By ddfourtwo
Visual thinking surface for AI-human collaboration. Claude writes research, strategy, copy, designs, code, or any other content as frames on a shared real-time canvas — so teams can see, compare, and refine AI output without drowning in chat. Skills library captures org SOPs so the team's best patterns propagate automatically. Bundles the MCP server + a Drafted skill + six slash commands (/drafted:status, /drafted:share, /drafted:new-project, /drafted:focus, /drafted:skills, /drafted:save-skill).
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Pan the Drafted canvas to a frame, lane, or layer
Start a new project on the Drafted surface — any kind of work (research, strategy, copy, design, code)
Capture reusable guidance from this conversation as an org skill so teammates and future agents inherit it automatically
Get a shareable canvas URL for the active Drafted project
Find, load, or browse Drafted skills — the org's standard operating procedures captured as reusable agent instructions
Public mirror of the Claude Code plugin and Gemini CLI extension for Drafted.
Source of truth: the private ddfourtwo/drafted repo. Do not PR here — open issues at https://drafted.live.
Claude Code:
claude plugin marketplace add ddfourtwo/drafted-plugin
claude plugin install drafted@drafted
Gemini CLI:
gemini extensions install https://github.com/ddfourtwo/drafted-plugin
See the full install flow at https://drafted.live/install.
npx claudepluginhub ddfourtwo/drafted-plugin --plugin draftedMemory compression system for Claude Code - persist context across sessions
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Write feature specs, plan roadmaps, and synthesize user research faster. Keep stakeholders updated and stay ahead of the competitive landscape.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns