v13.3.2 · MIT
Extract any website's complete design system with one command. DTCG tokens, semantic+primitive+composite, MCP server for Claude Code/Cursor/Windsurf, multi-platform emitters (iOS SwiftUI, Android Compose, Flutter, WordPress), Tailwind v4, Figma variables, shadcn/ui, CSS health audit, WCAG remediation, Chrome extension. MIT, Playwright, Node 20+.
v1.2.1 · MIT
Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured hardest on Claude Fable 5 (fable5), deep-studied on Sonnet 5, works on Opus 4.8 too. We publish our negative results. 82 raw benchmark runs.
v0.16.487 · MIT
Bring SynthesisUI design systems into any project - tokens, typed components, whole pages and an agent-ready CLAUDE.md manifest.
v0.1.0 · MIT
Figma to design.md — Convert Figma design tokens into structured design.md for AI-assisted coding (Cursor, Claude Code, Copilot)
v0.2.5 · MIT
Claude Code usage governor: compact professional output, context slimming, tool-output filtering, telemetry, and drift guardrails.
v2.0.0 · MIT
Quieter sessions for Claude Code: less narration, shorter tool output and concise answers focused on the result.
v9.7.0 · MIT
Your AI can write the UI. This makes sure it writes your UI. A deterministic scanner scores your design system 0-100 against 112 public repos, reads React and web components (Stencil, Lit), hands you a copy-paste fix prompt for each top finding, writes ru
v0.1.1 · MIT
Shorter replies with Claude Code. Save output token spend.
v0.1.179 · MIT
A context-compression plugin — small context windows (a 100K context is enough), 5x fewer tokens, month-long single sessions (billions of tokens), and compression quality — for all agents: pi, OpenCode, Codex, Claude Code, and more. billion-context is all
v0.4.0 · MIT
Stop wasting tokens and re-explaining your project every session. Recall gives Claude Code , Opencode durable memory — entirely offline.
v3.0.0 · Apache-2.0
Content-aware output compression for AI coding assistants. 36 specialized processors cut CLI output tokens by 60-99% (git, pytest, npm, terraform, kubectl, docker, and more) without losing errors, diffs, or stack traces.
v2.6.1 · MIT
A Claude Code plugin that acts as an intelligent harness for your development workflow: your codebase is read-only by default, every change passes through a Write Gate as planned and approved work, and craft tracks your project's history, design tokens, and decisions locally so Claude learns your taste and architectural preferences over time.
v3.34.6 · MIT
Framework-aware code intelligence MCP server — 88 framework integrations, 81 languages, 72.7% fewer input tokens to review a pull request, comprehension at parity
v1.4.0 · MIT
Tech-lead orchestration for Claude Code — the top-tier model (Fable) keeps architecture & decisions, cheap subagents (Sonnet/Opus) do the routine and the digging. Save tokens without losing quality.