By tonone-ai
Audits a codebase for hardcoded design tokens (colors, sizes, fonts) vs token references, reports coverage and gaps, and recommends pipeline improvements
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub tonone-ai/tonone --plugin tone-reconDesign and build networking infrastructure — VPCs, subnets, DNS, load balancers, firewall rules. Use when asked to "set up networking", "VPC design", "configure DNS", "load balancer setup", "network architecture", or "firewall rules".
Generate onboarding documentation — what this project does, how to set up locally, where things live, key decisions, how to deploy. Written for day-one engineers who know nothing. Use when asked for "onboarding docs", "new engineer guide", "how to get started", or "developer setup".
Implement a reusable, accessible, typed component from a design spec. Use when asked to "create a component", "build a widget", "implement this design", or "reusable UI element".
Verify observability posture — audit monitoring coverage, find blind spots, prioritize gaps. Use when asked "is monitoring sufficient", "observability review", "are we covered", or "pre-launch monitoring check".
ML reconnaissance — inventory all models, pipelines, data sources, and monitoring. Use when asked "what ML do we have", "model inventory", or "ML assessment".
Staff-level design system auditing, governance, documentation, validation, and communication — 40 skills, 4 agents, and 12 knowledge notes for the full design system lifecycle
Survey existing code samples — coverage, language parity, and freshness
Configures token-saving tools (rtk, caveman, graphify, context-mode) globally or per project. Allows auditing and calculating the token savings obtained.
Codebase exploration, refactoring, and quality analysis
Automated design system construction from repository analysis to production-ready implementation.
Adversarial multi-agent pipeline for Claude Code. GAN-style loops where generators produce artifacts, discriminators validate them, and feedback drives convergence.