3fn/DesignerPunk
DesignerPunk Design System - True Native cross-platform design system with mathematical foundations
Copy this rig
# review before running: this installs third-party code
$ npx degit 3fn/DesignerPunk/.claude ./rig-designerpunk # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit 3fn/DesignerPunk/.claude/skills/_fixture-skill .claude/skills/_fixture-skill $ npx degit 3fn/DesignerPunk/.claude/skills/adaptive .claude/skills/adaptive $ npx degit 3fn/DesignerPunk/.claude/skills/edge-to-edge .claude/skills/edge-to-edge $ npx degit 3fn/DesignerPunk/.claude/skills/impeccable .claude/skills/impeccable $ npx degit 3fn/DesignerPunk/.claude/skills/navigation-3 .claude/skills/navigation-3 $ npx degit 3fn/DesignerPunk/.claude/skills/theming-styles .claude/skills/theming-styles
$ curl -fsSL --create-dirs -o .claude/agents/ada.md https://raw.githubusercontent.com/3fn/DesignerPunk/main/.claude/agents/ada.md $ curl -fsSL --create-dirs -o .claude/agents/data.md https://raw.githubusercontent.com/3fn/DesignerPunk/main/.claude/agents/data.md $ curl -fsSL --create-dirs -o .claude/agents/kenya.md https://raw.githubusercontent.com/3fn/DesignerPunk/main/.claude/agents/kenya.md $ curl -fsSL --create-dirs -o .claude/agents/leonardo.md https://raw.githubusercontent.com/3fn/DesignerPunk/main/.claude/agents/leonardo.md $ curl -fsSL --create-dirs -o .claude/agents/lina.md https://raw.githubusercontent.com/3fn/DesignerPunk/main/.claude/agents/lina.md $ curl -fsSL --create-dirs -o .claude/agents/sparky.md https://raw.githubusercontent.com/3fn/DesignerPunk/main/.claude/agents/sparky.md $ curl -fsSL --create-dirs -o .claude/agents/stacy.md https://raw.githubusercontent.com/3fn/DesignerPunk/main/.claude/agents/stacy.md $ curl -fsSL --create-dirs -o .claude/agents/thurgood.md https://raw.githubusercontent.com/3fn/DesignerPunk/main/.claude/agents/thurgood.md $ curl -fsSL --create-dirs -o .claude/agents/ada.md https://raw.githubusercontent.com/3fn/DesignerPunk/main/canonical/_consumer-output/cc/.claude/agents/ada.md $ curl -fsSL --create-dirs -o .claude/agents/data.md https://raw.githubusercontent.com/3fn/DesignerPunk/main/canonical/_consumer-output/cc/.claude/agents/data.md $ curl -fsSL --create-dirs -o .claude/agents/kenya.md https://raw.githubusercontent.com/3fn/DesignerPunk/main/canonical/_consumer-output/cc/.claude/agents/kenya.md $ curl -fsSL --create-dirs -o .claude/agents/leonardo.md https://raw.githubusercontent.com/3fn/DesignerPunk/main/canonical/_consumer-output/cc/.claude/agents/leonardo.md $ curl -fsSL --create-dirs -o .claude/agents/lina.md https://raw.githubusercontent.com/3fn/DesignerPunk/main/canonical/_consumer-output/cc/.claude/agents/lina.md $ curl -fsSL --create-dirs -o .claude/agents/sparky.md https://raw.githubusercontent.com/3fn/DesignerPunk/main/canonical/_consumer-output/cc/.claude/agents/sparky.md $ curl -fsSL --create-dirs -o .claude/agents/stacy.md https://raw.githubusercontent.com/3fn/DesignerPunk/main/canonical/_consumer-output/cc/.claude/agents/stacy.md $ curl -fsSL --create-dirs -o .claude/agents/thurgood.md https://raw.githubusercontent.com/3fn/DesignerPunk/main/canonical/_consumer-output/cc/.claude/agents/thurgood.md $ curl -fsSL --create-dirs -o .claude/agents/_fixture.md https://raw.githubusercontent.com/3fn/DesignerPunk/main/canonical/_fixture-output/cc/.claude/agents/_fixture.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} MCP servers (4)
| server | source | est. tokens |
|---|---|---|
| documentation env: MCP_STEERING_DIR | local / custom | 2.5k |
| designerpunk-docs env: WORKSPACE_ROOT | local / custom | 2.5k |
| designerpunk-application env: COMPONENTS_DIR, TOKEN_INDEX_DIR | local / custom | 2.5k |
| designerpunk-product env: COMPONENT_DIR, PRODUCT_DIR, TOKEN_INDEX_DIR | local / custom | 2.5k |
Skills (6)
Subagents (47)
| ada | Rosetta token specialist — <redacted>, mathematical foundations (modular scale, baseline grid), token governance & compliance, Token-Family docs, cross-platform token output (CSS/Swift/Kotlin), the ex |
| data | Android platform engineer — implements product screens in Jetpack Compose/Kotlin, consuming DesignerPunk Android tokens and components. Use for Android screen implementation, Compose patterns, Android |
| kenya | iOS platform engineer — implements product screens in SwiftUI/Swift, consuming DesignerPunk iOS tokens and components. Use for iOS screen implementation, SwiftUI patterns, iOS accessibility (VoiceOver |
| leonardo | Cross-platform product architect. Use for screen/flow specification, component & pattern selection (via Application MCP), layout specification, token-selection guidance for product screens, cross-plat |
| lina | Stemma component specialist — component scaffolding & development, platform implementations (web/iOS/Android), behavioral contract testing, component schemas & token integration, inheritance/family ar |
| sparky | Web platform engineer — Web Components implementation, DesignerPunk token and component consumption, Web accessibility, and native screen development. Implements Leonardo's product-screen specs in Web |
| stacy | Product governance, quality assurance & execution-claims verification — process quality, test coverage verification, cross-platform parity auditing, spec structure governance, lessons-learned capture, |
| thurgood | Test governance, audit, spec standards & Civitas steward. Use for test-suite health audits, coverage-gap analysis, test-failure investigation, formalizing design outlines into specs (requirements/desi |
| ada | Rosetta token specialist — <redacted>, mathematical foundations (modular scale, baseline grid), token governance & compliance, Token-Family docs, cross-platform token output (CSS/Swift/Kotlin), the ex |
| data | Android platform engineer — implements product screens in Jetpack Compose/Kotlin, consuming DesignerPunk Android tokens and components. Use for Android screen implementation, Compose patterns, Android |
| kenya | iOS platform engineer — implements product screens in SwiftUI/Swift, consuming DesignerPunk iOS tokens and components. Use for iOS screen implementation, SwiftUI patterns, iOS accessibility (VoiceOver |
| leonardo | Cross-platform product architect. Use for screen/flow specification, component & pattern selection (via Application MCP), layout specification, token-selection guidance for product screens, cross-plat |
| lina | Stemma component specialist — component scaffolding & development, platform implementations (web/iOS/Android), behavioral contract testing, component schemas & token integration, inheritance/family ar |
| sparky | Web platform engineer — Web Components implementation, DesignerPunk token and component consumption, Web accessibility, and native screen development. Implements Leonardo's product-screen specs in Web |
| stacy | Product governance, quality assurance & execution-claims verification — process quality, test coverage verification, cross-platform parity auditing, spec structure governance, lessons-learned capture, |
| thurgood | Test governance, audit, spec standards & Civitas steward. Use for test-suite health audits, coverage-gap analysis, test-failure investigation, formalizing design outlines into specs (requirements/desi |
| _fixture | Standing pipeline fixture (Spec 122 C10.3) — exercises one member of every content class and transform disposition; emitted only under canonical/_fixture-output; no runtime ever loads it. |
| ada-prompt.md.attribution | — |
| ada | Rosetta token specialist — <redacted>, mathematical foundations (modular scale, baseline grid), token governance & compliance, Token-Family docs, cross-platform token output (CSS/Swift/Kotlin), the ex |
| ada.json.attribution | — |
| data-prompt.md.attribution | — |
| data | Android platform engineer — implements product screens in Jetpack Compose/Kotlin, consuming DesignerPunk Android tokens and components. Use for Android screen implementation, Compose patterns, Android |
| data.json.attribution | — |
| kenya-prompt.md.attribution | — |
| kenya | iOS platform engineer — implements product screens in SwiftUI/Swift, consuming DesignerPunk iOS tokens and components. Use for iOS screen implementation, SwiftUI patterns, iOS accessibility (VoiceOver |
| kenya.json.attribution | — |
| leonardo-prompt.md.attribution | — |
| leonardo | Cross-platform product architect. Use for screen/flow specification, component & pattern selection (via Application MCP), layout specification, token-selection guidance for product screens, cross-plat |
| leonardo.json.attribution | — |
| lina-prompt.md.attribution | — |
| lina | Stemma component specialist — component scaffolding & development, platform implementations (web/iOS/Android), behavioral contract testing, component schemas & token integration, inheritance/family ar |
| lina.json.attribution | — |
| sparky-prompt.md.attribution | — |
| sparky | Web platform engineer — Web Components implementation, DesignerPunk token and component consumption, Web accessibility, and native screen development. Implements Leonardo's product-screen specs in Web |
| sparky.json.attribution | — |
| stacy-prompt.md.attribution | — |
| stacy | Product governance, quality assurance & execution-claims verification — process quality, test coverage verification, cross-platform parity auditing, spec structure governance, lessons-learned capture, |
| stacy.json.attribution | — |
| thurgood-prompt.md.attribution | — |
| thurgood | Test governance, audit, spec standards & Civitas steward. Use for test-suite health audits, coverage-gap analysis, test-failure investigation, formalizing design outlines into specs (requirements/desi |
Hooks (21)
| event | matcher | runs |
|---|---|---|
| Manual | * | Check platform parity for the token system: (1) identify all token source files in src/tokens/ that have been modified (check git status or compare timestamps), (2) verify that corresponding platform output files in src/tokens/platforms/ re |
| Manual | * | Query Token-Governance.md via MCP for the current governance rules. Then analyze the token files in src/tokens/ and src/tokens/semantic/ to verify: (1) all semantic tokens reference valid primitives, (2) no hard-coded values bypass the prim |
| Manual | * | Analyze test coverage for the token system by: (1) listing all token files in src/tokens/, (2) checking which have corresponding test files in src/tokens/__tests__/, (3) identifying token families with no tests or minimal coverage. Cross-re |
| Manual | * | Run the token formula validation tests using `npx jest --config jest.config.js --testPathPatterns='tokens/__tests__'` and `npx jest --config jest.config.js --testPathPatterns='validators/__tests__'`. Report any failures with analysis of whi |
| Manual | * | Analyze the component directory structure in src/components/ to verify each component has: (1) types.ts with proper TypeScript interfaces, (2) platform implementations in platforms/web/, platforms/ios/, platforms/android/, (3) test files, ( |
| Manual | * | Query Token-Governance.md and Token-Quick-Reference.md via MCP for current governance rules and token routing. Then analyze component files in src/components/ to verify: (1) no hard-coded color, spacing, typography, or shadow values that sh |
| Manual | * | Analyze the component directory structure in src/components/ to verify platform parity: (1) for each component, check that web, iOS, and Android implementations exist in their respective platform directories, (2) compare the behavioral cont |
| Manual | * | Query Component-Inheritance-Structures.md and Test-Behavioral-Contract-Validation.md via MCP. Then analyze the component files in src/components/ to verify: (1) all components implement their required behavioral contracts, (2) inheritance s |
| Manual | * | Query Component-Inheritance-Structures.md via MCP to understand which behavioral contracts include accessibility requirements. Query Token-Governance.md to understand WCAG-related token compliance requirements. Then audit accessibility test |
| Manual | * | Query Process-Spec-Planning.md and Process-Ta<redacted>.md via MCP for current spec standards. Then scan all spec directories under .kiro/specs/ to validate: (1) requirements.md files follow EARS patterns and INCOSE quality rules, (2) desig |
| Manual | * | Query Test-Development-Standards.md and Test-Failure-Audit-Methodology.md via MCP for current standards and audit methodology. Then analyze the test suite: (1) run `npm test` to identify any failing tests, (2) scan test directories (src/__t |
| AgentSpawn | * | git status --porcelain |
| AgentSpawn | * | git status --porcelain |
| AgentSpawn | * | git status --porcelain |
| AgentSpawn | * | git status --porcelain |
| AgentSpawn | * | git status --porcelain |
| AgentSpawn | * | git status --porcelain |
| AgentSpawn | * | git status --porcelain |
| AgentSpawn | * | git status --porcelain |
| AgentSpawn | * | git status --porcelain |
| AgentSpawn | * | git status --porcelain |
Cursor rules (5)
Kiro (17 steering · 40 specs · 12 hook files)
Specs: 001-token-data-quality-fix, 002-test-infrastructure-fixes, 003-release-analysis-test-cleanup, 004-icon-system, 005-cta-button-component, 006-icon-size-tokens, 007-accessibility-token-family, 008-icon-web-component-conversion, 009-variant-attribute-standardization, 010-container-component, 011-inset-token-renaming, 011-release-system-test-fixes… (loaded on demand, not counted in context tax)
MCP config: 23 auto-approved tool(s)
How Kiro files are scored: methodology.