants design with psychological depth.

100 3mo ago A 66 tokens original MIT

HermeticOrmus/LibreUIUX-Claude-Code

Agent

Build production-ready Web3 applications, smart contracts, and decentralized systems. Implements DeFi protocols, NFT platforms, DAOs, and enterprise blockchain integrations. Use PROACTIVELY for smart contracts, Web3 apps, DeFi protocols, or blockchain infrastructure.

100 3mo ago A 56 tokens original MIT

CLAUDE

04

jubscodes/get-shit-pretty

Agent

Agent source of truth: gsp/agents/gsp-{name}.md. Never edit .claude/agents/ directly — those are symlinks.

53 2mo ago A 0 tokens original MIT

gsp-polisher

05

jubscodes/get-shit-pretty

Agent

Detects and fixes AI-slop craft failures in React/Tailwind codebases. Spawned by /gsp-polish.

53 2mo ago A 31 tokens original MIT

glebis/humane-agentic-design

Agent

An ordinary person reacting to copy, slogans, brand values, or marketing materials — gut-level, unfiltered, no expertise. Launch it when you want to know how something lands, not whether it is well-argued. Accepts an optional persona brief in the prompt (age, place, work, media diet, relationship to the category)…

27 22d ago A 96 tokens original MIT

brand-architect

08

HermeticOrmus/design-mastery-claude-code

Agent

Expert in building comprehensive brand identity systems from strategy through visual execution. Guides the complete brand development journey from positioning and values through logo, typography, color palette, voice, and brand guidelines. Use for brand creation, rebranding, or brand system development.

11 3mo ago A 54 tokens original MIT

design-master

09

HermeticOrmus/design-mastery-claude-code

Agent

Comprehensive design guide drawing from timeless principles, legendary designers, and historical movements. Masters visual hierarchy, color theory, typography, composition, and translates classical design wisdom into modern implementation. Use PROACTIVELY for any UI/UX design, component creation, or visual…

11 3mo ago A 59 tokens original MIT

visual-historian

10

HermeticOrmus/design-mastery-claude-code

Agent

Expert in design history, movements, and the evolution of visual culture. Connects contemporary design decisions to their historical roots. Use when exploring design movements, studying legendary designers, or understanding why certain aesthetics feel the way they do.

11 3mo ago A 50 tokens original MIT

build-triage

11

stag-build/phonebook

Agent Claude Code

Runs a build/test command (gradle, xcodebuild, npm, vitest) and returns a compressed failure summary — first failing task, error message, file:line — instead of raw logs.

8 yesterday A 46 tokens original MIT

docs-writer

12

stag-build/phonebook

Agent Claude Code

Writes or updates user-facing docs (README sections, setup guides, CI recipes) from the actual code and PLAN.md. Not for API design or code changes.

8 yesterday A 36 tokens original MIT

implementer

13

stag-build/phonebook

Agent Claude Code

Implements a well-specified, self-contained coding task (one module, one command, one component) from a detailed spec. Not for architecture decisions or cross-cutting changes.

8 yesterday A 39 tokens original MIT

memi-design/design-sandbox

Agent Claude Code

Scaffolds shadcn-based React compositions into src/app/sandbox/page.tsx from a spec (from screenshot-decoder) or a plain brief. Use AFTER screenshot-decoder, or directly when the user gives a text-only brief.

7 1mo ago A 53 tokens original MIT

motion-director

15

memi-design/design-sandbox

Agent Claude Code

Adds motion to a static composition. Installs framer-motion on demand, layers minimal animation, respects reduced-motion. Use AFTER component-scaffolder, only when the brief calls for motion.

7 1mo ago A 42 tokens original MIT

screenshot-decoder

16

memi-design/design-sandbox

Agent Claude Code

Read-only. Decodes a screenshot, image URL, Figma node, or written brief into a structured component spec. Use FIRST whenever the user provides a visual or a non-trivial brief, before any scaffolding.

7 1mo ago A 49 tokens original MIT

opensesh/canvas-to-code

Agent

Classifies each visual unit's data source. Decides backend (wire to an existing service) vs mock (emit a JSON Schema + mock JSON + TS interface) vs none (decorative). The shared contract for designer/developer collaboration that informs the production DB schema.

6 2mo ago A 61 tokens original MIT

opensesh/canvas-to-code

Agent

The keystone agent. Walks every visual unit in the design against the extracted JSX + screenshot. Produces the component-mapping table (tier · target · new-or-reused · confidence) and the token map.

6 2mo ago A 50 tokens original MIT

canvas-to-code-pm

19

opensesh/canvas-to-code

Agent

Conversational PM orchestrator for Canvas-to-Code. Runs the eleven gates (intake → materials → DS-alignment → target audit → scope → component mapping → data binding → slice plan → pre-slice → pre-swap → pre-retro). Never writes feature code.

6 2mo ago A 61 tokens original MIT

demo-director

20

ashishpatill/tell-proof

Agent Cursor

Tell build sprint demo director. Use proactively before review to rehearse the 3-minute demo, verify rules compliance, backup fallbacks, and CONTRIBUTIONS.md attribution. Best with GPT 5.5 for narrative; Composer for hardening.

1 5d ago A 52 tokens original MIT

mcp-engineer

21

ashishpatill/tell-proof

Agent Cursor

Tell MCP server specialist. Use proactively for packages/mcp, tell tools, install-info, .cursor/mcp.json, and Cursor Agent chat integration. Best with Composer 2.5.

1 5d ago A 44 tokens original MIT

orchestrator

22

ashishpatill/tell-proof

Agent Cursor

Tell build sprint orchestrator. Use proactively when starting a milestone, splitting parallel work, or merging subagent output. Best with Composer 2.5. Reads BUILD.md milestones M1-M10 and ORCHESTRATION.md multitask plan.

1 5d ago A 53 tokens original MIT